CN114943688A - Method for extracting interest region in mammary gland image based on palpation and ultrasonic data - Google Patents
Method for extracting interest region in mammary gland image based on palpation and ultrasonic data Download PDFInfo
- Publication number
- CN114943688A CN114943688A CN202210449593.4A CN202210449593A CN114943688A CN 114943688 A CN114943688 A CN 114943688A CN 202210449593 A CN202210449593 A CN 202210449593A CN 114943688 A CN114943688 A CN 114943688A
- Authority
- CN
- China
- Prior art keywords
- breast
- focus
- ultrasonic
- section
- imaging system
- 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.)
- Pending
Links
- 238000002559 palpation Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 37
- 210000005075 mammary gland Anatomy 0.000 title abstract description 12
- 210000000481 breast Anatomy 0.000 claims abstract description 134
- 238000003384 imaging method Methods 0.000 claims abstract description 58
- 230000003902 lesion Effects 0.000 claims description 40
- 239000000523 sample Substances 0.000 claims description 34
- 238000002091 elastography Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000012285 ultrasound imaging Methods 0.000 claims description 7
- 239000007787 solid Substances 0.000 claims description 5
- 210000000056 organ Anatomy 0.000 claims description 4
- 239000002775 capsule Substances 0.000 claims description 3
- 210000000062 pectoralis major Anatomy 0.000 claims description 3
- 238000010586 diagram Methods 0.000 abstract description 9
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 5
- 210000001519 tissue Anatomy 0.000 description 36
- 238000002604 ultrasonography Methods 0.000 description 8
- 206010006187 Breast cancer Diseases 0.000 description 6
- 208000026310 Breast neoplasm Diseases 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 206010028980 Neoplasm Diseases 0.000 description 3
- 208000030270 breast disease Diseases 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 210000004872 soft tissue Anatomy 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000004907 gland Anatomy 0.000 description 1
- 210000002216 heart Anatomy 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
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
-
- 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
- A61B8/0825—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the breast, e.g. mammography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06T7/40—Analysis of texture
-
- 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
- G06T2207/10132—Ultrasound 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30068—Mammography; Breast
-
- 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
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention provides a method for extracting an interested region in a mammary gland image based on palpation and ultrasonic data, belongs to the field of medical image processing, and particularly relates to a method for three-dimensional imaging of a focus in a breast and quickly extracting the interested region, which comprises the following steps: the stress distribution diagram of the mammary gland is acquired by using a palpation imaging system, the hardness distribution of the focus on the coronal plane and the setting of the region of interest are rapidly obtained, the setting efficiency of the region of interest of an ultrasonic imaging system is assisted, the three-dimensional image of the focus in the breast is reconstructed, and the three-dimensional hardness distribution in the focus in the breast is constructed. The method is used for extracting the outline of the focus region of interest of the focus in the breast and calculating to obtain the focus characteristic value, thereby completing the detection of the ellipsoidal focus.
Description
Technical Field
The invention relates to a method for extracting an interested region in a mammary gland image based on palpation and ultrasonic data, belongs to the field of medical image processing, and particularly relates to a method for three-dimensional imaging of a focus in a breast and quickly extracting the interested region.
Background
In recent years, the mortality rate caused by breast cancer is gradually increased, the main reason is that the time for discovering breast cancer is too late, early diagnosis and treatment are important measures for improving the survival rate of breast cancer patients, reducing the mortality rate and reducing medical expenses, and regular breast examination is the best choice for discovering breast cancer at early stage. The patient is usually detected internationally by adopting the modes of clinical breast palpation, palpation imaging, ultrasound, breast X-ray, nuclear magnetic resonance and the like, and various examination technologies disclose the characteristics of breast diseases from different angles by using different principles, so that the same breast examination and diagnosis problem is solved. There are thousands of years of clinical palpation that have been applied to history, and the accuracy of identifying the properties of breast lesions by using the principle of elastic difference of stress-type tissues is very high, as shown in the results of in vitro studies on breast diseases: the tissue elasticity (colloquially understood as stiffness) of various benign and malignant breast lesions varies widely, with very few overlapping portions of the same stiffness. Simulating bionic breast palpation imaging examination (BBE) of doctor Clinical Breast Examination (CBE), after being pressed on breast soft tissue by external force, identifying the tissue elasticity difference between normal tissue and focus, acquiring the stress distribution data of the coronal plane of the breast, analyzing the stress distribution data into a two-dimensional sequence image, and calculating and outputting parameters such as hardness, size, shape and the like of the focus in the breast. Various inspection techniques have advantages and disadvantages, and can complement each other, such as poor capability of detecting cystic lesions by palpation imaging and strong capability of detecting cystic lesions by ultrasound, so that the inspection techniques are often combined to improve the accuracy. If 2022 years 'national Weijian Commission of Breast cancer screening working plan' is taken as an application guide, the optimization effect of the combined application of palpation imaging and ultrasonic imaging in a preliminary screening mechanism is as follows: the sensitivity of detecting breast solid tumors by palpation imaging is very high, missed diagnosis is not easy, and the specificity of identifying cystic lesions by ultrasonic detection is very high, so misdiagnosis is not easy. And the palpation and the ultrasound are sequentially checked by one person, so that the efficiency and the accuracy can be greatly improved.
The ultrasonic examination accurately sets a region of interest (ROI) to determine a region of key analysis, and can avoid the delay and high complexity of data processing when the whole field of view (FOV) is subjected to quantitative analysis. However, accurate setting of the ROI is a challenge for the sonographer and is also an important cause of poor quality of images for diagnosis and difficulty in reproduction of examination results. According to the traditional breast ultrasound examination, after a doctor manually searches for representative sections in 2D images of a plurality of sections, a region of interest (ROI) and the center position and the edge of a focus are determined on each representative section, further analysis is carried out in a map locking mode, and the ROI of a three-dimensional image of the focus is constructed in the brain of the doctor, so that the time consumption of an ultrasound examination process is long, a learning curve is long, an examination result excessively depends on the experience of the doctor, and more artificial interference factors exist. In addition, ultrasound imaging has difficulty setting a coronal plane ROI parallel to the breast skin due to the restriction of the probe movement space.
Although the palpation stress type tissue elasticity is consistent with the basic principle of tissue elasticity used for ultrasonic strain type tissue elasticity imaging, the palpation stress type tissue elasticity imaging utilizes the stress distribution diagram of a coronal plane formed by the difference between a focus and surrounding normal tissues, can simply display the contour of the focus and the stress distribution in the contour in real time, and further obtains data such as relative hardness, size, shape, activity degree, internal homogeneity and the like of the focus. If the breast tumor is accurately positioned by using palpation imaging, and then the multiple image segmentation of ultrasonic imaging is carried out, the hardness distribution of the focus on the coronal plane and the region of interest can be rapidly obtained. Therefore, the three-dimensional image of the focus in the breast can be quickly reconstructed by combining palpation imaging and ultrasonic imaging, and the focus characteristic value is calculated, so that the focus detection of the focus ellipsoid is completed.
In order to overcome the defects that a patient cannot rapidly determine an interested region and cannot rapidly reconstruct a three-dimensional image of a focus in a breast when ultrasonic imaging is adopted, research and development personnel are urgently needed to develop a method for extracting the interested region in a mammary gland image based on palpation and ultrasonic data.
Disclosure of Invention
Technical problem to be solved
The invention aims to provide a method for extracting an interested region in a mammary gland image based on palpation and ultrasonic data, which is mainly used for carrying out three-dimensional stereo imaging on a focus in a breast of a patient and quickly extracting the interested region.
(II) technical scheme
In order to solve the technical problem, the invention provides a method for extracting an interested region in a breast image based on palpation and ultrasonic data, which comprises the following specific steps:
s01, acquiring the position of the lesion in the breast by using a palpation stress type tissue elastography system, and analyzing the data of the lesion in the breast into a two-dimensional sequence image of a coronal plane;
s02, setting a circumscribed rectangle according to the minimum area of the outline of the focus in the coronal plane image, and setting the circumscribed rectangle with the minimum area as an ROI (region of interest);
s03, setting a diagonal line segment a according to the circumscribed rectangle of the coronal plane, acquiring data of the lesion in the breast in the ROI along the diagonal line segment a by using an ultrasonic imaging system, analyzing the data into a two-dimensional sequence image of a first section of the breast, and extracting the edge and texture information of the breast lesion in the first section of the breast to describe the feature of the lesion region;
s04, rotating in the direction of a certain angle between the ultrasonic imaging system and the diagonal line segment a, collecting data of the focus in the breast in the ROI, analyzing the data into a two-dimensional sequence image of a second section of the breast, and extracting the edge and texture information of the breast focus in the second section of the breast to describe the characteristics of the focus area;
and S05, determining the final three-dimensional position and characteristics of the breast lesion according to the continuous stress distribution data collected in the coronal plane and the characteristics of the lesion region extracted from the first section and the second section of the breast.
Preferably, the step S04 specifically includes: the ultrasonic imaging system rotates 45 degrees with the diagonal line segment a every time, an ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of the breast skin, the long axis of the ultrasonic linear array probe rotates 45 degrees, 90 degrees and 135 degrees clockwise in sequence by taking the central point of the diagonal line segment a of the external connection rectangle of the coronal plane as a central axis, ultrasonic images of all sections of the breast are recorded, and the edge and texture information of the focus in the breast in the sections are extracted to describe the characteristics of the focus area.
Preferably, the step S04 specifically includes: the ultrasonic imaging system rotates 90 degrees with the diagonal line segment a at each time, an ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of the breast skin, the long axis of the ultrasonic linear array probe rotates 90 degrees clockwise by taking the central point of the diagonal line segment a of the external connection rectangle of the coronal plane as a central axis, the ultrasonic image of the breast section is recorded, and the edge and texture information of the focus in the breast section are extracted to describe the characteristics of the focus area.
Preferably, an angle meter is arranged inside the ultrasonic linear array probe of the ultrasonic imaging system, and the angle meter controls the angle of the ultrasonic linear array probe when the ultrasonic linear array probe rotates along the diagonal line segment a.
Preferably, the first section of the breast is analyzed, a first boundary line is arranged at the position with the maximum gray difference between the focus and the surrounding tissues, the second section of the breast is analyzed, a second boundary line is arranged at the position with the maximum gray difference between the focus and the surrounding tissues, a circumscribed rectangle of the focus in the coronal image is connected with the first boundary line and the second boundary line, a minimum volume circumscribed rectangle of the three-dimensional ellipsoid focus is constructed, and the minimum volume circumscribed rectangle is set as the region of interest ROI of the three-dimensional sequence image.
Preferably, the ultrasound imaging system resolves the capsule/solid nature inside a three-dimensional solid rectangle of the lesion within the breast.
Preferably, under the condition of ultrasonic fixed gain, a rectangular frame formed by extending the first boundary line and the second boundary line respectively by no less than 10mm is set as a view field FOV for ultrasonic tissue elastography analysis, and each section view field FOV is required to contain fat tissue, fibroglandular organ and pectoralis major muscle.
Preferably, the center point of the diagonal segment a of the circum-rectangle of the coronal plane in step S03 is set, and the continuous stress data recorded on the coronal plane is analyzed and calculated by a contour analysis method such as a stress distribution map, so as to output the property indexes of hardness, size, shape, surface smoothness and internal homogeneity of the lesion in the breast.
Preferably, the continuous stress distribution data of the coronal plane is fused with the elastic data of the ultrasonic tissues of the first section of the breast and the second section of the breast to construct the overall hardness distribution of the lesion so as to obtain the overall heterogeneity of the lesion.
Preferably, an ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of breast skin, a long axis of the ultrasonic linear array probe is displaced in the parallel direction of a diagonal line segment a of a coronal plane external rectangle, the interval distance of the central points of all the line segments is not more than 10mm, each section image of ultrasonic is recorded, and the edge and texture information of a focus in a breast in each section is extracted to describe the characteristics of a focus area.
(III) advantageous effects
The invention provides a method for extracting an interest region in a mammary gland image based on palpation and ultrasonic data, which comprises the steps of firstly, utilizing a palpation stress type tissue elastography system to quickly and vividly display a focus in soft tissue on a plane (namely a coronal plane) parallel to an X axis, setting a minimum area of a focus outline as an external rectangle, and setting a diagonal line segment a in the external rectangle; secondly, vertically collecting data of the breast internal focus position along a diagonal line segment a by using an ultrasonic strain type tissue elasticity imaging system, analyzing the data into a first breast section, rotating the breast internal focus position along the direction of a certain angle between the ultrasonic imaging system and the diagonal line segment a, vertically collecting the data of the breast internal focus position along the rotated line segment, analyzing the data into a second breast section, and determining the final three-dimensional position and the characteristics of the breast internal focus position according to continuous stress distribution data collected in the coronal plane and the characteristics of the focus region extracted by combining the first breast section and the second breast section. The palpation stress type tissue elastography and the ultrasonic strain type tissue elastography are combined, the advantages of the palpation stress type tissue elastography and the ultrasonic strain type tissue elastography are complementary, the region of interest can be extracted quickly, more data for diagnosis can be obtained, and the accuracy rate of auxiliary diagnosis is higher. The real-time stress distribution diagram output by the palpation stress type tissue elastography system has great effect on the elastography of the deformed tissue, and the stress of the ROI of the lesion area and the ROI of the reference area is ensured to be consistent.
The invention can efficiently determine the region of interest of the focus and can quickly reconstruct the three-dimensional image of the focus. The two tissue elastography images are superposed and fused, an enhanced tissue elastography algorithm can be constructed, and the three-dimensional imaging of the lesion in the true sense is realized.
Drawings
FIG. 1: according to the method for extracting the interest region in the breast image based on the palpation and ultrasonic data, the palpation stress type tissue elastography system acquires the schematic diagram of the image data of the coronal plane of the focus in the breast;
FIG. 2: the schematic diagram of a circumscribed rectangle and a diagonal line segment a is arranged in the palpation coronal plane image;
FIG. 3: the invention is based on palpation and ultrasonic data to the extraction method of the interest area in the mammary gland image in the ultrasonic strain type tissue elastography system to the focus gathers the schematic diagram of the section image data in the breast;
FIG. 4: in the invention, the coronal plane (the figure is a human body lying on the back and collected from top to bottom) and a first tangent line of a breast are schematically shown;
FIG. 5: the invention is based on palpation and ultrasonic data to the extraction method of the interest area in the mammary gland image the ultrasonic imaging system gathers the schematic diagram of the first tangent plane of the breast;
FIG. 6: the invention is based on palpation and ultrasonic data to the extraction method of the interest area in the mammary gland image the ultrasonic imaging system gathers the schematic diagram of the second section of the breast;
FIG. 7 is a schematic view of: the invention is based on palpation and ultrasonic data to the extraction method of the interest area in the mammary gland image the ultrasonic imaging system gathers the schematic diagram of each section of breast;
in the figure: 1. a palpation probe; 2. a breast; 21. a focus of disease; 22. a coronal plane; 23. a circumscribed rectangle; 24. a diagonal segment a; 241. a first section of the breast; 241a, a first dividing line; 242. a second section of the breast; 242a, a second dividing line; 25. a center point; 26. a 45 degree line segment; 27. a 90 degree line segment; 28. an ultrasound field of view FOV; 3. an ultrasound probe.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
In describing the present invention, it is to be noted that, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used herein do not denote any order, quantity, or importance, but rather are used to distinguish one image from another. Also, "a" or "an" does not denote a limitation of quantity, but rather denotes that there is one of the associated item.
Example (b):
as shown in fig. 1 and fig. 3, the invention provides a method for extracting a region of interest in a breast image based on palpation and ultrasound data, which comprises the following specific steps:
s01, acquiring the focus (21) position of a breast (2) by using a palpation stress type tissue elasticity imaging system, wherein the palpation stress type tissue elasticity imaging system is a breast palpation diagnostic instrument, and biomimetically simulates the principle of tactile perception of different tissue differences, applying external force to touch and press the breast of a human body, acquiring different responses generated by normal tissues and tumor tissues, analyzing the data at the focus (21) position of the breast (2) into two-dimensional sequence images of a coronal plane (22), wherein the two-dimensional sequence images of the coronal plane (22) can be acquired from top to bottom in the supine position of the human body or from bottom to top in the prone position of the human body, the format of the two-dimensional sequence images is DICOM, performing contour analysis on the two-dimensional sequence images of the coronal plane (22), analyzing and calculating recorded continuous stress data, and perceiving various character indexes of the tumor, such as hardness, size, shape, mobility, surface smoothness, internal homogeneity, etc.
Step S02, a circumscribed rectangle (23) is set according to the minimum area of the contour of the breast (2) focus (21) in the coronal plane (22) image, the circumscribed rectangle (23) with the minimum area is set as the region of interest ROI, fig. 1 shows the coronal plane (22) in order to clearly show the coronal plane (22), the coronal plane (22) adopts parallel displacement, and the approximate contour of the breast (2) focus (21) can be seen in the coronal plane (22) image. The approximate position of the focus (21) is found by using the palpation imaging system, and the ROI is set, so that the examination time of a large amount of ultrasonic imaging systems can be saved, and the technical problem of low ultrasonic breast examination efficiency under the actual condition is solved.
Step S03, as shown in fig. 2 and fig. 5, setting a diagonal line segment a (24) according to the circumscribed rectangle (23) of the coronal plane (22), acquiring data at the lesion (21) of the breast (2) inside the region of interest ROI along the diagonal line segment a (24) by using an ultrasound imaging system, analyzing the data into a two-dimensional sequence image of a first breast section (241), and extracting edge and texture information of the lesion (21) of the breast (2) in the first breast section (241) to describe the feature of the lesion (21) region. The ultrasonic imaging system is specifically a three-dimensional image ultrasonic instrument, an ultrasonic probe (3) is perpendicular to the breast (2), a linear sensor of the ultrasonic probe (3) is overlapped with a diagonal line segment a (24) for detection, and a first tangent plane (241) of the breast is obtained. Ultrasound imaging systems have different technical advantages than palpation imaging systems, and can obtain more characteristics of the lesion (21), helping to analyze the condition of the lesion (21).
Step S04, as shown in fig. 6, the ultrasound imaging system is rotated in a direction forming a certain angle with the diagonal line segment a (24), data at the lesion (21) of the breast (2) is collected inside the region of interest ROI, and is analyzed into a two-dimensional sequence image of the second section (242) of the breast, and the edge and texture information of the lesion (21) of the breast (2) in the second section (242) of the breast are extracted to describe the feature of the lesion (21) region. Specifically, on the basis of the first breast section (241), the center point of the diagonal line segment a (24) is used as an axis, the ultrasonic probe (3) of the ultrasonic imaging system is rotated, so that the linear sensor of the ultrasonic probe (3) and the diagonal line segment a (24) form a fixed angle, for example: data at the lesion (21) of the breast (2) are acquired within the region of interest ROI at 45 degrees, 90 degrees and resolved into a two-dimensional sequence of images of a second slice (242) of the breast.
Step S05, as shown in fig. 4, determines the final three-dimensional position and feature of the lesion (21) in the breast (2) according to the continuous stress distribution data collected in the coronal plane (22) and by combining the features of the lesion (21) region extracted from the first section (241) of the breast gland and the second section (242) of the breast.
The contour of a human breast is generally close to an ellipse, so an ellipse representing the breast is found by hough transform on the image of the coronal plane (22), as shown in fig. 4. In the following processing, the ultrasound imaging system only needs to consider processing the region of interest ROI determined by the palpation imaging system, i.e.: the external rectangle (23) can reduce the operation amount, eliminate the interference of noise, artifacts and the like outside the breast, further determine the ROI of the focus and quickly reconstruct a three-dimensional image of the focus.
Specifically, as shown in fig. 7, the step S04 specifically includes: the ultrasonic imaging system and the diagonal line segment a (24) rotate at an angle of 45 degrees each time, an ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of the breast skin, the long axis of the ultrasonic linear array probe rotates at 45 degrees, 90 degrees and 135 degrees clockwise by taking the central point of the diagonal line segment a (24) of the external rectangle (23) of the coronal plane (22) as a central axis, ultrasonic images of all sections of the breast are recorded, and the edge and texture information of the breast (2) focus (21) in the three sections are extracted to describe the characteristics of a focus area. More slices extracted can help to obtain more breast (2) lesion (21) information features.
Additionally, the step S04 specifically includes: the ultrasonic imaging system rotates 90 degrees at each time with the diagonal segment a (24), an ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of the breast skin, the long axis of the ultrasonic linear array probe rotates 90 degrees clockwise by taking the central point of the diagonal segment a (24) of the circumscribed rectangle (23) of the coronal plane (22) as the central axis, an ultrasonic image of the breast section is recorded, and the edge and texture information of a focus (21) of the breast (2) in the breast section is extracted to describe the characteristics of the focus area.
The ultrasonic imaging system and the diagonal line segment a (24) rotate in a direction with a certain angle, the specific angle can be any angle, and the overall shape of the focus is judged mainly according to the experience of the ultrasonic imaging system in collecting the cut surface of the breast focus. In order to determine the angle, an angle meter is arranged inside an ultrasonic linear array probe of the ultrasonic imaging system, and the angle meter controls the angle of the ultrasonic linear array probe when the ultrasonic linear array probe rotates around a central point (25) of a diagonal line segment a (24).
An ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of breast skin, the long axis of the ultrasonic linear array probe is displaced in the parallel direction of a diagonal line segment a (24) of a circumscribed rectangle (23) of a coronal plane (22), the interval distance of the central points of all line segments is not more than 10mm, preferably 5mm, each section image of ultrasonic is recorded, and the edge and texture information of a breast (2) focus (21) in each section is extracted to describe the characteristics of a focus area.
As shown in fig. 5 and 6, the first section (241) of the breast is analyzed by an ultrasonic imaging system, a first boundary line (241 a) is arranged at the position where the gray level difference between the lesion (21) and the surrounding tissue is maximum, the second section (242) of the breast is analyzed, a second boundary line (242 a) is arranged at the position where the gray level difference between the lesion (21) and the surrounding tissue is maximum, a circumscribed rectangle (23) of the lesion (21) in the image of the coronal plane (22) is connected with the first boundary line (241 a) and the second boundary line (242 a), a circumscribed cuboid with the minimum volume of the three-dimensional ellipsoid lesion is constructed, the circumscribed cuboid is arranged as a three-dimensional sequence image region of interest, more boundary lines can be obtained by arranging each section of the breast, and the formed three-dimensional lesion cuboid is closer to the real shape. The ultrasonic imaging system analyzes the capsule solidity inside the three-dimensional rectangular focus (21) of the breast (2), and the method specifically comprises the following steps: cystic or solid.
Under the condition of ultrasonic fixed gain, a rectangular frame formed by extending the first boundary line (241 a) and the second boundary line (242 a) by no less than 10mm is respectively set as a field of view FOV (28) for ultrasonic tissue elastography analysis, and each section FOV is required to contain fat tissue, fibroglandular bodies and pectoralis major muscles.
The invention takes the detection of the breast focus as an example, and can also be used for the detection of the focus of organs such as liver, heart, lung, kidney and the like, the detection steps are the same as the steps, and different organs are distinguished only in the three-dimensional data volume acquisition process. The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method for extracting an interest region in a breast image based on palpation and ultrasonic data is characterized by comprising the following specific steps:
s01, acquiring the position of the intra-mammary lesion by using a palpation stress type tissue elastography system, and analyzing the data of the intra-mammary lesion into a two-dimensional sequence image of a coronal plane;
s02, setting a circumscribed rectangle according to the minimum area of the outline of the focus in the coronal plane image, and setting the circumscribed rectangle with the minimum area as an ROI (region of interest);
s03, setting a diagonal segment a according to the circumscribed rectangle of the coronal plane, acquiring data of a focus position in the breast in the ROI along the diagonal segment a by using an ultrasonic imaging system, analyzing the data into a two-dimensional sequence image of a first section of the breast, and extracting the edge and texture information of the focus in the first section of the breast to describe the characteristics of the focus region;
s04, rotating in the direction of a certain angle between the ultrasonic imaging system and the diagonal line segment a, collecting data of the focus in the breast in the ROI, analyzing the data into a two-dimensional sequence image of a second section of the breast, and extracting the edge and texture information of the breast focus in the second section of the breast to describe the characteristics of the focus area;
and S05, determining the final three-dimensional position and characteristics of the breast lesion according to the continuous stress distribution data collected in the coronal plane and the characteristics of the lesion region extracted from the first section and the second section of the breast.
2. The method of claim 1, wherein the method comprises the steps of: the step S04 specifically includes: the ultrasonic imaging system rotates 45 degrees with the diagonal line segment a every time, an ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of the breast skin, the long axis of the ultrasonic linear array probe rotates 45 degrees, 90 degrees and 135 degrees clockwise in sequence by taking the central point of the diagonal line segment a of the external connection rectangle of the coronal plane as a central axis, ultrasonic images of all sections of the breast are recorded, and the edge and texture information of the focus in the breast in the sections are extracted to describe the characteristics of the focus area.
3. The method of claim 1, wherein the method comprises the following steps: the step S04 specifically includes: the ultrasonic imaging system rotates 90 degrees with the diagonal line segment a at each time, an ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of the breast skin, the long axis of the ultrasonic linear array probe rotates 90 degrees clockwise by taking the central point of the diagonal line segment a of the external connection rectangle of the coronal plane as a central axis, the ultrasonic image of the breast section is recorded, and the edge and texture information of the focus in the breast section are extracted to describe the characteristics of the focus area.
4. The method of claim 2 or 3, wherein the method comprises the following steps: an angle instrument is arranged in an ultrasonic linear array probe of the ultrasonic imaging system and controls the angle of the ultrasonic linear array probe when the ultrasonic linear array probe rotates along a diagonal segment a.
5. The method of claim 1, wherein the method comprises the steps of: analyzing the first section of the breast, setting a first boundary line at the position with the maximum gray difference between the focus and the surrounding tissues, analyzing a second section of the breast, setting a second boundary line at the position with the maximum gray difference between the focus and the surrounding tissues, connecting a circumscribed rectangle of the focus in the coronal image with the first boundary line and the second boundary line, constructing a minimum volume circumscribed cuboid of the three-dimensional ellipsoid focus, and setting the minimum volume circumscribed cuboid as a three-dimensional sequence image ROI.
6. The method of claim 5, wherein the method comprises the following steps: the ultrasound imaging system resolves the capsule/solid nature inside the three-dimensional solid rectangle of the lesion within the breast.
7. The method of claim 5, wherein the method comprises the steps of: under the condition of ultrasonic fixed gain, a rectangular frame formed by extending the first boundary line and the second boundary line not less than 10mm is respectively set as a view field FOV for ultrasonic tissue elastography analysis, and each section view field FOV is required to contain fat tissue, fibroglandular organ and pectoralis major.
8. The method of claim 1, wherein the method comprises the following steps: and (4) setting the central point of a diagonal segment a of the circumscribed rectangle of the coronal plane in the step (S03), analyzing and calculating continuous stress data recorded by the coronal plane by using a stress distribution map contour analysis method, and outputting property indexes of hardness, size, shape, surface smoothness and internal homogeneity of the focus in the breast.
9. The method of claim 1, wherein the method comprises the following steps: and the continuous stress distribution data of the coronal plane is fused with the elastic data of the ultrasonic tissues of the first section of the breast and the second section of the breast to construct the overall hardness distribution of the focus so as to obtain the overall heterogeneity of the focus.
10. The method of claim 1, wherein the method comprises the following steps: the ultrasonic linear array probe of the ultrasonic imaging system is perpendicular to the surface of breast skin, the long axis of the ultrasonic linear array probe is displaced in the parallel direction of a diagonal line segment a of a coronal plane external rectangle, the interval distance of the central points of all line segments is not more than 10mm, each section image of ultrasonic is recorded, and the edge and texture information of a focus in a breast in each section is extracted to describe the characteristics of a focus area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210449593.4A CN114943688A (en) | 2022-04-27 | 2022-04-27 | Method for extracting interest region in mammary gland image based on palpation and ultrasonic data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210449593.4A CN114943688A (en) | 2022-04-27 | 2022-04-27 | Method for extracting interest region in mammary gland image based on palpation and ultrasonic data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114943688A true CN114943688A (en) | 2022-08-26 |
Family
ID=82907740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210449593.4A Pending CN114943688A (en) | 2022-04-27 | 2022-04-27 | Method for extracting interest region in mammary gland image based on palpation and ultrasonic data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114943688A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117636076A (en) * | 2024-01-25 | 2024-03-01 | 北京航空航天大学 | Prostate MRI image classification method based on deep learning image model |
-
2022
- 2022-04-27 CN CN202210449593.4A patent/CN114943688A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117636076A (en) * | 2024-01-25 | 2024-03-01 | 北京航空航天大学 | Prostate MRI image classification method based on deep learning image model |
| CN117636076B (en) * | 2024-01-25 | 2024-04-12 | 北京航空航天大学 | Prostate MRI image classification method based on deep learning image model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Egorov et al. | Prostate mechanical imaging: 3-D image composition and feature calculations | |
| CN103578099B (en) | The extracting method of tumor elastic characteristic based on ultrasonic elastograph imaging | |
| KR102060895B1 (en) | Method for producing medical image and device for producing medical image | |
| Sencha et al. | Breast ultrasound | |
| CN107789056B (en) | Medical image matching and fusing method | |
| CN110111296A (en) | The automatic segmenting system of small infarct lesion and its method under the new hair cortex of deep learning | |
| Lee et al. | Endoscopic ultrasound elastography for the pancreas in Korea: a preliminary single center study | |
| Wang et al. | A 3-D region-growing motion-tracking method for ultrasound elasticity imaging | |
| Gazhonova | 3D automated breast volume sonography | |
| Shipley et al. | Automated quantitative volumetric breast ultrasound data-acquisition system | |
| CN114943688A (en) | Method for extracting interest region in mammary gland image based on palpation and ultrasonic data | |
| US20050245826A1 (en) | Apparatus for imaging human tissue | |
| CN109741439A (en) | A kind of three-dimensional rebuilding method of two dimension MRI fetus image | |
| US11672503B2 (en) | Systems and methods for detecting tissue and shear waves within the tissue | |
| CN113838020B (en) | Lesion area quantification method based on molybdenum target image | |
| Galea | Mapping tactile imaging information: parameter estimation and deformable registration | |
| Zhang et al. | Ultrasonic image fibrosis staging based on machine learning for chronic liver disease | |
| Berthomier et al. | Deep Venous Thrombosis: Database creation and image preprocessing | |
| CN116415649B (en) | Breast micro cancer analysis method based on multi-mode ultrasonic image self-supervision learning | |
| TWM547954U (en) | Diagnosis system for detecting pathological change | |
| Liu et al. | Inter-observer agreement on the evaluation of automated breast volume scanner for breast masses | |
| Pandilwar et al. | A Comprehensive Analysis of Ultrasound Image Processing Methods | |
| Morin et al. | 3D ultrasound simulation based on a biomechanical model of prone MRI in breast cancer imaging | |
| Józwik | Algorithm for the Fusion of Ultrasound Tomography Breast Images Allowing Automatic Discrimination Between Benign and Malignant Tumors in Screening Tests | |
| Fan et al. | Application of Elasticity Imaging Techniques Based on Ultrasound in Breast Tumor Activity, Blood Supply, and Benign and Malignant Tumor Diagnosis |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220826 |
|
| WD01 | Invention patent application deemed withdrawn after publication |