CN112155602A - Method and device for determining optimal standard section of fetus - Google Patents

Method and device for determining optimal standard section of fetus Download PDF

Info

Publication number
CN112155602A
CN112155602A CN202011015507.6A CN202011015507A CN112155602A CN 112155602 A CN112155602 A CN 112155602A CN 202011015507 A CN202011015507 A CN 202011015507A CN 112155602 A CN112155602 A CN 112155602A
Authority
CN
China
Prior art keywords
standard
structural feature
section
tangent plane
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011015507.6A
Other languages
Chinese (zh)
Other versions
CN112155602B (en
Inventor
谢红宁
汪南
冼建波
梁喆
杨燕淇
吴海涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Aiyunji Information Technology Co Ltd
Original Assignee
Guangzhou Aiyunji Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Aiyunji Information Technology Co Ltd filed Critical Guangzhou Aiyunji Information Technology Co Ltd
Priority to CN202011015507.6A priority Critical patent/CN112155602B/en
Publication of CN112155602A publication Critical patent/CN112155602A/en
Priority to PCT/CN2021/096821 priority patent/WO2022062458A1/en
Application granted granted Critical
Publication of CN112155602B publication Critical patent/CN112155602B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/523—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for generating planar views from image data in a user selectable plane not corresponding to the acquisition plane
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
    • A61B8/0866—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving foetal diagnosis; pre-natal or peri-natal diagnosis of the baby
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Gynecology & Obstetrics (AREA)
  • Pregnancy & Childbirth (AREA)
  • Physiology (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)

Abstract

The invention discloses a method and a device for determining an optimal standard section of a fetus, wherein the method comprises the steps of obtaining the standard section of each frame of fetus ultrasonic image in multiple frames of fetus ultrasonic images, and determining the section value of the standard section of each frame of fetus ultrasonic image; and determining the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes according to all the tangent plane scores to serve as the optimal standard tangent plane. Therefore, after the standard section of the fetal ultrasound image is obtained, the method and the device do not need manual analysis to determine the optimal standard section of the fetal ultrasound image, can automatically determine the section score of the standard section of the fetal ultrasound image, intelligently select the standard section with the highest section score from all section scores, realize automatic determination of the optimal standard section, and can improve the accuracy and efficiency of determination of the optimal standard section of the fetal ultrasound image, thereby realizing accurate acquisition of the growth and development conditions of the fetus.

Description

Method and device for determining optimal standard section of fetus
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for determining an optimal standard section of a fetus.
Background
Because the development condition of the fetus can be known from the standard fetus section, especially the optimal fetus section, the optimal fetus section becomes a key point for accurately determining the growth and development condition of the fetus. The current method for determining the optimal standard section of the fetus comprises the following steps: and further, after the primary fetus standard tangent plane is obtained, the primary fetus standard tangent plane is analyzed by experienced workers, so that the final determination of the optimal fetus standard tangent plane is completed.
However, practice finds that, because the preliminary standard section of the fetus is determined directly from a single ultrasound image with a small data volume and because of limited experience and/or fatigue of workers, the accuracy of the determined optimal standard section of the fetus is low, and therefore, the growth and development conditions of the fetus cannot be accurately determined. Therefore, how to obtain an accurate and optimal standard fetus section is very important, so that the growth and development conditions of the fetus are accurately determined.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a device for determining an optimal standard section of a fetus, which can obtain an accurate optimal standard section of the fetus, thereby realizing accurate determination of the growth and development conditions of the fetus.
In order to solve the technical problem, the first aspect of the present invention discloses a method for determining an optimal standard section of a fetus, the method comprising:
obtaining a standard section of each frame of fetal ultrasonic image in a plurality of frames of fetal ultrasonic images, and determining section values of the standard sections of each frame of fetal ultrasonic images;
and determining a standard section corresponding to the highest section score from all the standard sections according to the section scores of all the standard sections, and taking the standard section as the optimal standard section of all the fetal ultrasonic images.
As an optional implementation manner, in the first aspect of the present invention, after determining the tangent score of the standard tangent plane of the fetal ultrasound image for each frame, the method further includes:
judging whether all the standard tangent planes belong to the same class of standard tangent planes;
and when all the standard sections are judged to belong to the same type of standard sections, triggering and executing the operation of determining the standard section corresponding to the highest section score from all the standard sections as the optimal standard section of all the fetal ultrasonic images according to the section scores of all the standard sections.
As an optional implementation manner, in the first aspect of the present invention, when it is determined that all the standard sections do not belong to the same category of standard sections, a classification operation is performed on the standard sections of all the fetal ultrasound images according to a preset classification manner to obtain at least two standard section sets, each standard section set includes at least one frame of standard section of the fetal ultrasound image, and all the standard sections included in each standard section set are standard sections of the same category;
wherein, according to the section scores of all the standard sections, determining the standard section corresponding to the highest section score from all the standard sections as the optimal standard section, and the method comprises the following steps:
and according to all the tangent plane scores corresponding to each standard tangent plane set, determining a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes included in each standard tangent plane set as the optimal standard tangent plane corresponding to each standard tangent plane set.
As an optional implementation manner, in the first aspect of the present invention, after determining, according to all the tangent plane scores corresponding to each standard tangent plane set, a standard tangent plane corresponding to a highest tangent plane score from all the standard tangent planes included in each standard tangent plane set, and as an optimal standard tangent plane corresponding to each standard tangent plane set, the method further includes:
performing normalization operation on the tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set to obtain the normalized tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set;
and screening the standard tangent plane corresponding to the highest normalized tangent plane score from all the standard tangent planes according to all the normalized tangent plane scores to serve as the optimal standard tangent plane corresponding to all the fetal ultrasonic images.
As an alternative embodiment, in the first aspect of the present invention, at least one structural feature exists in the standard tangential plane of each frame of the fetal ultrasound image, and each structural feature has a corresponding weight value;
and the determining the section score of the standard section of each frame of the fetal ultrasound image comprises the following steps:
determining a weight value corresponding to each structural feature of a standard section of each frame of the fetal ultrasonic image;
and calculating the section score of the standard section of each frame of the fetal ultrasound image based on the weight value corresponding to each structural feature of each standard section and the characteristic parameter of the structural feature.
As an optional implementation manner, in the first aspect of the present invention, the determining a weight value corresponding to each structural feature of a standard section of each frame of the fetal ultrasound image includes:
determining a key weight value influence factor corresponding to each structural feature of a standard tangent plane of each frame of the fetal ultrasound image, wherein the number of the key weight value influence factors corresponding to each structural feature is more than or equal to 1, and each key weight value influence factor has a corresponding sub weight value;
according to each key weight value influence factor corresponding to each structural feature, determining a sub weight value corresponding to each key weight value influence factor, and calculating the sum of all sub weight values corresponding to each structural feature to serve as the weight value corresponding to each structural feature.
The invention discloses a device for determining the optimal standard section of a fetus in a second aspect, which comprises:
the acquisition module is used for acquiring a standard section corresponding to each frame of fetal ultrasound image in a plurality of frames of fetal ultrasound images;
the first determining module is used for determining the section score of the standard section of each frame of the fetal ultrasonic image;
and the second determining module is used for determining a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes according to the tangent plane scores of all the standard tangent planes, and the standard tangent plane is used as the optimal standard tangent plane of all the fetal ultrasonic images.
As an alternative embodiment, in the second aspect of the present invention, the apparatus further comprises:
the first determining module is configured to determine whether all the standard tangent planes belong to the same class of standard tangent planes after the first determining module determines the tangent plane score of the standard tangent plane of each frame of the fetal ultrasound image, and when it is determined that all the standard tangent planes belong to the same class of standard tangent planes, trigger the second determining module to execute the operation of determining, as the optimal standard tangent plane of all the fetal ultrasound images, the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes according to the tangent plane scores of all the standard tangent planes.
As an alternative embodiment, in the second aspect of the present invention, the apparatus further comprises:
the classification module is configured to, when the first judgment module judges that all the standard sections do not belong to the same category of standard sections, perform classification operation on the standard sections of all the fetal ultrasound images according to a preset classification manner to obtain at least two standard section sets, where each standard section set includes at least one frame of standard section of the fetal ultrasound image, and all the standard sections included in each standard section set are standard sections of the same category;
the second determining module determines a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes according to the tangent plane scores of all the standard tangent planes, and the mode of serving as the optimal standard tangent plane specifically comprises the following steps:
and according to all the tangent plane scores corresponding to each standard tangent plane set, determining a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes included in each standard tangent plane set as the optimal standard tangent plane corresponding to each standard tangent plane set.
As an alternative embodiment, in the second aspect of the present invention, the apparatus further comprises:
a normalization module, configured to determine, at the second determination module, a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes included in each standard tangent plane set according to all the tangent plane scores corresponding to each standard tangent plane set, and after the standard tangent plane corresponding to each standard tangent plane set is used as an optimal standard tangent plane corresponding to each standard tangent plane set, perform normalization operation on the tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set, so as to obtain a normalized tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set;
and the screening module is used for screening a standard section corresponding to the highest normalized section score from all the standard sections according to all the normalized section scores to serve as an optimal standard section corresponding to all the fetal ultrasonic images.
As an alternative embodiment, in the second aspect of the present invention, at least one structural feature exists in the standard tangential plane of each frame of the fetal ultrasound image, and each structural feature has a corresponding weight value;
and, the first determining module comprises:
the determining submodule is used for determining a weight value corresponding to each structural feature of a standard tangent plane of each frame of the fetal ultrasound image;
and the calculating submodule is used for calculating the section score of the standard section of each frame of the fetal ultrasound image based on the weight value corresponding to each structural feature of each standard section and the characteristic parameter of the structural feature.
As an alternative implementation, in the second aspect of the present invention, the determining sub-module includes:
the determining unit is used for determining a key weight value influence factor corresponding to each structural feature of a standard section of each frame of fetal ultrasound image, wherein the number of the key weight value influence factors corresponding to each structural feature is greater than or equal to 1, and each key weight value influence factor has a corresponding sub weight value;
the determining unit is further configured to determine, according to each key weight value influence factor corresponding to each structural feature, a sub-weight value corresponding to each key weight value influence factor;
and the calculating unit is used for calculating the sum of all the sub-weight values corresponding to each structural feature as the weight value corresponding to each structural feature.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides a method and a device for determining an optimal standard section of a fetus, wherein the method comprises the steps of obtaining the standard section of each frame of fetus ultrasonic image in multiple frames of fetus ultrasonic images, and determining the section value of the standard section of each frame of fetus ultrasonic images; and according to all the section scores, determining the standard section corresponding to the highest section score from all the standard sections to serve as the optimal standard section of all the fetal ultrasonic images. Therefore, after the standard section of the fetal ultrasound image is obtained, the method and the device do not need manual analysis to determine the optimal standard section of the fetal ultrasound image, can automatically determine the section score of the standard section of the fetal ultrasound image, intelligently select the standard section with the highest section score from all section scores, realize automatic determination of the optimal standard section, and can improve the accuracy and efficiency of determination of the optimal standard section of the fetal ultrasound image, thereby realizing accurate acquisition of the growth and development conditions of the fetus.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for determining an optimal standard section of a fetus according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another method for determining an optimal standard section of a fetus according to the embodiment of the invention;
fig. 3 is a flow chart illustrating a method for determining a section score of a standard section of a fetus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a device for determining an optimal standard section of a fetus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of another device for determining an optimal standard section of a fetus according to the embodiment of the invention;
FIG. 6 is a schematic structural diagram of a first determining module according to an embodiment of the disclosure;
FIG. 7 is a schematic structural diagram of another first determining module disclosed in the embodiments of the present invention;
fig. 8 is a schematic structural diagram of another device for determining an optimal standard section of a fetus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or apparatus that comprises a list of steps or elements is not limited to those listed but may alternatively include other steps or elements not listed or inherent to such process, method, product, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention discloses a method and a device for determining an optimal standard section of a fetus, which can determine the optimal standard section of a fetus ultrasonic image without manual analysis after the standard section of the fetus ultrasonic image is obtained, can automatically determine the section score of the standard section of the fetus ultrasonic image, intelligently select the standard section with the highest section score from all section scores, realize the automatic determination of the optimal standard section, and can improve the accuracy and the efficiency of the determination of the optimal standard section of the fetus ultrasonic image, thereby realizing the accurate acquisition of the growth and development conditions of the fetus. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for determining an optimal standard section of a fetus according to an embodiment of the present invention. The method for determining the optimal standard fetus tangent plane described in fig. 1 may be applied to a standard tangent plane determination server (service device), where the standard tangent plane determination server may include a local standard tangent plane determination server or a cloud standard tangent plane determination server, and the embodiment of the present invention is not limited thereto. As shown in fig. 1, the method for determining the optimal standard section of the fetus may include the following operations:
101. and acquiring a standard section of each frame of fetal ultrasound image in the plurality of frames of fetal ultrasound images.
In an embodiment of the present invention, as an optional implementation manner, obtaining a standard tangent plane of each frame of fetal ultrasound image in multiple frames of fetal ultrasound images may include:
sequentially inputting each frame of fetal ultrasound image in the obtained continuous multi-frame fetal ultrasound images into a predetermined characteristic detection model for analysis;
obtaining analysis results sequentially output by the feature detection model as feature information of each frame of fetal ultrasound image, wherein the feature information of each frame of fetal ultrasound image comprises the position feature information of the fetal ultrasound image and the structural feature information of the fetal ultrasound image, the position feature information of each frame of fetal ultrasound image at least comprises the category of the position feature of the fetal ultrasound image, the structural feature information of each frame of fetal ultrasound image at least comprises the category of the structural feature of the fetal ultrasound image, and the structural feature of each fetal ultrasound image at least comprises the key structural feature of the fetal ultrasound image;
and determining a standard tangent plane corresponding to the fetal ultrasonic image according to the type of the position characteristics of each frame of fetal ultrasonic image and the type of the structural characteristics of the fetal ultrasonic image.
In this alternative embodiment, a plurality of frames of fetal ultrasound images may be continuously acquired at a predetermined frame rate, where the predetermined frame rate is related to a standard section of the fetal ultrasound image to be acquired, that is, the frame rate is selected according to the standard section of the fetal ultrasound image to be acquired, for example: if the abdominal circumference section needs to be acquired, the frame rate can be 30 frames/second; if a four-chamber cardiotomy is to be obtained, the frame rate may be 60 frames/second. Therefore, the corresponding frame rate is selected according to the standard section of the fetal ultrasonic image to be acquired, and the acquisition efficiency and accuracy of the standard section of the fetal ultrasonic image are improved.
In the embodiment of the invention, each frame of fetal ultrasound image has a unique corresponding frame number. Therefore, by setting a unique frame number for each frame of fetal ultrasound image, each frame of fetal ultrasound image can be clearly distinguished in the process of acquiring the standard section of the fetal ultrasound image, and the management of the fetal ultrasound image and the information of the standard section of the fetal ultrasound image is facilitated.
In this embodiment of the present invention, the feature detection model may include at least one of a target detection model, an instance segmentation model, a semantic segmentation model, and the like, which can acquire the part feature information and the structural feature information of the ultrasound image of the fetus.
Therefore, in the optional embodiment, the standard section of the fetal ultrasound image is determined by acquiring the position characteristics and the structural characteristics of the continuous multi-frame fetal ultrasound images and combining the position characteristics and the structural characteristics of the fetal ultrasound images, so that the determination of the standard section of the fetal ultrasound images does not need to be manually participated, and the determination accuracy of the standard section of the fetal ultrasound images can be improved; and the fetal ultrasonic image is input into the characteristic detection model for analysis, so that the determination efficiency of the standard section of the fetal ultrasonic image can be improved.
In the embodiment of the present invention, further optionally, the obtaining of the standard section of the fetal ultrasound image may also be implemented by receiving the standard section of each frame of the fetal ultrasound image in the multiple frames of the fetal ultrasound images sent by the authorization terminal device. Therefore, the standard section of the ultrasonic image of the fetus is obtained through multiple ways, the obtaining mode of the standard section can be enriched, and the obtaining possibility of the standard section is improved.
102. The section score of the standard section of each frame of fetal ultrasound image is determined.
In an optional embodiment, the method may further comprise the operations of:
determining the proportion of the target characteristics of each frame of fetal ultrasound image, wherein the proportion of the target characteristics is used for representing the display proportion of the target characteristics and the display device, and the target characteristics of each frame of fetal ultrasound image comprise the standard section of the fetal ultrasound image or the structural characteristics in the standard section of the fetal ultrasound image;
and when the target feature of each frame of the fetal ultrasound image is a standard tangent plane of the fetal ultrasound image, after the step 102 is performed, the method may further include the following operations:
determining a score coefficient corresponding to the percentage of the standard section of each frame of fetal ultrasound image, correcting the section score of the standard section of each frame of fetal ultrasound image based on the score coefficient corresponding to the percentage of the standard section of each frame of fetal ultrasound image to obtain the corrected section score of the standard section of each frame of fetal ultrasound image, and triggering to execute step 103.
In this optional embodiment, optionally, the ratio of the standard tangent plane may be calculated by calculating an area surrounded by the contour of the standard tangent plane and/or a distance value between two endpoints that are farthest from the contour of the standard tangent plane, so that the calculation accuracy and reliability of the ratio of the standard tangent plane may be improved. The area surrounded by the outline of the standard tangent plane is preferably selected to calculate the proportion of the structural features, such as: when the area enclosed by the outline of the abdominal circumference section accounts for two thirds of the area of the display screen, the score correction coefficient corresponding to the proportion of the abdominal circumference section is 1.
Therefore, after the section score of the standard section of the fetal ultrasound image is obtained, the section score is further updated according to the score coefficient corresponding to the ratio of the obtained standard section of the fetal ultrasound image to the display area of the current display device, so that the accuracy and reliability of determining the section score of the standard section of the fetal ultrasound image are improved, and the accuracy and reliability of determining the optimal standard section of the fetal ultrasound image are improved.
In an embodiment of the present invention, as an optional implementation manner, determining a section score of a standard section of each frame of the fetal ultrasound image may include:
determining a weight value corresponding to each structural feature of the standard section of each frame of fetal ultrasound image;
and calculating the section score of the standard section of each frame of fetal ultrasound image based on the weight value corresponding to each structural feature of each standard section and the characteristic parameter of the structural feature.
In this alternative embodiment, there is at least one structural feature in the standard slice of each frame of fetal ultrasound image, and there is a corresponding weight value for each structural feature. The structural features in each standard tangential plane at least include key structural features (also called basic structural features or main structural features) of the standard tangential plane, and further, the structural features in each standard tangential plane may also include other structural features besides the key structural features. For example: the thalamic standard section includes at least one critical structural feature of the hyaline compartment, thalamus and lateral ventricles, and further, the thalamic standard section may include at least one other structural feature of the choroid plexus and lateral cerebrum. Therefore, the more the structural features in the standard tangent plane are, the better the calculation accuracy and reliability of the tangent plane score of the standard tangent plane are improved, and the determination accuracy and reliability of the optimal standard tangent plane are improved. The key structural feature of each standard section is a structural feature capable of representing the standard section, that is, when the key structural feature of the fetal ultrasound image is obtained, the standard section corresponding to the key structural feature can be determined. For example: and when the structural features of the fetal ultrasound image are the gastric vacuole and the umbilical vein, the standard section of the fetal ultrasound image is the abdominal circumference section. Therefore, the standard section of the fetal ultrasound image is determined through the key structural features, and the determination efficiency of the standard section can be improved while the standard section is ensured to be determined correctly.
Therefore, in the optional implementation mode, by combining the weight value of each structural feature of the standard tangent plane with the feature parameter of the structural feature, the automatic calculation of the tangent plane score of the standard tangent plane can be realized, and the calculation accuracy and efficiency of the tangent plane score of the standard tangent plane are improved.
In this optional embodiment, further optionally, determining a weight value corresponding to each structural feature of the standard section of each frame of the fetal ultrasound image may include:
determining a key weight value influence factor corresponding to each structural feature of the standard section of each frame of fetal ultrasound image, wherein the number of the key weight value influence factors corresponding to each structural feature is more than or equal to 1, and each key weight value influence factor has a corresponding sub weight value;
and determining a sub-weight value corresponding to each key weight value influence factor according to each key weight value influence factor corresponding to each structural feature, and calculating the sum of all sub-weight values corresponding to each structural feature to serve as the weight value corresponding to each structural feature.
In this optional embodiment, the key weight value influence factors corresponding to each structural feature of each standard tangent plane may be the same or different. For example: the key weight value influence factors of the skull halo structure characteristics of the lateral ventricle section comprise the head circumference size corresponding to the contour of the skull halo structure characteristics, the integrity of the contour of the skull halo structure characteristics and the relative position of the region surrounded by the contour of the skull halo structure characteristics and the brain midline; the key weight value influence factors of the femur structure characteristics of the femur measurement section comprise the length corresponding to the contour of the femur structure characteristics, the area enclosed by the contour of the femur structure characteristics and the relative position of the area enclosed by the contour of the femur structure characteristics and the midline of the brain.
Therefore, in the optional embodiment, the key weight value influence factor corresponding to each structural feature is determined in a targeted manner, and the sub-weight values corresponding to all the key weight value influence factors are determined as the weight values corresponding to the structural feature, so that the calculation accuracy of the weight values of the structural features can be improved, the calculation accuracy of the section scores corresponding to the standard section is improved, and the determination accuracy of the optimal standard section is improved.
In this further optional implementation manner, further optionally, determining, according to each key weight value influence factor corresponding to each structural feature, a sub-weight value corresponding to each key weight value influence factor may include:
for any structural feature, when the key weight value influence factor corresponding to the structural feature comprises a geometric parameter of the outline of the structural feature, determining a sub-weight value corresponding to the geometric parameter of the outline of the structural feature according to the geometric parameter of the outline of the structural feature, wherein the geometric parameter of the outline of the structural feature comprises the size and/or area of the outline of the structural feature;
for any structural feature, when the key weight value influence factor corresponding to the structural feature comprises the definition of the structural feature, inputting the fetal ultrasound image corresponding to the structural feature into the determined classification model for analysis, and acquiring an analysis result output by the classification model as a sub-weight value corresponding to the definition of the structural feature;
for any structural feature, when the key weight value influence factor corresponding to the structural feature comprises the integrity of the structural feature, calculating a geometric parameter corresponding to the structural feature according to the outline of the structural feature, and determining a sub-weight value corresponding to the integrity of the structural feature according to the geometric parameter corresponding to the structural feature;
for any structural feature, when the key weight value influence factor corresponding to the structural feature comprises the position of the structural feature in the standard tangent plane, determining a sub-weight value corresponding to the position of the structural feature in the standard tangent plane based on the relative position relationship between the brain midline corresponding to the structural feature and the region surrounded by the outline of the structural feature;
and when the target feature of each frame of fetal ultrasound image is the structural feature in the standard section of the fetal ultrasound image, determining a sub-weight value matched with the proportion of the structural feature according to the proportion of the structural feature for any structural feature.
In this optional embodiment, optionally, the proportion of the structural feature may be calculated by calculating an area surrounded by the outline of the structural feature and/or a distance value between two end points on the outline of the structural feature that are farthest from each other, so that the calculation accuracy and reliability of the proportion of the structural feature may be improved. The area surrounded by the outline of the structural feature is preferentially selected to calculate the proportion of the structural feature, for example: the area enclosed by the outline of the left atrial structural feature accounts for one seventh of the area of the display screen, and the sub-weight value corresponding to the proportion of the left atrial structural feature is 0.8.
In this alternative embodiment, the dimensions of the contour of the structural feature may include the circumference of the contour of the structural feature and/or the corresponding length of the contour of the structural feature (e.g., the length of the humeral structural feature).
In this optional embodiment, after the geometric parameters of the contour of the structural feature are obtained, it is further determined whether the geometric parameters of the contour of the structural feature are within the determined geometric parameter range corresponding to the gestational week of the fetal ultrasound image, and when it is determined that the geometric parameters are not within the geometric parameter range, the sub-weight value corresponding to the geometric parameters of the contour of the structural feature is multiplied by the determined weight correction coefficient (for example, 0.8) to obtain a corrected sub-weight value; and when the judgment result is yes, triggering and executing the operation of calculating the sum of all the sub-weight values corresponding to each structural feature as the weight value corresponding to each structural feature. For example: if the current gestational week of the fetus is 20 weeks and the length of the femur of the fetus at the 20 th week is normally 10cm-15cm, when the determined length of the femur structural feature is 13cm, keeping the calculated sub-weight value (0.7) unchanged, and when the length of the femur structural feature is 8cm or 20cm, multiplying the calculated sub-weight value (0.7) by a weight correction coefficient (0.9) to obtain a corrected sub-weight value (0.63). Wherein, the higher the weight value is, the more obvious the corresponding structural feature is expressed. Therefore, the correction operation is executed on the sub-weight values corresponding to the geometric parameters of the structural features which are not in the normal parameter range corresponding to the gestational weeks, and the calculation accuracy of the tangent plane score of the corresponding standard tangent plane can be improved.
In this optional embodiment, based on the relative position relationship between the brain midline corresponding to the structural feature and the region surrounded by the contour of the structural feature, the sub-weight value corresponding to the position of the structural feature in the standard tangent plane is determined, specifically: when an intersection point exists in an area defined by the central line of the brain corresponding to the structural feature and the outline of the structural feature, determining that a sub-weight value corresponding to the position of the structural feature in the standard tangent plane is a first sub-weight value; when the distance between the brain midline corresponding to the structural feature and the outline of the structural feature is within a predetermined distance range value, determining that the subweight value corresponding to the position of the structural feature in the standard tangent plane is a second subweight value; when the distance between the brain midline corresponding to the structural feature and the outline of the structural feature is larger than the maximum distance value in the predetermined distance range value, determining that the sub-weight value corresponding to the position of the structural feature in the standard tangent plane is a third sub-weight value, and sequentially reducing the first sub-weight value, the second sub-weight value and the third sub-weight value. For example: when the brain midline passes through the area surrounded by the outline of the brain midline saccule structural feature, the sub-weight value is 1, which indicates that the brain midline saccule structural feature does not deviate from the brain midline; when the outline of the structural feature of the cerebral midline saccule and the cerebral midline do not have an intersection point and the deviation distance is 1mm, the subweight value is 0.8; when the offset distance is 5mm, the sub-weight value is 0.
In this optional embodiment, when there are a plurality of key weight value influence factors corresponding to the structural feature, the weight value of the corresponding structural feature is equal to the sum of the sub-weight values corresponding to each key weight value influence factor. For example: the key weight value influence factor of the femur structure characteristic of the femur measurement tangent plane comprises the length corresponding to the contour of the femur structure characteristic, the area surrounded by the contour of the femur structure characteristic and the relative position of the area surrounded by the contour of the femur structure characteristic and the midline, wherein the sub weight value of the length corresponding to the contour of the femur structure characteristic is 0.7, the sub weight value corresponding to the area surrounded by the contour of the femur structure characteristic is 0.6, the sub weight value corresponding to the relative position of the area surrounded by the contour of the femur structure characteristic and the midline is 0.8, and the weight value of the femur structure characteristic is 0.7+0.6+0.8 which is 2.1.
Therefore, according to the optional implementation mode, the corresponding sub-weight value determining mode is selected according to different key weight value influence factors, so that the sub-weight value corresponding to the key weight value influence factor can be obtained, the obtaining efficiency and accuracy of the sub-weight value can be improved, the calculating accuracy and efficiency of the weight value corresponding to the structural characteristic are improved, and the calculating accuracy and efficiency of the section score corresponding to the standard section are improved.
In this further optional embodiment, further optionally, calculating a geometric parameter corresponding to the structural feature according to the contour of the structural feature includes:
calculating the length of the outline of the structural feature as a geometric parameter corresponding to the structural feature; and/or the presence of a gas in the gas,
determining a central point corresponding to the contour of the structural feature, and determining a central angle corresponding to the contour of the structural feature as a geometric parameter corresponding to the structural feature based on the central point corresponding to the contour of the structural feature and the contour of the structural feature; and/or the presence of a gas in the gas,
fitting the contour of the structural feature based on the determined fitting method to obtain a target contour of the structural feature;
and/or determining a central point corresponding to the target contour of the structural feature, and determining a central angle corresponding to the contour of the structural feature based on the central point corresponding to the target contour of the structural feature and the contour of the overlapping part as the geometric parameter corresponding to the structural feature.
In this optional embodiment, optionally, the fitting of the contour of the structural feature based on the determined fitting method to the contour of the structural feature to obtain the target contour of the structural feature may include:
acquiring the arc radius corresponding to the outline of each structural feature;
when the arc radius corresponding to the outline of each structural feature is larger than or equal to the determined arc radius threshold (for example, 5mm), selecting a preset number (for example, 50) of target nodes from all nodes corresponding to the structural feature, and sequentially connecting all target nodes corresponding to each structural feature according to a mode that every two adjacent nodes are connected to obtain a target outline of the structural feature;
and when the arc radius corresponding to the profile of each structural feature is not more than or equal to the determined arc radius threshold value, sequentially connecting all nodes corresponding to each structural feature according to the mode of connecting every two adjacent nodes to obtain the target profile of the structural feature.
In this alternative embodiment, when the contour of the structural feature has a plurality of circular arcs and/or the curvature of the contour is greater than or equal to the determined curvature threshold, the fitting operation is performed on the contour of the structural feature in a segmented manner. Specifically, the method comprises the following steps: when the contour of the structural feature has a plurality of circular arcs, respectively performing fitting operation on each circular arc in the plurality of circular arcs of the structural feature; when the curvature of the contour of the structural feature is larger than or equal to the curvature threshold value, the contour of the structural feature is divided into multiple sections at equal intervals or unequal intervals, and the fitting operation is performed on each section of contour respectively. Therefore, when the contour of the structural feature has a plurality of circular arcs and/or the curvature of the contour is large, the fitting efficiency and accuracy of the contour of the structural feature can be improved by performing the fitting operation on the contour of the structural feature in a segmented manner, so that the measurement accuracy and reliability of the geometric parameters of the structural feature of the fetal ultrasonic image can be further improved.
In this optional embodiment, a fitting operation may be performed on the contour of each structural feature based on the determined B-spline curve fitting manner and/or ellipse fitting manner to obtain a target contour of the structural feature, which is not limited in this optional embodiment.
Therefore, in the optional implementation mode, different fitting modes are selected according to the size of the circular arc radius of the structural feature of the fetal ultrasound image, so that not only can the fitting of the structural feature be realized, but also the fitting efficiency and accuracy of the structural feature can be improved, and the calculation accuracy of the geometric parameters of the structural feature is improved.
In this alternative embodiment, after calculating the length of the contour of the overlapping portion of the contour of the structural feature and the target contour of the structural feature as the geometric parameter corresponding to the structural feature, the method further includes:
and calculating the ratio of the length of the contour of the overlapped part of the target contour of the structural feature to the perimeter of the target contour, and updating the geometric parameter corresponding to the structural feature into the ratio. Wherein, different ratios correspond to different sub-weight values, for example: when the ratio is greater than or equal to 0.8, the corresponding sub-weight value is 1; when the ratio is smaller than 0.8, the corresponding sub-weight value is 0.8. Therefore, the geometric parameters corresponding to the structural features are updated to be the ratio of the length of the outline of the overlapped part of the target outline of the structural features to the perimeter of the target outline, so that the accuracy of determining the sub-weight values is improved, and the accuracy of calculating the weight values of the structural features is improved.
In this optional embodiment, after determining the central angle corresponding to the contour of the structural feature as the geometric parameter corresponding to the structural feature, the method further includes:
and calculating the ratio of the central angle corresponding to the outline of the structural feature to the 360-degree central angle, and updating the geometric parameters corresponding to the structural feature into the ratio of the central angle corresponding to the outline of the structural feature to the 360-degree central angle.
Therefore, in the optional embodiment, the geometric parameters corresponding to the structural features are determined in multiple ways, so that the acquisition ways of the geometric parameters corresponding to the structural features can be enriched, and the acquisition possibility of the geometric parameters corresponding to the structural features is improved; and one or a combination of the length of the contour of the structural feature, the central angle corresponding to the contour of the structural feature, the length of the contour of the structural feature, the contour of the fitted contour at the overlapping part and the central angle corresponding to the contour at the overlapping part is used as the geometric parameter corresponding to the structural feature, so that the acquisition accuracy of the geometric parameter corresponding to the structural feature can be improved, and the calculation accuracy of the weight value corresponding to the structural feature can be improved.
In this further optional embodiment, still further optionally, calculating a section score of the standard section of each frame of the fetal ultrasound image based on the weight value corresponding to each structural feature of each standard section and the feature parameter of the structural feature, which may include:
calculating a structural score corresponding to each structural feature of each standard tangent plane based on the weight value corresponding to each structural feature of each standard tangent plane, the category probability of the structural feature and the position probability of the structural feature;
and calculating the sum of the structural scores corresponding to all the structural features of each standard section to serve as the section score of the standard section of each frame of fetal ultrasound image.
In this alternative embodiment, the feature parameter of each structural feature of each standard tangent plane includes a class probability of the structural feature and a position probability of the structural feature.
In this alternative embodiment, the calculation formula of the section score of the standard section of each frame of fetal ultrasound image is as follows:
Figure BDA0002698925920000121
Hi＝Pi×Qi×Oi；
Figure BDA0002698925920000122
wherein S is the score of each standard section, HiThe structure score of the ith structural feature in each standard section, M is the total number of structural features in each standard section, PiIs the class probability (also called confidence) of the ith structural feature in each standard section, QiFor the position probability of the ith structural feature in each standard section, OiThe weight value of the ith structural feature in each standard tangent plane, N is the total number of the key weight value influence factors of the ith structural feature, and OijAnd the subweight value corresponding to the jth key weight value influence factor in the ith structural feature in each standard tangent plane.
In this optional embodiment, further, the parameter included in the structural feature in each standard tangent plane further includes a probability of a location where the structural feature is located, and at this time, the structural score of the ith structural feature in each standard tangent plane is calculated by the following formula:
Hi＝Pi×Qi×Oi×Ci；
in the formula, CiThe parameters included for a structural feature in each standard cut plane also include the probability of the site where the structural feature is located. The more the parameters of the structural characteristics are, the calculation accuracy of the structural score of the structural characteristics is improved, and therefore the calculation of the score of the tangent plane of the standard tangent plane is improvedThe accuracy is further favorable for improving the determination accuracy and the reliability of the optimal standard tangent plane.
Therefore, in the optional implementation mode, the calculation of the section score of the standard section can be realized by respectively calculating the structure score corresponding to each structure feature of the standard section, and the calculation accuracy and efficiency of the section score of the standard section are favorably improved; and different parameters are selected according to different structural characteristics, so that the calculation accuracy and efficiency of the structural scores corresponding to the structural characteristics can be improved, and the calculation accuracy and efficiency of the section scores of the standard sections are further improved.
103. And according to the section scores of all the standard sections, determining the standard section corresponding to the highest section score from all the standard sections to serve as the optimal standard section of all the fetal ultrasonic images.
In an optional embodiment, the method for determining the optimal standard section of the fetus may further include the following operations:
acquiring a positive fetal ultrasound image sample and a negative fetal ultrasound image sample, wherein the pixel value of the positive fetal ultrasound image sample is greater than the pixel value of the negative fetal ultrasound image sample, and the key weight value influence factor of the structural feature of each positive sample fetal ultrasound image in the positive fetal ultrasound image sample and each negative sample fetal ultrasound image in the negative fetal ultrasound image sample comprises the definition of the structural feature;
and training the determined initial classification model based on the positive fetal ultrasound image sample and the negative fetal ultrasound image sample, and acquiring the trained initial classification model as the determined classification model.
In this alternative embodiment, the initial classification model includes classification models formed by one or a combination of KNN, Bayesian, Neural Network, Ensemble-Stacking, Ensemble-Boosting, Ensemble-Bagging, and the like, which can implement image classification, and this alternative embodiment is not limited.
In this alternative embodiment, the sample fetal ultrasound images included in the positive fetal ultrasound image sample and the negative fetal ultrasound image sample may be screened by the device terminal, may be selected by the relevant person according to experience, or may be determined by both the positive fetal ultrasound image sample and the negative fetal ultrasound image sample.
In this alternative embodiment, since the key weight value influence factors include a plurality of structural features corresponding to the definition of the structural features, the positive fetal ultrasound image sample is composed of a plurality of sub positive fetal ultrasound image samples, and the negative fetal ultrasound image sample is composed of a plurality of sub negative fetal ultrasound image samples. Wherein each sub-positive fetal ultrasound image sample corresponds to one sub-negative fetal ultrasound image sample. Further, each sample fetal ultrasound image has a corresponding sample weight value. For example: the positive fetal ultrasound image sample comprises a sub-positive fetal ultrasound image sample containing the structural feature of the transparent compartment and a sub-positive fetal ultrasound image sample containing the structural feature of the arterial duct, and the negative fetal ultrasound image sample comprises a sub-negative fetal ultrasound image sample containing the structural feature of the transparent compartment and a sub-negative fetal ultrasound image sample containing the structural feature of the arterial duct. At this time, the determined initial classification model is trained based on the positive fetal ultrasound image sample, the negative fetal ultrasound image sample and the weight value corresponding to each sample fetal ultrasound image, and the trained initial classification model is obtained as the determined classification model. Therefore, the training accuracy of the classification model can be improved, and the classification model with high accuracy is obtained.
Therefore, in the optional embodiment, the training operation is performed on the initial classification model based on the sample fetal ultrasonic image in advance, and the classification model meeting the requirement and accurate can be obtained, so that the analysis accuracy and reliability of the sub-weight values of the definition of the key weight value influence factors including the structural features are improved, and the calculation accuracy and efficiency of the weight values corresponding to the structural features are improved.
In another alternative embodiment, after step 102 is executed, the method for determining the optimal standard cut plane of the fetus may further include the following operations:
judging whether all the standard sections belong to the same class of standard sections;
when all the standard facets are judged to belong to the same category of standard facets, step 103 is triggered to be executed.
In this alternative embodiment, it should be noted that the step of determining whether all the standard facets belong to the same class of standard facets may occur simultaneously with step 102, or may occur before step 102, and this alternative embodiment is not limited.
In this optional embodiment, as an optional implementation manner, the determining whether all the standard facets belong to the same class of standard facets may include:
judging whether the categories of the structural features of each standard section are matched, and if so, determining that all the standard sections belong to the same category of standard sections; when the judgment result is negative, determining that all the standard tangent planes do not belong to the same class of standard tangent planes; alternatively, the first and second electrodes may be,
acquiring a section mark of each standard section, judging whether the section marks of the standard sections are matched, and if so, determining that all the standard sections belong to the same class of standard sections; and when the judgment result is negative, determining that all the standard tangent planes do not belong to the same class of standard tangent planes, wherein the tangent plane identifier of each standard tangent plane comprises a tangent plane number and/or a tangent plane icon.
For example, when each standard section includes structural features of the gastric pouch, all standard sections are standard sections of the same class and are standard sections of the abdominal circumference class. For example, the first bits of the slice number of each standard slice are 0001, and all standard slices are standard slices of the same category.
In this optional implementation manner, further, when both the two determination results are yes, it is determined that all the standard facets belong to the standard facets of the same category, so that not only can the determination manners of all the standard facets belonging to the standard facets of the same category be enriched, but also the determination accuracy of all the standard facets belonging to the standard facets of the same category can be improved.
Therefore, after the standard sections of all the fetal ultrasound images are obtained, the optional embodiment further judges that all the standard sections belong to the same type of standard section, if yes, the subsequent operation is executed, and the accuracy of determining the optimal standard section of the fetal ultrasound images can be improved; and whether all standard tangent planes belong to the same class is determined by providing the classes based on the structural characteristics of the standard tangent planes and/or the tangent plane marks of the standard tangent planes, so that the determination modes that all standard tangent planes belong to the standard tangent planes of the same class can be enriched, and the determination accuracy that all standard tangent planes belong to the standard tangent planes of the same class can be improved.
In yet another alternative embodiment, the method for determining the optimal standard cut plane of the fetus may further include the following operations:
when all the standard sections are judged not to belong to the same type of standard sections, classifying the standard sections of all the fetal ultrasonic images according to a preset classification mode to obtain at least two standard section sets, wherein each standard section set comprises at least one frame of standard sections of the fetal ultrasonic images, and all the standard sections of each standard section set are the same type of standard sections;
wherein, according to the section scores of all standard sections, determining the standard section corresponding to the highest section score from all standard sections as the optimal standard section, including:
and according to all the tangent plane scores corresponding to each standard tangent plane set, determining the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes included in each standard tangent plane set as the optimal standard tangent plane corresponding to each standard tangent plane set.
In this alternative embodiment, optionally, while the classification operation is performed on all the standard slices of the fetal ultrasound images, the slice scores of all the standard slices included in each standard slice set may be determined.
Therefore, in the optional embodiment, when the standard sections of all the fetal ultrasound images are judged to belong to different categories, the classification operation is performed on all the standard sections, and the standard sections of different categories can be obtained, so that the situation that non-optimal standard sections are obtained due to different section categories is reduced, and the accuracy and the reliability of determining the optimal standard sections corresponding to the standard sections of different categories are improved.
In yet another optional embodiment, after determining the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes included in each standard tangent plane set according to all the tangent plane scores corresponding to each standard tangent plane set, as the optimal standard tangent plane corresponding to each standard tangent plane set, the method for determining the optimal standard tangent plane for the fetus may further include the following operations:
performing normalization operation on the tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set to obtain the normalized tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set;
and screening the standard section corresponding to the highest normalized section score from all the standard sections according to all the normalized section scores to serve as the optimal standard section corresponding to all the fetal ultrasonic images.
In this alternative embodiment, for example, the section score of the optimal standard section of the femur measurement standard section is 20 minutes, the section score of the optimal standard section of the skull median standard section is 100 minutes, and the section score of the optimal standard section of the cholecyst-umbilical vein standard section is 60 minutes, then normalization operations are respectively performed on the section score of the optimal standard section of the femur measurement standard section, the section score of the optimal standard section of the skull median standard section, and the section score of the optimal standard section of the cholecyst-umbilical vein standard section, so that each section score falls within the range of 0-1, then the normalized section scores are sequentially 0.8, 0.5, and 0.9, and then the optimal standard sections of all fetal ultrasound images are the optimal standard section of the cholecyst-umbilical vein standard section.
Therefore, after the optimal standard tangent planes corresponding to the different types of standard tangent planes are obtained, the optional embodiment further performs normalization operation on the tangent plane scores of the optimal standard tangent planes corresponding to the different types of standard tangent planes, so that the tangent plane scores of the optimal standard tangent planes corresponding to the different types of standard tangent planes can be compared, the accuracy and efficiency for determining the optimal standard tangent planes corresponding to all fetal ultrasound images are improved, and the growth and development conditions of the fetus can be further accurately obtained.
Therefore, by implementing the method for determining the optimal standard section of the fetus described in fig. 1, after the standard section of the ultrasound image of the fetus is obtained, the optimal standard section of the ultrasound image of the fetus does not need to be determined through manual analysis, the section score of the standard section of the ultrasound image of the fetus can be automatically determined, the standard section with the highest section score can be intelligently selected from all section scores, the automatic determination of the optimal standard section is realized, the accuracy and the efficiency for determining the optimal standard section of the ultrasound image of the fetus can be improved, and the growth and development conditions of the fetus can be accurately obtained.
Example two
Referring to fig. 2, fig. 2 is a schematic flow chart of another method for determining an optimal standard section of a fetus according to the embodiment of the invention. The method for determining the optimal standard fetus tangent plane described in fig. 2 may be applied to a standard tangent plane determination server (service device), where the standard tangent plane determination server may include a local standard tangent plane determination server or a cloud standard tangent plane determination server, and the embodiment of the present invention is not limited thereto. As shown in fig. 2, the method for determining the optimal standard section of the fetus may include the following operations:
201. and acquiring a standard section of each frame of fetal ultrasound image in the plurality of frames of fetal ultrasound images.
202. The section score of the standard section of each frame of fetal ultrasound image is determined.
203. Judging whether abnormal standard sections with structural features as abnormal structural features exist in all the standard sections according to the structural features of all the standard sections, and triggering to execute the step 205 when the judgment result is negative; when the determination result is yes, execution of step 204 may be triggered.
In the embodiment of the present invention, step 202 and step 203 may also occur simultaneously.
204. And correcting the section score of each abnormal standard section based on the score correction coefficient corresponding to each abnormal standard section.
In the embodiment of the present invention, after the step 204 is completed, the step 205 is triggered to be executed, and at this time, the tangent plane scores of all the standard tangent planes in the step 205 include the tangent plane scores of all the standard tangent planes which do not need to be corrected and the tangent plane scores of all the standard tangent planes which need to be corrected and are already corrected.
In the embodiment of the invention, each abnormal standard section has a corresponding score correction coefficient. Further, the score correction coefficients corresponding to different abnormal standard tangent planes may be the same or different, and the embodiment of the present invention is not limited. For example: the score correction coefficient corresponding to the abnormal lateral ventricle standard section is 10, and the score correction coefficient corresponding to the abnormal thalamus standard section is 8.
In this embodiment of the present invention, optionally, the score correction coefficient includes at least one of a tangent score correction coefficient, a structure score correction coefficient, and a weight value correction coefficient. And, as an optional implementation, modifying the score of the tangent plane of each abnormal standard tangent plane based on the score modification coefficient corresponding to the abnormal standard tangent plane may include:
when the score correction coefficient is the section score correction coefficient, for any abnormal standard section, multiplying the score correction coefficient corresponding to the abnormal standard section by the section score of the abnormal standard section to obtain the corrected section score of the abnormal standard section;
when the score correction coefficient is a structural score correction coefficient, multiplying the score correction coefficient corresponding to the abnormal standard tangent plane by the structural score corresponding to the abnormal structural feature to obtain a structural score corresponding to the corrected abnormal structural feature, and adding the structural scores of each structural feature (including the normal structural feature and the abnormal structural feature) of the abnormal standard tangent plane to obtain a corrected tangent plane score of the abnormal standard tangent plane;
and when the score correction coefficient is a weight value correction coefficient, multiplying the score value correction coefficient corresponding to the abnormal standard tangent plane by the weight value corresponding to the abnormal structure characteristic to obtain the weight value corresponding to the corrected abnormal structure characteristic, calculating the structure score corresponding to the abnormal structure characteristic, and adding the structure scores of each structure characteristic (including the normal structure characteristic and the abnormal structure characteristic) of the abnormal standard tangent plane to obtain the corrected tangent plane score of the abnormal standard tangent plane.
In this optional embodiment, when there are at least two correction methods for correcting the tangent plane score of the abnormal standard tangent plane, the average value of the tangent plane scores of the abnormal standard tangent plane corrected by all the correction methods is obtained as the corrected tangent plane score of the abnormal standard tangent plane. Therefore, the correction accuracy of the section score of the abnormal standard section can be improved, and the accurate section score of the abnormal standard section can be further obtained.
Therefore, according to the optional implementation mode, the section score of the abnormal standard section is corrected by providing at least one correction mode among section score correction, structure score correction and weight value correction, so that the correction modes of the section score of the abnormal standard section can be enriched, the correction accuracy of the section score of the abnormal standard section can be improved, the accurate section score of the abnormal standard section can be obtained, and the accuracy and the reliability of the determination of the optimal standard section can be improved.
205. And according to the section scores of all the standard sections, determining the standard section corresponding to the highest section score from all the standard sections to serve as the optimal standard section of all the fetal ultrasonic images.
Therefore, after the section score of the standard section of the fetal ultrasound image is obtained, whether abnormal standard sections exist in all the standard sections is further judged, if the abnormal standard sections exist, correction operation is carried out on the section score of the abnormal standard sections based on the score correction coefficient, the accuracy of determining the section score of the abnormal standard sections can be improved, the situation that non-optimal standard sections are obtained due to the fact that the optimal standard sections are continuously obtained when the abnormal standard sections appear is reduced, and the accuracy and the reliability of determining the optimal standard sections when the abnormal standard sections appear are improved.
In the embodiment of the present invention, please refer to the detailed description of step 101 to step 103 in the first embodiment for the other descriptions of step 201, step 202, and step 205, which is not described again in the embodiment of the present invention.
In an optional embodiment, the determining whether there is an abnormal standard section with a structural feature being an abnormal structural feature in all the standard sections according to the structural features of all the standard sections may include:
acquiring target information of each structural feature of each standard section, wherein the target information of each structural feature is used for determining whether the standard section in which the structural feature is located is an abnormal standard section;
judging whether each structural feature is matched with the standard tangent plane according to the target information of each structural feature of each standard tangent plane;
and when judging that the non-matching structural features which are not matched with the standard tangent plane are existed in all the structural features, determining that an abnormal standard tangent plane with the structural features as abnormal structural features exists in all the standard tangent planes, wherein the abnormal standard tangent plane is the standard tangent plane with the non-matching structural features.
Therefore, in the optional embodiment, the determination of the abnormal standard tangent plane can be realized by acquiring the target information of each structural feature of the standard tangent plane and judging whether each structural feature is matched with the corresponding standard tangent plane according to the target information of each structural feature.
In another alternative embodiment, the determining whether each structural feature matches the standard tangent plane according to the target information of each structural feature of each standard tangent plane may include:
determining a representation type corresponding to each structural feature according to the target information of each structural feature of each standard tangent plane, wherein the representation types comprise numerical representation types and/or feature morphology representation types;
when the expression type of the structural feature is a numerical expression type, acquiring a target geometric parameter value corresponding to the structural feature, judging whether the target geometric parameter value corresponding to the structural feature is within a predetermined normal parameter value range, and when the judgment result is negative, determining that the structural feature is not matched with the standard tangent plane in which the structural feature is located;
and when the representation type of the structural feature is a feature form representation type, judging whether the structural feature is located in a detection area of the part feature corresponding to the structural feature, and when the judgment result is negative, determining that the structural feature is not matched with the standard tangent plane in which the structural feature is located.
In this alternative embodiment, the detection area of each part feature may be represented by a detection frame, for example: and selecting a polygonal frame or an elliptical frame.
In this optional embodiment, the target geometric parameter value corresponding to each structural feature includes a cross diameter corresponding to the structural feature and/or a circumference corresponding to the structural feature, so that the more contents included in the geometric parameter value, the more the judgment accuracy of matching the structural feature with the standard tangent plane where the structural feature is located is facilitated to be improved. The different structural characteristics all have corresponding normal parameter value ranges, wherein the normal parameter value ranges corresponding to the different structural characteristics may be the same or different. Furthermore, different geometric parameter values of the same structural feature correspond to different normal parameter value ranges. Still further, the geometric parameter values corresponding to each structural feature may include a proportional dimension and/or an actual dimension. Specifically, after the proportional size corresponding to the structural feature is judged to be within the range of the predetermined normal parameter value, the actual size corresponding to the structural feature is further obtained, whether the actual size is within the range of the predetermined normal size is judged, and when the judgment result is negative, the structural feature is determined not to be matched with the standard tangent plane in which the structural feature is located. Therefore, by comparing the proportional size and the actual size of the structural feature with respective normal values, the accuracy of determining whether the structural feature is matched with the standard tangent plane can be improved, the condition of error correction of the tangent plane score of the abnormal standard tangent plane is reduced, and the accuracy and the reliability of correction of the tangent plane score of the abnormal standard tangent plane are improved.
In this optional embodiment, when it is determined that the structural feature is located in the detection region of the location feature corresponding to the structural feature, it is determined whether the structural feature exists in all the multiple frames of fetal ultrasound images, and when the determination result is yes, it is determined that the structural feature is not matched with the standard section in which the structural feature exists. The multi-frame fetal ultrasound image can be a fetal ultrasound image which continuously or discontinuously appears backwards by taking the fetal ultrasound image with the structural feature as the first frame fetal ultrasound image. Therefore, when the structural feature is judged to be in the detection area of the corresponding part feature, whether the multi-frame fetal ultrasonic image has the structural feature is further judged, if yes, the structural feature is determined to be not matched with the standard section, the accuracy of determining whether the structural feature is matched with the standard section can be improved, the condition of error correction of section scores of abnormal standard sections is reduced, and the accuracy and the reliability of correction of section scores of abnormal standard sections are improved.
The structural features of the numerical representation type and the feature morphology representation type are now illustrated, respectively:
the (one) numerical value represents the type: when the detected structural feature is a critical widening feature of a lateral ventricle, inputting profile information of the critical widening feature of the lateral ventricle into a measuring module for measurement to obtain a transverse diameter (proportional size) of the critical widening feature of the lateral ventricle, judging whether the transverse diameter is greater than or equal to 12 pixels, and if so, judging that the critical widening feature of the lateral ventricle is an abnormal structural feature, namely that the critical widening feature of the lateral ventricle is not matched with a standard tangent plane where the critical widening feature of the lateral ventricle is located. Further, after the transverse diameter of the critical widening feature of the lateral ventricle is obtained, the actual size of the critical widening feature of the lateral ventricle is calculated according to the transverse diameter and the scale of the fetal ultrasound image, whether the actual size is larger than or equal to 10mm or not is judged, if the judgment result is yes, the critical widening feature of the lateral ventricle is an abnormal structural feature, namely the critical widening feature of the lateral ventricle is not matched with the standard tangent plane where the critical widening feature of the lateral ventricle is located. Still further, when the cross diameter of the critical widening feature of the lateral ventricle is judged to be smaller than 12 pixels and/or the actual size of the critical widening feature of the lateral ventricle is judged to be smaller than 10mm, the critical widening feature of the lateral ventricle is determined to be a normal structural feature, and the critical widening feature of the lateral ventricle is modified into a normal lateral ventricle feature, namely the critical widening feature of the lateral ventricle is matched with the standard tangent plane of the critical widening feature of the lateral ventricle.
(II) characteristic morphology representation type: and when the detected structural feature is the structural feature of the choroid from the cyst, determining whether the structural feature of the choroid from the cyst is present in the detection area of the lateral ventricle, and when the structural feature of the choroid from the cyst is present in the detection area of the lateral ventricle, determining that the structural feature of the choroid from the cyst is an abnormal structural feature, namely determining that the structural feature of the choroid from the cyst is not matched with the standard section in which the structural feature of the choroid from the cyst is present. Further, when detecting that the structural feature of the choroid secondary cyst appears in the detection area of the lateral ventricle, judging whether the structural feature of the choroid secondary cyst exists in 4 frames of fetal ultrasonic images, and when the judgment result is yes, determining that the structural feature of the choroid secondary cyst does not match the standard tangent plane in which the structural feature of the choroid secondary cyst exists.
Therefore, when the structural feature of the ultrasonic image of the fetus is judged, the optional embodiment judges whether the structural feature is matched with the standard section where the structural feature is located or not through the acquired geometric parameter value of the structural feature, or judges whether the structural feature is located in the detection area of the feature of the corresponding part, so that the judgment on whether the structural feature is matched with the standard section where the structural feature is located or not is realized, and the determination possibility, accuracy and determination efficiency on whether the structural feature is matched with the standard section where the structural feature is located can be improved.
Therefore, the method for determining the optimal standard section of the fetus described in fig. 2 can determine the optimal standard section of the ultrasound image of the fetus without manual analysis after the standard section of the ultrasound image of the fetus is obtained, can automatically determine the section score of the standard section of the ultrasound image of the fetus, and intelligently selects the standard section with the highest section score from all the section scores, so as to realize automatic determination of the optimal standard section, improve the accuracy and efficiency of determination of the optimal standard section of the ultrasound image of the fetus, and further realize accurate acquisition of the growth and development conditions of the fetus.
EXAMPLE III
Referring to fig. 3, fig. 3 is a flowchart illustrating a method for determining a section score of a standard section of a fetus according to an embodiment of the present invention. The method for determining the score of the fetal standard cut plane described in fig. 3 may be applied to a standard cut plane determination server (service device), where the standard cut plane determination server may include a local standard cut plane determination server or a cloud standard cut plane determination server, and the embodiment of the present invention is not limited thereto. As shown in fig. 3, the method for determining the section score of the standard section of the fetus may include the following operations:
301. and determining a weight value corresponding to each structural feature of the standard section of each frame of fetal ultrasound image.
In the embodiment of the invention, at least one structural feature exists in the standard tangent plane of each frame of fetal ultrasound image, and each structural feature has a corresponding weight value.
302. And calculating the section score of the standard section of each frame of fetal ultrasound image based on the weight value corresponding to each structural feature of each standard section and the characteristic parameter of the structural feature.
In the embodiment of the present invention, please refer to the detailed description of the relevant contents in the first embodiment and the second embodiment for the other relevant descriptions of step 301 and step 302 and the relevant descriptions of other schemes expanded on the basis of step 301 and step 302, which is not repeated herein.
Therefore, by implementing the method for determining the optimal standard section of the fetus described in fig. 3, the weight value of each structural feature of the standard section can be combined with the feature parameter of the structural feature, so that the section score of the standard section can be automatically calculated, the calculation accuracy and efficiency of the section score of the standard section can be improved, the optimal standard section can be automatically determined, and the growth and development conditions of the fetus can be accurately obtained.
Example four
Referring to fig. 4, fig. 4 is a schematic structural diagram of a device for determining an optimal standard section of a fetus according to an embodiment of the present invention. The apparatus for determining the optimal standard fetal cut plane depicted in fig. 4 may be applied to a standard cut plane determining server (service device), where the standard cut plane determining server may include a local standard cut plane determining server or a cloud standard cut plane determining server, and the embodiment of the present invention is not limited thereto. As shown in fig. 4, the apparatus for determining the optimal standard cut plane of the fetus may include an obtaining module 401, a first determining module 402, and a second determining module 403, wherein:
the obtaining module 401 is configured to obtain a standard section corresponding to each frame of fetal ultrasound image in multiple frames of fetal ultrasound images.
A first determining module 402, configured to determine a tangent score of the standard tangent plane of each frame of the fetal ultrasound image.
The second determining module 403 is configured to determine, according to the tangent plane scores of all the standard tangent planes, a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes, as an optimal standard tangent plane of all the fetal ultrasound images.
It can be seen that, by implementing the device for determining the optimal standard section of the fetus described in fig. 4, after the standard section of the ultrasound image of the fetus is obtained, the optimal standard section of the ultrasound image of the fetus does not need to be determined through manual analysis, the section score of the standard section of the ultrasound image of the fetus can be automatically determined, the standard section with the highest section score can be intelligently selected from all the section scores, the automatic determination of the optimal standard section is realized, the accuracy and the efficiency of determining the optimal standard section of the ultrasound image of the fetus can be improved, and the growth and development conditions of the fetus can be accurately obtained.
In an alternative embodiment, as shown in fig. 5, the apparatus further comprises a first determining module 404, wherein:
the first determining module 404 is configured to determine whether all the standard sections belong to the same standard section class after the first determining module 402 determines the section scores of the standard sections of each frame of the fetal ultrasound image, and when it is determined that all the standard sections belong to the same standard section class, trigger the second determining module 403 to execute the above-mentioned operation of determining the standard section corresponding to the highest section score from all the standard sections as the optimal standard section of all the fetal ultrasound images according to the section scores of all the standard sections.
It can be seen that, by implementing the determining device described in fig. 5, after the standard tangent planes of all the fetal ultrasound images are obtained, it can be further determined that all the standard tangent planes belong to the same type of standard tangent plane, if yes, the subsequent operation is performed, and the accuracy of determining the optimal standard tangent plane of the fetal ultrasound images can be improved; and whether all standard tangent planes belong to the same class is determined by providing the classes based on the structural characteristics of the standard tangent planes and/or the tangent plane marks of the standard tangent planes, so that the determination modes that all standard tangent planes belong to the standard tangent planes of the same class can be enriched, and the determination accuracy that all standard tangent planes belong to the standard tangent planes of the same class can be improved.
In another alternative embodiment, as shown in fig. 5, the apparatus further comprises a classification module 405, wherein:
the classifying module 405 is configured to, when the first determining module 404 determines that all the standard sections do not belong to the same category of standard sections, perform a classifying operation on the standard sections of all the fetal ultrasound images according to a preset classifying manner to obtain at least two standard section sets, where each standard section set includes the standard section of at least one frame of fetal ultrasound image, and all the standard sections included in each standard section set are the same category of standard sections.
The second determining module 403 determines, according to the tangent plane scores of all the standard tangent planes, a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes, and the mode of serving as the optimal standard tangent plane specifically is as follows:
and according to all the tangent plane scores corresponding to each standard tangent plane set, determining the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes included in each standard tangent plane set as the optimal standard tangent plane corresponding to each standard tangent plane set.
Therefore, the determining device described in fig. 5 can perform classification operation on all the standard sections when determining that the standard sections of all the fetal ultrasound images belong to different categories, and can obtain different categories of standard sections, thereby being beneficial to reducing the occurrence of reducing the situation of obtaining non-optimal standard sections due to different section categories, and further improving the accuracy and reliability of determining the optimal standard sections corresponding to different categories of standard sections.
In yet another alternative embodiment, as shown in fig. 5, the apparatus may further include a normalization module 406 and a filtering module 407, where:
a normalization module 406, configured to, in the second determining module 403, determine, according to all tangent plane scores corresponding to each standard tangent plane set, a standard tangent plane corresponding to the highest tangent plane score from all standard tangent planes included in each standard tangent plane set, and after the standard tangent plane is used as the optimal standard tangent plane corresponding to each standard tangent plane set, perform normalization operation on the tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set, so as to obtain a normalized tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set.
And the screening module 407 is configured to screen, according to the scores of all normalized sections, a standard section corresponding to the highest score of the normalized section from all standard sections, as an optimal standard section corresponding to all fetal ultrasound images.
It can be seen that, by implementing the determining device described in fig. 5, after the optimal standard tangent planes corresponding to the different types of standard tangent planes are obtained, normalization operation can be further performed on the tangent plane scores of the optimal standard tangent planes corresponding to the different types of standard tangent planes, so that the tangent plane scores of the optimal standard tangent planes corresponding to the different types of standard tangent planes can be made comparable, thereby improving the accuracy and efficiency of determining the optimal standard tangent planes corresponding to all fetal ultrasound images, and further facilitating accurate acquisition of the growth and development conditions of the fetus.
In yet another alternative embodiment, as shown in fig. 5, the apparatus further comprises a training module 408, wherein:
the obtaining module 401 is further configured to obtain a positive fetal ultrasound image sample and a negative fetal ultrasound image sample, where a pixel value of the positive fetal ultrasound image sample is greater than a pixel value of the negative fetal ultrasound image sample, and a key weight value influence factor of a structural feature of each positive fetal ultrasound image in the positive fetal ultrasound image sample and a key weight value influence factor of a structural feature of each negative fetal ultrasound image in the negative fetal ultrasound image sample include a degree of sharpness of the structural feature.
The training module 408 is configured to train the determined initial classification model based on the positive fetal ultrasound image sample and the negative fetal ultrasound image sample.
The obtaining module 401 is further configured to obtain the trained initial classification model as the determined classification model.
It can be seen that, by implementing the determining device described in fig. 5, the training operation can be performed on the initial classification model based on the sample fetal ultrasound image in advance, and the classification model meeting the requirement and being accurate can be obtained, so that the analysis accuracy and reliability of the sub-weight values of which the key weight value influence factors include the definition of the structural features are improved, and the calculation accuracy and efficiency of the weight values corresponding to the structural features are improved.
In yet another alternative embodiment, as shown in fig. 5, the apparatus further includes a second determining module 409, wherein:
a second determining module 409, configured to determine, after the first determining module 402 determines the tangent plane score of the standard tangent plane of each frame of the fetal ultrasound image, whether an abnormal standard tangent plane with a structural feature being an abnormal structural feature exists in all the standard tangent planes according to the structural features of all the standard tangent planes; when it is determined that there is no abnormal standard tangent plane in all the standard tangent planes, the second determining module 403 is triggered to execute the above-mentioned operation of determining the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes according to all the tangent plane scores, as the optimal standard tangent plane.
It can be seen that, by implementing the determining device described in fig. 5, after the section score of the standard section of the fetal ultrasound image is obtained, it can be further determined whether an abnormal standard section exists in all the standard sections, and if not, the determining operation of the optimal standard section is continuously executed, so that the accuracy of executing the determination of the optimal standard section can be improved, and the accuracy of determining the optimal standard section is improved.
In yet another alternative embodiment, as shown in fig. 5, the apparatus further comprises a modification module 410, wherein:
the second determining module 403 is further configured to determine a score correction coefficient corresponding to each abnormal standard tangent plane when the second determining module 409 determines that at least one abnormal standard tangent plane exists in all the standard tangent planes.
The correcting module 410 is configured to correct the score of the tangent plane of each abnormal standard tangent plane based on the score correction coefficient corresponding to each abnormal standard tangent plane, and trigger the second determining module 403 to perform the above-mentioned operation of determining the standard tangent plane corresponding to the highest score of the tangent plane from all the standard tangent planes as the optimal standard tangent plane according to the score of all the tangent planes.
It can be seen that, by implementing the determining device described in fig. 5, after the section score of the standard section of the fetal ultrasound image is obtained, whether an abnormal standard section exists in all the standard sections can be further determined, and if the abnormal standard section exists, the section score of the abnormal standard section is corrected based on the score correction coefficient, so that the accuracy of determining the section score of the abnormal standard section can be improved, the situation that the non-optimal standard section is obtained due to the fact that the optimal standard section is continuously obtained when the abnormal standard section occurs is reduced, and the accuracy and the reliability of determining the optimal standard section when the abnormal standard section occurs are improved.
In yet another alternative embodiment, as shown in fig. 5, the manner that the second determining module 409 determines whether there is an abnormal standard section with a structural feature being an abnormal structural feature in all the standard sections according to the structural features of all the standard sections specifically is as follows:
acquiring target information of each structural feature of each standard section, wherein the target information of each structural feature is used for determining whether the standard section in which the structural feature is located is an abnormal standard section;
judging whether each structural feature is matched with the standard tangent plane according to the target information of each structural feature of each standard tangent plane;
and when judging that the non-matching structural features which are not matched with the standard tangent plane are existed in all the structural features, determining that an abnormal standard tangent plane with the structural features as abnormal structural features exists in all the standard tangent planes, wherein the abnormal standard tangent plane is the standard tangent plane with the non-matching structural features.
It can be seen that, by implementing the determining apparatus described in fig. 5, it is possible to determine the abnormal standard tangent plane by acquiring the target information of each structural feature of the standard tangent plane and determining whether each structural feature matches the corresponding standard tangent plane according to the target information of each structural feature.
In yet another alternative embodiment, at least one structural feature exists in the standard tangential plane of each frame of fetal ultrasound image, and each structural feature has a corresponding weight value; as shown in fig. 6, the first determining module 402 may include a determining sub-module 4021 and a calculating sub-module 4022, wherein:
the determining sub-module 4021 is configured to determine a weight value corresponding to each structural feature of the standard section of each frame of fetal ultrasound image.
The calculating sub-module 4022 is configured to calculate a section score of the standard section of each frame of the fetal ultrasound image based on the weight value corresponding to each structural feature of each standard section and the feature parameter of the structural feature.
Therefore, by implementing the determination device described in fig. 6, the weight value of each structural feature of the standard tangent plane can be combined with the feature parameter of the structural feature, so that the automatic calculation of the tangent plane score of the standard tangent plane can be realized, the calculation accuracy and efficiency of the tangent plane score of the standard tangent plane can be improved, the automatic determination of the optimal standard tangent plane can be favorably realized, and the growth and development conditions of the fetus can be accurately obtained.
In yet another alternative embodiment, as shown in fig. 7, the determining sub-module 4021 includes a determining unit 40211 and a calculating unit 40212, wherein:
the determining unit 40211 is configured to determine a key weight value influence factor corresponding to each structural feature of the standard section of each frame of fetal ultrasound image, where the number of the key weight value influence factors corresponding to each structural feature is greater than or equal to 1, and each key weight value influence factor has a corresponding sub-weight value.
The determining unit 40211 is further configured to determine a sub-weight value corresponding to each key weight value influence factor according to each key weight value influence factor corresponding to each structural feature.
The calculating unit 40212 is configured to calculate a sum of all sub weight values corresponding to each structural feature as a weight value corresponding to each structural feature.
It can be seen that, by implementing the determining apparatus described in fig. 7, the key weight value influence factor corresponding to each structural feature can be determined in a targeted manner, and the sub-weight values corresponding to all the key weight value influence factors are determined as the weight values corresponding to the structural feature, so that the calculation accuracy of the weight values of the structural features can be improved, thereby improving the calculation accuracy of the tangent plane score of the corresponding standard tangent plane, and further improving the determination accuracy of the optimal standard tangent plane.
In yet another alternative embodiment, as shown in fig. 7, the determining unit 40211 determines, according to each key weight value influence factor corresponding to each structural feature, a sub-weight value corresponding to each key weight value influence factor specifically:
for any structural feature, when the key weight value influence factor corresponding to the structural feature comprises a geometric parameter of the outline of the structural feature, determining a sub-weight value corresponding to the geometric parameter of the outline of the structural feature according to the geometric parameter of the outline of the structural feature, wherein the geometric parameter of the outline of the structural feature comprises the size and/or area of the outline of the structural feature;
for any structural feature, when the key weight value influence factor corresponding to the structural feature comprises the definition of the structural feature, inputting the fetal ultrasound image corresponding to the structural feature into the determined classification model for analysis, and acquiring an analysis result output by the classification model as a sub-weight value corresponding to the definition of the structural feature;
for any structural feature, when the key weight value influence factor corresponding to the structural feature comprises the integrity of the structural feature, calculating a geometric parameter corresponding to the structural feature according to the outline of the structural feature, and determining a sub-weight value corresponding to the integrity of the structural feature according to the geometric parameter corresponding to the structural feature;
for any structural feature, when the key weight value influence factor corresponding to the structural feature includes the position of the structural feature in the standard tangent plane, calculating the area of the region surrounded by the outline of the structural feature, and determining the sub-weight value corresponding to the position of the structural feature in the standard tangent plane based on the relative position relationship between the brain midline corresponding to the structural feature and the area of the region surrounded by the outline of the structural feature.
It can be seen that, by implementing the determining device described in fig. 7, a corresponding sub-weight value determining manner can be selected according to different key weight value influence factors, so that not only can the sub-weight value corresponding to the key weight value influence factor be obtained, but also the obtaining efficiency and accuracy of the sub-weight value can be improved, thereby improving the calculation accuracy and efficiency of the weight value corresponding to the structural feature, and further improving the calculation accuracy and efficiency of the tangent plane score corresponding to the standard tangent plane.
In yet another alternative embodiment, as shown in fig. 5, the second determining module 403 is further configured to determine a ratio of a target feature of each frame of the fetal ultrasound image, where the ratio of the target feature is used to represent a display ratio of the target feature to a display device, and the target feature of each frame of the fetal ultrasound image includes a structural feature in a standard section of the fetal ultrasound image or a standard section of the fetal ultrasound image.
The second determining module 403 is further configured to determine a score coefficient corresponding to the proportion of the standard section of each frame of fetal ultrasound image when the target feature of each frame of fetal ultrasound image is the standard section of the fetal ultrasound image and after the first determining module 402 determines the score of the standard section of each frame of fetal ultrasound image.
The obtaining module 401 is further configured to correct the tangent plane score of the standard tangent plane of each frame of the fetal ultrasound image based on the score coefficient corresponding to the percentage of the standard tangent plane of each frame of the fetal ultrasound image, to obtain the tangent plane score of the standard tangent plane of each frame of the fetal ultrasound image after correction, and to trigger the second determining module 403 to execute the above-mentioned operation of determining the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes according to the tangent plane scores of all the standard tangent planes, as the optimal standard tangent plane of all the fetal ultrasound images.
It can be seen that, after the section score of the standard section of the fetal ultrasound image is obtained by implementing the determining device described in fig. 5, the section score is further updated according to the score coefficient corresponding to the ratio of the obtained standard section of the fetal ultrasound image to the display area of the current display device, which is beneficial to improving the accuracy and reliability of determining the section score of the standard section of the fetal ultrasound image, and further improving the accuracy and reliability of determining the optimal standard section of the fetal ultrasound image.
In yet another alternative embodiment, as shown in fig. 7, the determining unit 40211 determines, according to each key weight value influence factor corresponding to each structural feature, a sub-weight value corresponding to each key weight value influence factor specifically:
and when the target feature of each frame of fetal ultrasound image is the structural feature in the standard section of the fetal ultrasound image, determining a sub-weight value matched with the proportion of the structural feature according to the proportion of the structural feature for any structural feature.
It can be seen that, by implementing the determining apparatus described in fig. 7, by calculating the proportion of the structural feature in the standard section of the fetal ultrasound image and determining the sub-weight value corresponding to the proportion, the determination of the weight value corresponding to the structural feature can be achieved, and the calculation dimension of the weight value corresponding to the structural feature is increased, so that the calculation accuracy and reliability of the weight value corresponding to the structural feature can be further improved, and further, the determination accuracy and reliability of the section score of the standard section of the fetal ultrasound image are improved, and further, the determination accuracy and reliability of the optimal standard section of the fetal ultrasound image are improved.
In yet another alternative embodiment, as shown in fig. 7, the determining unit 40211 calculates the geometric parameters corresponding to the structural features according to the profiles of the structural features by:
calculating the length of the outline of the structural feature as a geometric parameter corresponding to the structural feature; and/or the presence of a gas in the gas,
determining a central point corresponding to the contour of the structural feature, and determining a central angle corresponding to the contour of the structural feature as a geometric parameter corresponding to the structural feature based on the central point corresponding to the contour of the structural feature and the contour of the structural feature; and/or the presence of a gas in the gas,
fitting the contour of the structural feature based on the determined fitting method to obtain a target contour of the structural feature;
and/or determining a central point corresponding to the target contour of the structural feature, and determining a central angle corresponding to the overlapped part contour as the geometric parameter corresponding to the structural feature based on the central point corresponding to the target contour of the structural feature and the overlapped part contour.
It can be seen that, by implementing the determination apparatus described in fig. 7, different fitting modes can be selected according to the size of the circular arc radius of the structural feature of the fetal ultrasound image, so that not only can the fitting of the structural feature be realized, but also the fitting efficiency and accuracy of the structural feature can be improved, and thus the calculation accuracy of the geometric parameters of the structural feature is improved.
In yet another alternative embodiment, the feature parameters of each structural feature of each standard slice include a class probability of the structural feature and a location probability of the structural feature. As shown in fig. 6, the calculation sub-module 4022 calculates a tangent plane score of the standard tangent plane of each frame of fetal ultrasound image based on the weight value corresponding to each structural feature of each standard tangent plane and the feature parameter of the structural feature in a specific manner:
calculating a structural score corresponding to each structural feature of each standard tangent plane based on the weight value corresponding to each structural feature of each standard tangent plane, the category probability of the structural feature and the position probability of the structural feature;
and calculating the sum of the structural scores corresponding to all the structural features of each standard section to serve as the section score of the standard section of each frame of fetal ultrasound image.
Therefore, the determining device described in fig. 6 can calculate the tangent plane score of the standard tangent plane by calculating the structure score corresponding to each structure feature of the standard tangent plane, and is beneficial to improving the accuracy and efficiency of calculating the tangent plane score of the standard tangent plane; and different parameters are selected according to different structural characteristics, so that the calculation accuracy and efficiency of the structural scores corresponding to the structural characteristics can be improved, and the calculation accuracy and efficiency of the section scores of the standard sections are further improved.
EXAMPLE five
Referring to fig. 8, fig. 8 is a schematic diagram of another apparatus for determining an optimal standard section of a fetus according to the embodiment of the present invention. The apparatus for determining an optimal standard fetal cut plane depicted in fig. 8 may be applied to a standard cut plane determining server (service device), where the standard cut plane determining server may include a local standard cut plane determining server or a cloud standard cut plane determining server, and the embodiment of the present invention is not limited thereto. As shown in fig. 8, the device for determining the optimal standard cut plane of the fetus may include:
a memory 801 in which executable program code is stored;
a processor 802 coupled with the memory 801;
further, an input interface 803 and an output interface 804 coupled to the processor 802 may also be included;
the processor 802 calls the executable program code stored in the memory 801 to execute some or all of the steps of the method for determining the optimal standard fetal section described in the first embodiment or the second embodiment.
EXAMPLE six
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of the method for determining the optimal standard section of the fetus described in the first embodiment or the second embodiment.
EXAMPLE seven
The embodiment of the invention discloses a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, wherein the computer program is operable to make a computer execute part or all of the steps of the method for determining the optimal standard section of the fetus described in the first embodiment or the second embodiment.
The above-described embodiments of the apparatus are merely illustrative, and the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above detailed description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, where the storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc-Read-Only Memory (CD-ROM), or other disk memories, CD-ROMs, or other magnetic disks, A tape memory, or any other medium readable by a computer that can be used to carry or store data.
Finally, it should be noted that: the method and device for determining the optimal standard section of the fetus disclosed in the embodiments of the present invention are only the preferred embodiments of the present invention, and are only used for illustrating the technical solution of the present invention, not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (16)

1. A method for determining an optimal standard section of a fetus, the method comprising:
obtaining a standard section of each frame of fetal ultrasonic image in a plurality of frames of fetal ultrasonic images, and determining section values of the standard sections of each frame of fetal ultrasonic images;
and determining a standard section corresponding to the highest section score from all the standard sections according to the section scores of all the standard sections, and taking the standard section as the optimal standard section of all the fetal ultrasonic images.
2. The method for determining the optimal standard section of the fetus according to claim 1, wherein after determining the section score of the standard section of each frame of the ultrasound image of the fetus, the method further comprises:
judging whether all the standard tangent planes belong to the same class of standard tangent planes;
and when all the standard sections are judged to belong to the same type of standard sections, triggering and executing the operation of determining the standard section corresponding to the highest section score from all the standard sections as the optimal standard section of all the fetal ultrasonic images according to the section scores of all the standard sections.
3. The method for determining the optimal standard section of the fetus according to claim 2, further comprising:
when all the standard sections are judged not to belong to the same type of standard sections, classifying the standard sections of all the fetal ultrasonic images according to a preset classification mode to obtain at least two standard section sets, wherein each standard section set comprises at least one frame of standard sections of the fetal ultrasonic images, and all the standard sections of each standard section set are the same type of standard sections;
wherein, according to the section scores of all the standard sections, determining the standard section corresponding to the highest section score from all the standard sections as the optimal standard section, and the method comprises the following steps:
and according to all the tangent plane scores corresponding to each standard tangent plane set, determining a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes included in each standard tangent plane set as the optimal standard tangent plane corresponding to each standard tangent plane set.
4. The method for determining the optimal standard section for fetus according to claim 3, wherein the method further comprises, after determining the standard section corresponding to the highest section score from all the standard sections included in each standard section set according to all the section scores corresponding to each standard section set, as the optimal standard section corresponding to each standard section set:
performing normalization operation on the tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set to obtain the normalized tangent plane score of the optimal standard tangent plane corresponding to each standard tangent plane set;
and screening the standard tangent plane corresponding to the highest normalized tangent plane score from all the standard tangent planes according to all the normalized tangent plane scores to serve as the optimal standard tangent plane corresponding to all the fetal ultrasonic images.
5. The method for determining the optimal standard section of a fetus according to any one of claims 1 to 4, wherein at least one structural feature exists in the standard section of each frame of the ultrasound image of the fetus, and each structural feature has a corresponding weight value;
and the determining the section score of the standard section of each frame of the fetal ultrasound image comprises the following steps:
determining a weight value corresponding to each structural feature of a standard section of each frame of the fetal ultrasonic image;
and calculating the section score of the standard section of each frame of the fetal ultrasound image based on the weight value corresponding to each structural feature of each standard section and the characteristic parameter of the structural feature.
6. The method for determining the optimal standard section of the fetus according to claim 5, wherein the determining the weight value corresponding to each structural feature of the standard section of each frame of the fetal ultrasound image comprises:
determining a key weight value influence factor corresponding to each structural feature of a standard tangent plane of each frame of the fetal ultrasound image, wherein the number of the key weight value influence factors corresponding to each structural feature is more than or equal to 1, and each key weight value influence factor has a corresponding sub weight value;
according to each key weight value influence factor corresponding to each structural feature, determining a sub weight value corresponding to each key weight value influence factor, and calculating the sum of all sub weight values corresponding to each structural feature to serve as the weight value corresponding to each structural feature.
7. The method of claim 6, wherein the determining a sub-weight value corresponding to each key weight value influence factor according to each key weight value influence factor corresponding to each structural feature comprises:
for any structural feature, when the key weight value influence factor corresponding to the structural feature includes a geometric parameter of the contour of the structural feature, determining a sub-weight value corresponding to the geometric parameter of the contour of the structural feature according to the geometric parameter of the contour of the structural feature, where the geometric parameter of the contour of the structural feature includes a size and/or an area of the contour of the structural feature;
for any structural feature, when the key weight value influence factor corresponding to the structural feature includes the definition of the structural feature, inputting the fetal ultrasound image corresponding to the structural feature into the determined classification model for analysis, and acquiring an analysis result output by the classification model as a sub-weight value corresponding to the definition of the structural feature;
for any structural feature, when the key weight value influence factor corresponding to the structural feature comprises the integrity of the structural feature, calculating a geometric parameter corresponding to the structural feature according to the contour of the structural feature, and determining a sub-weight value corresponding to the integrity of the structural feature according to the geometric parameter corresponding to the structural feature;
for any one of the structural features, when the key weight value influence factor corresponding to the structural feature includes the position of the structural feature in the standard tangent plane, determining a sub-weight value corresponding to the position of the structural feature in the standard tangent plane based on the relative position relationship between the brain midline corresponding to the structural feature and the region surrounded by the contour of the structural feature.
8. The method for determining the optimal standard section of the fetus according to claim 6, further comprising:
determining the proportion of the target features of each frame of the fetal ultrasound image, wherein the proportion of the target features is used for representing the display proportion of the target features and the display device where the target features are located, and the target features of each frame of the fetal ultrasound image comprise the structural features in the standard section of the fetal ultrasound image or the standard section of the fetal ultrasound image;
and when the target feature of each frame of the fetal ultrasound image is the standard section of the fetal ultrasound image, after determining the section score of the standard section of each frame of the fetal ultrasound image, the method further comprises:
determining a score coefficient corresponding to the proportion of the standard tangent plane of each frame of the fetal ultrasound image, correcting the tangent plane score of the standard tangent plane of each frame of the fetal ultrasound image based on the score coefficient corresponding to the proportion of the standard tangent plane of each frame of the fetal ultrasound image to obtain the corrected tangent plane score of the standard tangent plane of each frame of the fetal ultrasound image, and triggering and executing the operation of determining the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes as the optimal standard tangent plane of all the fetal ultrasound images according to the tangent plane scores of all the standard tangent planes;
when the target feature of each frame of the fetal ultrasound image is a structural feature in a standard section of the fetal ultrasound image, determining a sub-weight value corresponding to each key weight value influence factor according to each key weight value influence factor corresponding to each structural feature, including:
for any structural feature, determining a sub-weight value matched with the proportion of the structural feature according to the proportion of the structural feature.
9. The method for determining the optimal standard section of the fetus according to claim 7, wherein the calculating the geometric parameters corresponding to the structural feature according to the contour of the structural feature comprises:
calculating the length of the contour of the structural feature as a geometric parameter corresponding to the structural feature; and/or the presence of a gas in the gas,
determining a central point corresponding to the contour of the structural feature, and determining a central angle corresponding to the contour of the structural feature as a geometric parameter corresponding to the structural feature based on the central point corresponding to the contour of the structural feature and the contour of the structural feature; and/or the presence of a gas in the gas,
fitting the contour of the structural feature based on the determined fitting method to obtain a target contour of the structural feature;
calculating the length of the outline of the structural feature and the outline of the overlapped part of the target outline of the structural feature as the geometric parameter corresponding to the structural feature, and/or determining the central point corresponding to the target outline of the structural feature, and determining the central angle corresponding to the overlapped part of the outline based on the central point corresponding to the target outline of the structural feature and the overlapped part of the outline as the geometric parameter corresponding to the structural feature.
10. The method for determining the optimal standard section of the fetus according to claim 8 or 9, wherein the method comprises the following steps:
obtaining a positive fetal ultrasound image sample and a negative fetal ultrasound image sample, wherein the pixel value of the positive fetal ultrasound image sample is greater than the pixel value of the negative fetal ultrasound image sample, and the key weight value influence factor of the structural feature of each positive fetal ultrasound image in the positive fetal ultrasound image sample and each negative fetal ultrasound image in the negative fetal ultrasound image sample comprises the definition of the structural feature;
training the determined initial classification model based on the positive fetal ultrasound image sample and the negative fetal ultrasound image sample, and acquiring the trained initial classification model as the determined classification model.
11. The method for determining the optimal standard section of a fetus according to any one of claims 5 to 10, wherein the characteristic parameters of each of the structural features of each of the standard sections comprise a class probability of the structural feature and a position probability of the structural feature;
wherein, the calculating the section score of the standard section of each frame of the fetal ultrasound image based on the weight value corresponding to each structural feature of each standard section and the characteristic parameter of the structural feature includes:
calculating a structure score corresponding to each structural feature of each standard tangent plane based on a weight value corresponding to each structural feature of each standard tangent plane, the category probability of the structural feature and the position probability of the structural feature;
and calculating the sum of the structural scores corresponding to all the structural features of each standard section to serve as the section score of the standard section of each frame of the fetal ultrasound image.
12. The method for determining the optimal standard section of fetus according to any one of claims 1 to 9, wherein after determining the section score of the standard section of each frame of the ultrasound image of fetus, the method further comprises:
judging whether an abnormal standard section with the structural characteristics being abnormal structural characteristics exists in all the standard sections according to the structural characteristics of all the standard sections;
and when judging that the abnormal standard tangent plane does not exist in all the standard tangent planes, triggering and executing the operation of determining the standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes as the optimal standard tangent plane according to all the tangent plane scores.
13. The method for determining the optimal standard section of the fetus according to claim 12, wherein the method comprises:
when judging that at least one abnormal standard tangent plane exists in all the standard tangent planes, determining a score correction coefficient corresponding to each abnormal standard tangent plane;
correcting the section score of the abnormal standard section based on the score correction coefficient corresponding to each abnormal standard section, and triggering and executing the operation of determining the standard section corresponding to the highest section score from all the standard sections as the optimal standard section according to all the section scores.
14. The method for determining the optimal standard section of the fetus according to claim 13, wherein the step of determining whether the abnormal standard section with the structural feature being the abnormal structural feature exists in all the standard sections according to the structural features of all the standard sections comprises:
acquiring target information of each structural feature of each standard tangent plane, wherein the target information of each structural feature is used for determining whether the standard tangent plane in which the structural feature is located is an abnormal standard tangent plane;
judging whether each structural feature is matched with the standard tangent plane according to the target information of each structural feature of each standard tangent plane;
and when judging that the non-matching structural features which are not matched with the standard tangent plane are existed in all the structural features, determining that an abnormal standard tangent plane with the structural features as abnormal structural features exists in all the standard tangent planes, wherein the abnormal standard tangent plane is the standard tangent plane with the non-matching structural features.
15. An apparatus for determining an optimal standard section of a fetus, the apparatus comprising:
the acquisition module is used for acquiring a standard section corresponding to each frame of fetal ultrasound image in a plurality of frames of fetal ultrasound images;
the first determining module is used for determining the section score of the standard section of each frame of the fetal ultrasonic image;
and the second determining module is used for determining a standard tangent plane corresponding to the highest tangent plane score from all the standard tangent planes according to the tangent plane scores of all the standard tangent planes, and the standard tangent plane is used as the optimal standard tangent plane of all the fetal ultrasonic images.
16. An apparatus for determining an optimal standard section of a fetus, the apparatus comprising:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to execute the method for determining the optimal standard cut plane of the fetus as claimed in any one of claims 1 to 14.
CN202011015507.6A 2020-09-24 2020-09-24 Method and device for determining optimal standard section of fetus Active CN112155602B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202011015507.6A CN112155602B (en) 2020-09-24 2020-09-24 Method and device for determining optimal standard section of fetus
PCT/CN2021/096821 WO2022062458A1 (en) 2020-09-24 2021-05-28 Method and apparatus for determining optimal fetal standard view

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011015507.6A CN112155602B (en) 2020-09-24 2020-09-24 Method and device for determining optimal standard section of fetus

Publications (2)

Publication Number Publication Date
CN112155602A true CN112155602A (en) 2021-01-01
CN112155602B CN112155602B (en) 2023-05-05

Family

ID=73863773

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011015507.6A Active CN112155602B (en) 2020-09-24 2020-09-24 Method and device for determining optimal standard section of fetus

Country Status (2)

Country Link
CN (1) CN112155602B (en)
WO (1) WO2022062458A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112991289A (en) * 2021-03-10 2021-06-18 深圳市鹭鸣科技有限公司 Method and device for processing standard image section
WO2022062458A1 (en) * 2020-09-24 2022-03-31 广州爱孕记信息科技有限公司 Method and apparatus for determining optimal fetal standard view
WO2022062457A1 (en) * 2020-09-24 2022-03-31 广州爱孕记信息科技有限公司 Method and apparatus for determining weight values of fetal structure features
CN115760851A (en) * 2023-01-06 2023-03-07 首都儿科研究所附属儿童医院 Ultrasonic image data processing method and system based on machine learning

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115919367A (en) * 2022-12-09 2023-04-07 开立生物医疗科技(武汉)有限公司 Ultrasonic image processing method and device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3510933A1 (en) * 2018-01-10 2019-07-17 Samsung Medison Co., Ltd. Ultrasound diagnosis apparatus and method for controlling the same
CN110033020A (en) * 2019-03-07 2019-07-19 李胜利 The Plays tangent plane picture recognition methods of fetal ultrasound image and identifying system based on deep learning
CN110555836A (en) * 2019-09-05 2019-12-10 李肯立 Automatic identification method and system for standard fetal section in ultrasonic image
CN110604592A (en) * 2019-03-04 2019-12-24 北京大学第三医院 Hip joint imaging method and hip joint imaging system
CN111223092A (en) * 2020-02-28 2020-06-02 长沙大端信息科技有限公司 Automatic quality control system and detection method for ultrasonic sectional images of fetus
CN111402244A (en) * 2020-03-20 2020-07-10 华侨大学 Automatic classification method for standard fetal heart tangent planes

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112184656B (en) * 2020-09-24 2024-04-16 广州爱孕记信息科技有限公司 Method and device for determining fetal section based on ultrasonic dynamic image
CN112155602B (en) * 2020-09-24 2023-05-05 广州爱孕记信息科技有限公司 Method and device for determining optimal standard section of fetus

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3510933A1 (en) * 2018-01-10 2019-07-17 Samsung Medison Co., Ltd. Ultrasound diagnosis apparatus and method for controlling the same
CN110604592A (en) * 2019-03-04 2019-12-24 北京大学第三医院 Hip joint imaging method and hip joint imaging system
CN110033020A (en) * 2019-03-07 2019-07-19 李胜利 The Plays tangent plane picture recognition methods of fetal ultrasound image and identifying system based on deep learning
CN110555836A (en) * 2019-09-05 2019-12-10 李肯立 Automatic identification method and system for standard fetal section in ultrasonic image
CN111223092A (en) * 2020-02-28 2020-06-02 长沙大端信息科技有限公司 Automatic quality control system and detection method for ultrasonic sectional images of fetus
CN111402244A (en) * 2020-03-20 2020-07-10 华侨大学 Automatic classification method for standard fetal heart tangent planes

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022062458A1 (en) * 2020-09-24 2022-03-31 广州爱孕记信息科技有限公司 Method and apparatus for determining optimal fetal standard view
WO2022062457A1 (en) * 2020-09-24 2022-03-31 广州爱孕记信息科技有限公司 Method and apparatus for determining weight values of fetal structure features
CN112991289A (en) * 2021-03-10 2021-06-18 深圳市鹭鸣科技有限公司 Method and device for processing standard image section
CN112991289B (en) * 2021-03-10 2024-03-26 深圳市鹭鸣科技有限公司 Processing method and device for standard section of image
CN115760851A (en) * 2023-01-06 2023-03-07 首都儿科研究所附属儿童医院 Ultrasonic image data processing method and system based on machine learning

Also Published As

Publication number Publication date
CN112155602B (en) 2023-05-05
WO2022062458A1 (en) 2022-03-31

Similar Documents

Publication Publication Date Title
CN112155602A (en) Method and device for determining optimal standard section of fetus
CN110648350B (en) Liver blood vessel segmentation method and device and electronic equipment
CN109389592B (en) Method, device and system for calculating coronary artery calcification score
US8116544B2 (en) Apparatus, method, and program for detecting three dimensional abdominal cavity regions
CN112184656B (en) Method and device for determining fetal section based on ultrasonic dynamic image
CN112155601B (en) Method and device for determining imaging quality control of fetal ultrasound image
CN112215806A (en) Output control method, device and system for detection result of fetus ultrasonic image
EP3644232B1 (en) Method and device for classifying samples to be assessed
CN112232206B (en) Face recognition method and face recognition platform based on big data and artificial intelligence
CN111462102A (en) Intelligent analysis system and method based on novel coronavirus pneumonia X-ray chest radiography
CN116092680B (en) Abdominal aortic aneurysm early prediction method and system based on random forest algorithm
CN112233167A (en) Automatic measurement method and device for structural characteristics of fetus
CN112508086A (en) System and method for classifying medical images
CN112155603B (en) Weight value determining method and device for fetal structural characteristics
CN111724371A (en) Data processing method and device and electronic equipment
JP2002230546A (en) Image processing program, computer readable storage medium storing it, and image processing method and device
CN113763331A (en) Coronary artery dominant type determination method, device, storage medium, and electronic apparatus
CN114612967B (en) Face clustering method, device, equipment and storage medium
CN115907003A (en) Measurement learning-based detection method and system for updating federal learning malicious model
CN112232338B (en) Data entry method, device, equipment and storage medium for warranty claim checking process
CN115797186A (en) Image restoration method and device, electronic equipment and storage medium
CN111524081B (en) Lung image angle correction method, device, electronic equipment and storage medium
CN115359051B (en) Aneurysm identification method based on pattern identification
CN115312178A (en) Acute hypotension data processing method and device based on noninvasive parameters
CN117132585A (en) Image processing method and device applied to early warning of malocclusion

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
PE01 Entry into force of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: A Method and Device for Determining the Optimal Standard Section of the Fetus

Effective date of registration: 20231011

Granted publication date: 20230505

Pledgee: Bank of China Limited by Share Ltd. Guangzhou Haizhu branch

Pledgor: GUANGZHOU AIYUN INFORMATION TECHNOLOGY CO.,LTD.

Registration number: Y2023980060768