CN109242837B - Method, system, apparatus and storage medium for measuring cervical shaft angle in pelvic X-ray film - Google Patents
Method, system, apparatus and storage medium for measuring cervical shaft angle in pelvic X-ray film Download PDFInfo
- Publication number
- CN109242837B CN109242837B CN201810992671.9A CN201810992671A CN109242837B CN 109242837 B CN109242837 B CN 109242837B CN 201810992671 A CN201810992671 A CN 201810992671A CN 109242837 B CN109242837 B CN 109242837B
- Authority
- CN
- China
- Prior art keywords
- femoral
- shaft
- angle
- neck
- femoral neck
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Abstract
The invention provides a method, a system, equipment and a storage medium for measuring a cervical shaft angle in a pelvis X-ray film, wherein the method for measuring the cervical shaft angle in the pelvis X-ray film comprises the following steps: acquiring an X-ray image containing a pelvis; detecting a femoral shaft area and a femoral neck area in the X-ray image; extracting a longitudinal axis of a femoral shaft from the femoral shaft region and a minor axis of a femoral neck from the femoral neck region; and acquiring a shaft angle according to the longitudinal axis of the femoral shaft and the minor axis of the femoral neck. The invention can accurately and efficiently automatically measure the cervical shaft angle in the pelvis X-ray film, and effectively solves the problems that misjudgment is easy to occur and time and labor are wasted because the cervical shaft angle in the X-ray film is judged by depending on subjective observation of medical staff or a hand-drawing method in the prior art.
Description
Technical Field
The invention belongs to the technical field of image processing, particularly relates to the technical field of X-ray image processing, and particularly relates to a method, a system, equipment and a storage medium for measuring a cervical spine angle in a pelvis X-ray image.
Background
The shaft angle is the angle formed between the long axis of the femoral neck and the longitudinal axis of the femoral shaft, and is also known as the angle of inclination. The normal value is between 110-140 degrees, the average for men is 132 degrees and the average for women is 127 degrees. If the angle of the shaft of the neck is larger than the normal value, the hip is everted, and if the angle is smaller than the normal value, the hip is everted. The angle of the cervical shaft is an important indicator for diagnosing hip dysplasia and impingement syndrome. In medical practice, medical staff often judge whether the cervical shaft angle is in a normal range by a subjective observation method on a pelvis X-ray film or measure the numerical value of the cervical shaft angle by a manual drawing method. The subjective observation method is fast but depends on the experience of medical care personnel, so the judgment result is different due to different subjective differences of the medical care personnel, and misjudgment is easy to occur. The manual drawing method is highly accurate but time-consuming.
Therefore, how to accurately and efficiently measure the cervical shaft angle automatically from the pelvis X-ray film is an urgent problem to be solved.
Disclosure of Invention
In view of the above-mentioned shortcomings in the prior art, an object of the present invention is to provide a method, a system, a device and a storage medium for measuring the cervical shaft angle in a pelvic X-ray film, which are used to solve the problems in the prior art that misjudgment is easy to occur and time and labor are wasted when the cervical shaft angle in the X-ray film is judged by means of subjective observation of medical staff or a hand-drawing method.
To achieve the above and other related objects, the present invention provides a method for measuring a cervical shaft angle in a pelvic X-ray examination, the method comprising: acquiring an X-ray image containing a pelvis; detecting a femoral shaft area and a femoral neck area in the X-ray image; extracting a longitudinal axis of a femoral shaft from the femoral shaft region and a minor axis of a femoral neck from the femoral neck region; and acquiring a shaft angle according to the longitudinal axis of the femoral shaft and the minor axis of the femoral neck.
In an embodiment of the present invention, a femoral shaft region in the X-ray image is detected by a femoral shaft detection model; and detecting the femoral neck area in the X-ray image through a femoral neck detection model.
In an embodiment of the present invention, the method for measuring the cervical shaft angle in the pelvic X-ray film further includes: obtaining a plurality of pelvis X-ray film samples; marking a femoral shaft area and a femoral neck area in the pelvis X-ray film sample respectively to form a training picture set; and training a target detection neural network model through the training picture set to obtain the femoral shaft detection model and the femoral neck detection model.
In an embodiment of the present invention, an implementation manner of extracting a longitudinal axis of the femoral shaft from the femoral shaft region includes: intercepting a femoral shaft region image; extracting a femoral shaft edge point from the femoral shaft region image; clustering the backbone edge points to obtain two types of backbone edge points with the largest quantity: a first diaphysis point set and a second diaphysis point set; fitting a first straight line according to the first femoral shaft point set, making a vertical line for each point in the second femoral shaft point set to the first straight line respectively, and taking a midpoint of each vertical line to form a third femoral shaft point set; fitting a second straight line according to the second femoral shaft point set, making a vertical line for each point in the first femoral shaft point set to the second straight line, and taking a midpoint of each vertical line to form a fourth femoral shaft point set; and fitting a third straight line according to the third femoral shaft point set and the fourth femoral shaft point set, wherein the third straight line is the longitudinal axis of the femoral shaft.
In one embodiment of the present invention, one implementation of extracting the short axis of the femoral neck from the femoral neck region comprises: intercepting an image of a femoral neck region; extracting femoral neck edge points from the femoral shaft region image; clustering the backbone edge points to obtain two types of backbone edge points with the largest quantity: a first set of femoral neck points and a second set of femoral neck points; acquiring Euclidean distance between each point in the first femur neck point set and each point in the second femur neck point set; acquiring two points with the shortest Euclidean distance: the first point and the second point, and the connecting line segment between the first point and the second point is the short axis of the femoral neck.
In an embodiment of the present invention, one implementation of the obtaining of the shaft angle according to the longitudinal axis of the femoral shaft and the minor axis of the femoral neck includes: making a perpendicular bisector for the short axis of the femoral neck, and obtaining the long axis of the femoral neck; acquiring an inclination angle A of a long axis of the femoral neck and an inclination angle B of a longitudinal axis of the femoral shaft; acquiring the absolute value of the difference value of the inclination angle A and the inclination angle B, and recording the absolute value as an angle C; if the angle C is an obtuse angle, the angle C is the neck angle, and if the angle C is an acute angle, the neck angle is 180-angle C.
The embodiment of the present invention further provides a system for measuring a cervical shaft angle in a pelvic X-ray film, the system for measuring a cervical shaft angle in a pelvic X-ray film comprising: the image acquisition module is used for acquiring an X-ray image containing the pelvis; the area detection module is used for detecting a femoral shaft area and a femoral neck area in the X-ray image; an axis extraction module for extracting a longitudinal axis of the femoral shaft from the femoral shaft region and extracting a short axis of the femoral neck from the femoral neck region; and the neck shaft angle acquisition module is used for acquiring a neck shaft angle according to the longitudinal axis of the femoral shaft and the short axis of the femoral neck.
In an embodiment of the present invention, the system for measuring the cervical shaft angle in the pelvic X-ray film further includes: the model training module is used for acquiring a plurality of pelvis X-ray film samples, labeling femoral shaft areas and femoral neck areas in the pelvis X-ray film samples respectively to form a training picture set, training a target detection neural network model through the training picture set, and acquiring a femoral shaft detection model for detecting the femoral shaft areas in the X-ray film images and a femoral neck detection model for detecting the femoral neck areas in the X-ray film images.
An embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program, characterized in that the program, when being executed by a processor, implements the method for measuring the cervical shaft angle in a pelvic X-ray film as described above.
Embodiments of the present invention also provide an electronic device, including a processor and a memory, where the memory stores program instructions, and the processor executes the program instructions to implement the method for measuring the cervical shaft angle in a pelvic X-ray image as described above.
As described above, the method, system, apparatus and storage medium for measuring the cervical shaft angle in the pelvic X-ray film according to the present invention have the following advantages:
according to the invention, by detecting the femoral shaft region and the femoral neck region in the X-ray image, the longitudinal shaft of the femoral shaft is extracted from the femoral shaft region, and the short shaft and the long shaft of the femoral neck are extracted from the femoral neck region, the cervical shaft angle can be accurately and efficiently and automatically measured in the pelvis X-ray film, and the problems that misjudgment is easy to occur and time and labor are wasted when the cervical shaft angle in the X-ray film is judged by depending on the subjective observation of medical staff or a hand-drawing method in the prior art are effectively solved.
Drawings
FIG. 1 is a schematic overall flow chart of the method for measuring the cervical shaft angle in the pelvic X-ray film according to the present invention.
FIG. 2 is a diagram showing an example of a pelvic X-ray image in the method for measuring the angle of the cervical spine on a pelvic X-ray according to the present invention.
FIG. 3 is a schematic diagram of the detection model obtained in the method for measuring the cervical shaft angle on the pelvic X-ray film according to the present invention.
Fig. 4 is a diagram showing an example of a femoral shaft image captured in the method for measuring the cervical shaft angle in a pelvic X-ray film according to the present invention.
FIG. 5 is a diagram showing an example of a femoral neck image captured in the method for measuring the angle of the shaft of the neck on a pelvic X-ray according to the present invention.
Fig. 6 is a flowchart of an implementation manner of extracting the longitudinal axis of the femoral shaft in the method for measuring the cervical shaft angle in the pelvic X-ray film according to the present invention.
FIG. 7 is a flowchart of one embodiment of the method for measuring the angle of the shaft of the neck on a pelvic X-ray examination of the present invention to extract the minor axis of the neck of the femur.
FIG. 8 is a schematic flow chart illustrating an implementation of obtaining the cervical shaft angle in the method for measuring the cervical shaft angle on the pelvic X-ray film according to the present invention.
FIG. 9 is a schematic diagram showing an image of the cervical shaft angle obtained in the method for measuring the cervical shaft angle on the pelvic X-ray film according to the present invention.
Fig. 10 is a schematic diagram of the principle structure of the system for measuring the cervical shaft angle in the pelvic X-ray film according to the present invention.
Fig. 11 is a schematic structural diagram of a preferred principle of the system for measuring the cervical shaft angle in the pelvic X-ray film according to the present invention.
Description of the element reference numerals
100 System for measuring cervical shaft angle in pelvis X-ray film
110 image acquisition module
120 region detection module
130-axis extraction module
140 cervical shaft angle acquisition module
150 model training module
S110 to S140
S101 to S103
S131 a-S131 f
S132 a-S132 e
S141 to S146 steps
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The embodiment aims to provide a method, a system, equipment and a storage medium for measuring the cervical shaft angle in a pelvis X-ray film, and is used for solving the problems that misjudgment is easy to occur and time and labor are wasted when the cervical shaft angle in the pelvis X-ray film is judged by means of subjective observation of medical staff or a hand-drawing method in the prior art.
The principle and implementation of the method, system, device and storage medium for measuring the cervical shaft angle in the pelvic X-ray film according to the present invention will be described in detail below, so that those skilled in the art can understand the method, system, device and storage medium for measuring the cervical shaft angle in the pelvic X-ray film without creative work.
First, the technical terms involved in the present embodiment are explained:
femur: the largest long tubular bone in the human body can be divided into two integrated ends; the upper end faces inwards and upwards, the tail end of the upper end is expanded to be spherical, called as the femoral head and is associated with the acetabulum; a small recess, called femoral head recess, is located slightly below the center of the head and is the attachment of the femoral head ligament; the thinner part of the head is called the femoral neck; the long tubular part below the femoral neck is the femoral shaft.
As shown in fig. 1, the present embodiment provides a method for measuring a cervical shaft angle in a pelvic X-ray examination, which includes the following steps:
step S110, acquiring an X-ray image containing pelvis;
step S120, detecting a femoral shaft area and a femoral neck area in the X-ray image;
step S130, extracting a longitudinal axis of the femoral shaft from the femoral shaft region, and extracting a short axis of the femoral neck from the femoral neck region;
step S140, a shaft angle is obtained according to the longitudinal axis of the femoral shaft and the short axis of the femoral neck.
The following describes steps S110 to S140 of the method for measuring the cervical shaft angle on the pelvic X-ray film in this embodiment in detail.
In step S110, an X-ray image including the pelvis is acquired.
The pelvis X-ray image of the detected body collected by image collecting equipment such as a medical X-ray machine, an intelligent camera and the like is obtained. An exemplary view of a pelvic X-ray image is shown in fig. 2.
And step S120, detecting a femoral shaft area and a femoral neck area in the X-ray image.
In this embodiment, a femoral shaft region in the X-ray image is detected by a femoral shaft detection model; and detecting the femoral neck area in the X-ray image through a femoral neck detection model.
Before detecting the femoral shaft area and the femoral neck area in the X-ray image, a femoral shaft detection model and a femoral neck detection model are established. Specifically, in this embodiment, as shown in fig. 3, the method for measuring the cervical shaft angle in the pelvic X-ray film further includes:
step S101, obtaining a plurality of pelvis X-ray film samples;
step S102, marking a femoral shaft area and a femoral neck area in the pelvis X-ray film sample respectively to form a training picture set; for example, the femoral neck and femoral shaft regions in the human pelvis radiographic image are marked with rectangular frames to obtain a training picture set.
Step S103, training a target detection neural network model through the training picture set to obtain the femoral shaft detection model and the femoral neck detection model.
The target detection neural network model includes, but is not limited to, fast-RCNN, YOLO, SSD, etc., for example, the target detection neural network model SSD is used to train the target detection model on the training picture set, so as to obtain the femoral shaft detection model and the femoral neck detection model. Then, detecting a femoral shaft region in the X-ray image through the femoral shaft detection model, inputting a human body pelvis X-ray image to be detected into the femoral shaft detection model, detecting the obtained femoral shaft image as shown in figure 4, detecting a femoral neck region in the X-ray image through the femoral neck detection model, inputting the human body pelvis X-ray image to be detected into the femoral neck detection model, and detecting the obtained femoral neck image as shown in figure 5.
Step S130, extracting a longitudinal axis of the femoral shaft from the femoral shaft region, and extracting a short axis of the femoral neck from the femoral neck region.
Specifically, as shown in fig. 6, in this embodiment, one implementation manner of extracting the longitudinal axis of the femoral shaft from the femoral shaft region includes:
step S131a, intercepting a femoral shaft region image; and intercepting the image of the femoral shaft region from the human pelvis X-ray film through the femoral shaft region in the X-ray film image detected by the femoral shaft detection model.
Step S131b, a femoral shaft edge point is extracted from the femoral shaft region image.
Specifically, a femoral shaft edge point in the image of the femoral shaft region is extracted by using an edge detection or segmentation algorithm.
Step S131c, performing clustering processing on the femoral shaft edge points to obtain two types of femoral shaft edge points with the largest number: a first set of femoral stem points and a second set of femoral shaft points.
The femoral stem edge points may be clustered by using a Clustering algorithm in the prior art, for example, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to cluster the femoral stem edge points, and two types with the largest number of points are reserved: a first set of femoral stem points and a second set of femoral shaft points.
Step S131d, fitting a first straight line according to the first femoral shaft point set, making a perpendicular line from each point in the second femoral shaft point set to the first straight line, and taking a midpoint of each perpendicular line to form a third femoral shaft point set.
Step S131e, a second straight line is fitted according to the second femoral shaft point set, a perpendicular line is drawn from each point in the first femoral shaft point set to the second straight line, and a midpoint of each perpendicular line is taken to form a fourth femoral shaft point set.
Step S131f, a third straight line is fitted according to the third femoral shaft point set and the fourth femoral shaft point set, where the third straight line is a longitudinal axis of the femoral shaft.
Specifically, the third femoral shaft point set and the fourth femoral shaft point set are combined and recorded as a fifth femoral shaft point set, and the fifth femoral shaft point set is used for fitting a straight line to form a third straight line, namely the longitudinal axis of the femoral shaft.
In the present embodiment, as shown in fig. 7, one implementation of extracting the short axis of the femoral neck from the femoral neck region includes:
in step S132a, a femoral neck region image is captured.
And intercepting the image of the femoral neck region from the human pelvis X-ray film through the femoral neck region in the X-ray image detected by the femoral neck detection model.
Step S132b, extracting femoral neck edge points from the femoral shaft region image.
Specifically, femoral neck edge points in the image of the femoral neck region are extracted using an edge detection or segmentation algorithm.
Step S132c, performing clustering processing on the femoral shaft edge points to obtain two types of femoral shaft edge points with the largest number: a first set of femoral neck points and a second set of femoral neck points.
The femoral neck edge points may be clustered by using a Clustering algorithm in the prior art, for example, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to cluster the femoral neck edge points, and two types with the largest number of points are reserved:
step S132d, obtaining a euclidean distance between each point in the first femur neck point set and each point in the second femur neck point set.
Step S132e, acquiring two points with the shortest euclidean distance: the first point and the second point, and the connecting line segment between the first point and the second point is the short axis of the femoral neck.
Step S140, a shaft angle is obtained according to the longitudinal axis of the femoral shaft and the short axis of the femoral neck.
Specifically, as shown in fig. 8, in the present embodiment, one implementation of the method for obtaining the shaft angle according to the longitudinal axis of the femoral shaft and the minor axis of the femoral neck includes:
step S141, making a perpendicular bisector for the short axis of the femoral neck, and obtaining the long axis of the femoral neck; namely, a perpendicular bisector is made through the short axis of the femoral neck, and the obtained straight line is the long axis of the femoral neck. Calculating an obtuse angle between the long axis of the femoral neck and the longitudinal axis of the femoral shaft to obtain a shaft angle, and specifically executing the steps S142 to S146.
Step S142, obtaining an inclination angle A of a long axis of the femoral neck and obtaining an inclination angle B of a longitudinal axis of the femoral shaft;
step S143, acquiring an absolute value of a difference value between the inclination angle A and the inclination angle B, and recording the absolute value as an angle C;
step S144, determining whether the angle C is an obtuse angle, if so, executing step S145: the angle C is the shaft angle, if not, step S146 is executed: and the angle C is an acute angle, so that the angle of the shaft neck is 180-angle C.
As shown in fig. 9, line L3 is the longitudinal axis of the femoral shaft, line L2 is the minor axis of the femoral neck, line L1 is the major axis of the femoral neck, and the obtuse angle enclosed by line L1 and line L3 is the angle of the cervical shaft.
Therefore, the method for measuring the cervical shaft angle in the pelvis X-ray film of the embodiment can accurately and efficiently automatically measure the cervical shaft angle in the pelvis X-ray film.
In addition, as shown in fig. 10, the present embodiment further provides a system 100 for measuring the cervical shaft angle in a pelvic X-ray film, wherein the system 100 for measuring the cervical shaft angle in the pelvic X-ray film comprises: an image acquisition module 110, a region detection module 120, an axis extraction module 130, and a shaft angle acquisition module 140.
In the present embodiment, the image acquiring module 110 is used for acquiring an X-ray image including a pelvis.
The image acquisition module 110 acquires a pelvis X-ray image of the subject acquired by image acquisition equipment such as a medical X-ray machine and an intelligent camera. An exemplary view of a pelvic X-ray image is shown in fig. 2.
In this embodiment, the area detection module 120 is configured to detect a femoral shaft area and a femoral neck area in the X-ray image.
Before detecting the femoral shaft area and the femoral neck area in the X-ray image, a femoral shaft detection model and a femoral neck detection model are established. Therefore, as shown in fig. 11, in the present embodiment, the system 100 for measuring the cervical shaft angle in the pelvic X-ray film further includes: the model training module 150 is configured to obtain a plurality of pelvis X-ray film samples, label femoral shaft regions and femoral neck regions in the pelvis X-ray film samples respectively to form a training picture set, train a target detection neural network model through the training picture set, and obtain a femoral shaft detection model for detecting the femoral shaft regions in the X-ray film image and a femoral neck detection model for detecting the femoral neck regions in the X-ray film image.
The target detection neural network model includes, but is not limited to, fast-RCNN, YOLO, SSD, etc., for example, the target detection neural network model SSD is used to train the target detection model on the training picture set, so as to obtain the femoral shaft detection model and the femoral neck detection model. Then, detecting a femoral shaft region in the X-ray image through the femoral shaft detection model, inputting a human body pelvis X-ray image to be detected into the femoral shaft detection model, detecting the obtained femoral shaft image as shown in figure 4, detecting a femoral neck region in the X-ray image through the femoral neck detection model, inputting the human body pelvis X-ray image to be detected into the femoral neck detection model, and detecting the obtained femoral neck image as shown in figure 5.
In this embodiment, the axis extraction module 130 is configured to extract a longitudinal axis of the femoral shaft from the femoral shaft region and extract a short axis of the femoral neck from the femoral neck region.
Specifically, the axis extraction module 130 includes a femoral shaft longitudinal axis extraction unit, and one implementation manner of the femoral shaft longitudinal axis extraction unit extracting a longitudinal axis of a femoral shaft includes:
and intercepting a femoral shaft region image, intercepting the image of the femoral shaft region from a human body pelvis X-ray film through the femoral shaft region in the X-ray film image detected by a femoral shaft detection model, and then extracting a femoral shaft edge point from the femoral shaft region image.
Specifically, a femoral shaft edge point in the image of the femoral shaft region is extracted by using an edge detection or segmentation algorithm.
Clustering the backbone edge points to obtain two types of backbone edge points with the largest quantity: a first set of femoral stem points and a second set of femoral shaft points.
The femoral stem edge points may be clustered by using a Clustering algorithm in the prior art, for example, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to cluster the femoral stem edge points, and two types with the largest number of points are reserved: a first set of femoral stem points and a second set of femoral shaft points.
Fitting a first straight line according to the first femoral shaft point set, making a vertical line for each point in the second femoral shaft point set to the first straight line, and taking a midpoint of each vertical line to form a third femoral shaft point set.
And fitting a second straight line according to the second femoral shaft point set, making a vertical line for each point in the first femoral shaft point set to the second straight line, and taking a midpoint of each vertical line to form a fourth femoral shaft point set.
And fitting a third straight line according to the third femoral shaft point set and the fourth femoral shaft point set, wherein the third straight line is the longitudinal axis of the femoral shaft.
Specifically, the third femoral shaft point set and the fourth femoral shaft point set are combined and recorded as a fifth femoral shaft point set, and the fifth femoral shaft point set is used for fitting a straight line to form a third straight line, namely the longitudinal axis of the femoral shaft.
Specifically, the shaft extraction module 130 includes a femoral neck short axis extraction unit, and one implementation of the femoral neck short axis extraction unit to extract the short axis of the femoral neck includes:
and (5) intercepting an image of the femoral neck region. And intercepting the image of the femoral neck region from the human pelvis X-ray film through the femoral neck region in the X-ray film image detected by the femoral neck detection model, and extracting the femoral neck edge point from the image of the femoral stem region.
Specifically, femoral neck edge points in the image of the femoral neck region are extracted using an edge detection or segmentation algorithm.
Clustering the backbone edge points to obtain two types of backbone edge points with the largest quantity: a first set of femoral neck points and a second set of femoral neck points.
The femoral neck edge points may be clustered by using a Clustering algorithm in the prior art, for example, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to cluster the femoral neck edge points, and two types with the largest number of points are reserved:
and acquiring the Euclidean distance from each point in the first femur neck point set to each point in the second femur neck point set. Acquiring two points with the shortest Euclidean distance: the first point and the second point, and the connecting line segment between the first point and the second point is the short axis of the femoral neck.
In this embodiment, the shaft angle acquisition module 140 is configured to acquire a shaft angle according to a longitudinal axis of the femoral shaft and a short axis of the femoral neck.
One implementation of the shaft angle obtaining module 140 for obtaining the shaft angle includes:
making a perpendicular bisector for the short axis of the femoral neck, and obtaining the long axis of the femoral neck; namely, a perpendicular bisector is made through the short axis of the femoral neck, and the obtained straight line is the long axis of the femoral neck. And calculating an obtuse angle between the long axis of the femoral neck and the longitudinal axis of the femoral shaft to obtain the angle of the shaft of the neck. The method comprises the following specific steps:
acquiring an inclination angle A of a long axis of the femoral neck and an inclination angle B of a longitudinal axis of the femoral shaft;
acquiring the absolute value of the difference value of the inclination angle A and the inclination angle B, and recording the absolute value as an angle C;
and judging whether the angle C is an obtuse angle, if so, determining that the angle C is the neck angle, and if not, determining that the angle C is an acute angle, wherein the neck angle is 180-C.
As shown in fig. 9, line L3 is the longitudinal axis of the femoral shaft, line L2 is the minor axis of the femoral neck, line L1 is the major axis of the femoral neck, and the obtuse angle enclosed by line L1 and line L3 is the angle of the cervical shaft.
Embodiments of the present invention also provide a computer-readable storage medium, such as a memory configured to store various types of data to support operations at a device. Examples of such data include instructions, messages, pictures, etc. for any application or method operating on the electronic device. The memory may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), high speed random access memory (high speed ram), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic memory, flash memory, magnetic or optical disks, or the like. The memory stores program instructions that, when executed, implement the method of measuring the shaft angle in a pelvic X-ray. The method for measuring the cervical shaft angle in the pelvis X-ray film has been described in detail above, and is not repeated herein.
Embodiments of the present invention also provide an electronic device, such as but not limited to a medical examination device, an image processing device, etc., including a processor and a memory, the memory storing program instructions, the processor executing the program instructions to implement the method for measuring the cervical shaft angle in a pelvic X-ray film as described above.
In an actual implementation manner, the electronic device is, for example, an electronic device installed with an Android operating system or an iOS operating system, or an operating system such as Palm OS, Symbian, Black Berry OS, or Windows Phone.
In an exemplary embodiment, the electronic device may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors, cameras, or other electronic components for performing the above-described method of measuring the shaft angle in the pelvic X-ray film.
In conclusion, the invention extracts the longitudinal axis of the femoral shaft from the femoral shaft region and extracts the short axis and the long axis of the femoral neck from the femoral neck region by detecting the femoral shaft region and the femoral neck region in the X-ray image, accurately and efficiently and automatically measures the cervical shaft angle in the pelvis X-ray film, and effectively solves the problems that misjudgment is easy to occur and time and labor are wasted when the cervical shaft angle in the X-ray film is judged by depending on the subjective observation of medical staff or a hand-drawing method in the prior art. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (8)
1. A method of measuring a shaft angle in a pelvic X-ray examination, the method comprising:
acquiring an X-ray image containing a pelvis;
detecting a femoral shaft area and a femoral neck area in the X-ray image;
extracting a longitudinal axis of a femoral shaft from the femoral shaft region and a minor axis of a femoral neck from the femoral neck region;
acquiring a shaft angle according to a longitudinal axis of the femoral shaft and a minor axis of the femoral neck;
one implementation of extracting a minor axis of a femoral neck from the femoral neck region includes:
intercepting an image of a femoral neck region;
extracting femoral neck edge points from the femoral neck region image;
clustering the femoral neck edge points to obtain two types of femoral neck edge points with the largest quantity: a first set of femoral neck points and a second set of femoral neck points;
acquiring Euclidean distance between each point in the first femur neck point set and each point in the second femur neck point set;
acquiring two points with the shortest Euclidean distance: a first point and a second point, wherein a connecting line section between the first point and the second point is a short axis of the femoral neck;
one implementation of the method for obtaining a shaft angle from a longitudinal axis of the femoral shaft and a minor axis of the femoral neck includes:
making a perpendicular bisector for the short axis of the femoral neck, and obtaining the long axis of the femoral neck;
acquiring an inclination angle A of a long axis of the femoral neck and an inclination angle B of a longitudinal axis of the femoral shaft;
acquiring the absolute value of the difference value of the inclination angle A and the inclination angle B, and recording the absolute value as an angle C;
if the angle C is an obtuse angle, the angle C is the neck angle, and if the angle C is an acute angle, the neck angle is 180-angle C.
2. The method of claim 1, wherein the femoral shaft region in the radiographic image is detected by a femoral shaft detection model; and detecting the femoral neck area in the X-ray image through a femoral neck detection model.
3. The method of measuring the cervical shaft angle on a pelvic X-ray examination as claimed in claim 2, further comprising:
obtaining a plurality of pelvis X-ray film samples;
marking a femoral shaft area and a femoral neck area in the pelvis X-ray film sample respectively to form a training picture set;
and training a target detection neural network model through the training picture set to obtain the femoral shaft detection model and the femoral neck detection model.
4. The method of claim 1, wherein one implementation of the extraction of the longitudinal axis of the femoral shaft from the femoral shaft region comprises:
intercepting a femoral shaft region image;
extracting a femoral shaft edge point from the femoral shaft region image;
clustering the backbone edge points to obtain two types of backbone edge points with the largest quantity: a first diaphysis point set and a second diaphysis point set;
fitting a first straight line according to the first femoral shaft point set, making a vertical line for each point in the second femoral shaft point set to the first straight line respectively, and taking a midpoint of each vertical line to form a third femoral shaft point set;
fitting a second straight line according to the second femoral shaft point set, making a vertical line for each point in the first femoral shaft point set to the second straight line, and taking a midpoint of each vertical line to form a fourth femoral shaft point set;
and fitting a third straight line according to the third femoral shaft point set and the fourth femoral shaft point set, wherein the third straight line is the longitudinal axis of the femoral shaft.
5. A system for measuring the shaft angle on a pelvic X-ray, the system comprising:
the image acquisition module is used for acquiring an X-ray image containing the pelvis;
the area detection module is used for detecting a femoral shaft area and a femoral neck area in the X-ray image;
an axis extraction module for extracting a longitudinal axis of the femoral shaft from the femoral shaft region and extracting a short axis of the femoral neck from the femoral neck region;
one implementation of extracting a minor axis of a femoral neck from the femoral neck region includes:
intercepting an image of a femoral neck region;
extracting femoral neck edge points from the femoral neck region image;
clustering the femoral neck edge points to obtain two types of femoral neck edge points with the largest quantity: a first set of femoral neck points and a second set of femoral neck points;
acquiring Euclidean distance between each point in the first femur neck point set and each point in the second femur neck point set;
acquiring two points with the shortest Euclidean distance: a first point and a second point, wherein a connecting line section between the first point and the second point is a short axis of the femoral neck;
the neck shaft angle acquisition module is used for acquiring a neck shaft angle according to a longitudinal axis of the femoral shaft and a short axis of the femoral neck;
one implementation way for the shaft angle acquisition module to acquire the shaft angle comprises:
making a perpendicular bisector for the short axis of the femoral neck, and obtaining the long axis of the femoral neck; namely, a perpendicular bisector is made through the short axis of the femoral neck, and the obtained straight line is the long axis of the femoral neck;
acquiring an inclination angle A of a long axis of the femoral neck and an inclination angle B of a longitudinal axis of the femoral shaft;
acquiring the absolute value of the difference value of the inclination angle A and the inclination angle B, and recording the absolute value as an angle C;
and judging whether the angle C is an obtuse angle, if so, determining that the angle C is the neck angle, and if not, determining that the angle C is an acute angle, wherein the neck angle is 180-C.
6. The system for measuring the shaft angle on a pelvic X-ray examination as claimed in claim 5, further comprising:
the model training module is used for acquiring a plurality of pelvis X-ray film samples, labeling femoral shaft areas and femoral neck areas in the pelvis X-ray film samples respectively to form a training picture set, training a target detection neural network model through the training picture set, and acquiring a femoral shaft detection model for detecting the femoral shaft areas in the X-ray film images and a femoral neck detection model for detecting the femoral neck areas in the X-ray film images.
7. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of measuring the angle of the nape in a pelvic X-ray image as set forth in any one of claims 1 to 4.
8. An electronic device comprising a processor and a memory, the memory storing program instructions, the processor executing the program instructions to implement the method of measuring the angle of the cervical spine on a pelvic X-ray as claimed in any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810992671.9A CN109242837B (en) | 2018-08-29 | 2018-08-29 | Method, system, apparatus and storage medium for measuring cervical shaft angle in pelvic X-ray film |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810992671.9A CN109242837B (en) | 2018-08-29 | 2018-08-29 | Method, system, apparatus and storage medium for measuring cervical shaft angle in pelvic X-ray film |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109242837A CN109242837A (en) | 2019-01-18 |
| CN109242837B true CN109242837B (en) | 2021-09-14 |
Family
ID=65068677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810992671.9A Active CN109242837B (en) | 2018-08-29 | 2018-08-29 | Method, system, apparatus and storage medium for measuring cervical shaft angle in pelvic X-ray film |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242837B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110111323B (en) * | 2019-05-13 | 2021-08-10 | 上海交通大学医学院附属上海儿童医学中心 | Hip joint detection method and device |
| CN110634133A (en) * | 2019-09-04 | 2019-12-31 | 杭州健培科技有限公司 | Knee joint orthopedic measurement method and device based on X-ray plain film |
| CN112700427B (en) * | 2021-01-07 | 2024-04-16 | 哈尔滨晓芯科技有限公司 | Automatic evaluation method for hip joint X-ray |
| CN113870229B (en) * | 2021-09-29 | 2022-03-11 | 北京长木谷医疗科技有限公司 | Method, device, equipment and storage medium for processing image data of proximal femoral medullary cavity |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107545578A (en) * | 2017-08-25 | 2018-01-05 | 沈阳东软医疗***有限公司 | Femoral head region segmentation method, device and equipment in CT images |
| CN108309334A (en) * | 2017-12-08 | 2018-07-24 | 李书纲 | A kind of data processing method of spine X-ray image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070056050A1 (en) * | 2005-06-29 | 2007-03-08 | Clokie Cameron M L | PRODUCTION OF BONE MORPHOGENIC PROTEINS (BMPs) IN TRANSGENIC MAMMALS |
-
2018
- 2018-08-29 CN CN201810992671.9A patent/CN109242837B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107545578A (en) * | 2017-08-25 | 2018-01-05 | 沈阳东软医疗***有限公司 | Femoral head region segmentation method, device and equipment in CT images |
| CN108309334A (en) * | 2017-12-08 | 2018-07-24 | 李书纲 | A kind of data processing method of spine X-ray image |
Non-Patent Citations (1)
| Title |
|---|
| 全髋关节置换术治疗成人先天性髋关节发育不良的临床研究;李鹏;《中国优秀硕士学位论文全文数据库医药卫生科技楫》;中国学术期刊（光盘版）电子杂志社;20120415(第04期);E066-397 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109242837A (en) | 2019-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109242837B (en) | Method, system, apparatus and storage medium for measuring cervical shaft angle in pelvic X-ray film | |
| CN108520519B (en) | Image processing method and device and computer readable storage medium | |
| CN109754387B (en) | Intelligent detection and positioning method for whole-body bone imaging radioactive concentration focus | |
| CN108133476B (en) | Method and system for automatically detecting pulmonary nodules | |
| CN107045721B (en) | Method and device for extracting pulmonary blood vessels from chest CT (computed tomography) image | |
| CN105701799B (en) | Divide pulmonary vascular method and apparatus from lung's mask image | |
| CN111080573B (en) | Rib image detection method, computer device and storage medium | |
| CN109242838A (en) | Measure method, system, equipment and the medium at center edge angle in pelvis X-ray | |
| CN110929728B (en) | Image region-of-interest dividing method, image segmentation method and device | |
| CN105930852B (en) | A kind of bubble image-recognizing method | |
| CN107146214A (en) | The method that children's hip development condition computer is diagnosed automatically | |
| CN112037200A (en) | Method for automatically identifying anatomical features and reconstructing model in medical image | |
| CN111652301B (en) | Femoral lesser trochanter identification method and device based on deep learning and electronic equipment | |
| CN111798976A (en) | DDH artificial intelligence auxiliary diagnosis method and device | |
| CN102132320A (en) | Method and device for image processing, particularly for medical image processing | |
| CN107832838A (en) | The method and apparatus for evaluating cell smear sample satisfaction | |
| Bano et al. | AutoFB: Automating fetal biometry estimation from standard ultrasound planes | |
| WO2023071114A1 (en) | Artificial intelligence-based stone image recognition method and apparatus, and device | |
| CN110580948A (en) | Medical image display method and display equipment | |
| CN105956386A (en) | Health indicator index classification system and method based on chest radiography of healthy people | |
| CN110738702B (en) | Three-dimensional ultrasonic image processing method, device, equipment and storage medium | |
| Lenga et al. | Deep learning based rib centerline extraction and labeling | |
| CN112785591B (en) | Method and device for detecting and segmenting rib fracture in CT image | |
| CN113012127A (en) | Cardiothoracic ratio measuring method based on chest medical image | |
| CN115661728B (en) | Virus sampling in-place judgment method based on image recognition and virus sampling system |
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 |