CN108932714B - Plaque classification method of coronary artery CT image - Google Patents
Plaque classification method of coronary artery CT image Download PDFInfo
- Publication number
- CN108932714B CN108932714B CN201810810078.8A CN201810810078A CN108932714B CN 108932714 B CN108932714 B CN 108932714B CN 201810810078 A CN201810810078 A CN 201810810078A CN 108932714 B CN108932714 B CN 108932714B
- Authority
- CN
- China
- Prior art keywords
- coronary artery
- plaque
- image
- calcified
- radius
- 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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T7/68—Analysis of geometric attributes of symmetry
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The invention discloses a plaque classification method of coronary artery CT images, which comprises the following steps: segmenting the original coronary artery CT sequence image to obtain a coronary artery extraction image; extracting the equivalent surface of coronary artery tree data, generating grid model data, calculating a normal vector, positioning a starting point and an ending point of all points on a grid model, calculating a shortest path between the starting point and the ending point, and performing equidistant filtering on an obtained curve to obtain a central line and a radius; locating bright spots from the coronary extraction map; positioning a narrow position and a narrow interval according to the radius and the curve; obtaining a coronary artery binary image after the calcified plaque is removed, obtaining a central line of the coronary artery binary image after the calcified plaque is removed, and calculating the radius; the stenosis position and the stenosis section are located based on the radius and the curve, and if the stenosis position is the same as the stenosis position in step S04, the plaque is a non-calcified plaque, otherwise, the plaque is a calcified plaque position. Calcified and non-calcified plaques can be detected in CT images and automatically classified.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a plaque classification method of a coronary artery CT image, which can be applied to X-ray coronary angiography image analysis in clinical research.
Background
The method for safely and reliably checking the coronary artery disease is a main target of clinical future development, so that the plaque can be accurately extracted from the CT image sequence to judge the coronary artery disease, and the method has important clinical value and practical significance. The rate of coronary artery disease leading to death has risen year after year over the last decade, so accurate extraction of quantification of arterial vascular disease is essential, especially for early plaque detection and quantitative analysis. However, early detection and quantification of plaque requires a very experienced doctor to perform manual plaque segmentation and analysis in a long time, so that a method for automatically and rapidly detecting coronary plaque needs to be provided to improve the working efficiency of the doctor.
In the detection direction of coronary artery plaque, some methods are proposed at present to improve the detection of plaque, but the detection of calcified plaque is almost all, and non-calcified plaque which is not completely developed in a CT image is lost.
Since most of calcified plaques are converted from non-calcified plaques, the method can detect the non-calcified plaques as early as possible, and is more valuable for predicting coronary artery diseases. The invention is achieved accordingly.
Disclosure of Invention
In order to solve the technical problems, the invention aims to: a method for classifying coronary artery CT image plaque is provided, which can detect calcified plaque and non-calcified plaque in CT image and automatically classify the plaque.
The technical scheme of the invention is as follows:
a plaque classification method of coronary artery CT images is characterized by comprising the following steps:
s01: segmenting the original coronary artery CT sequence image to obtain a coronary artery extraction image;
s02: extracting the equivalent surface of coronary artery tree data, generating grid model data, calculating a normal vector, positioning a starting point and an ending point of all points on a grid model, calculating a shortest path between the starting point and the ending point, and performing equidistant filtering on an obtained curve to obtain a central line and a radius;
s03: locating bright spots from the coronary extraction map;
s04: positioning a narrow position and a narrow interval according to the radius and the curve;
s05: obtaining a coronary artery binary image after the calcified plaque is removed, obtaining a central line of the coronary artery binary image after the calcified plaque is removed, and calculating the radius;
s06: the stenosis position and the stenosis section are located based on the radius and the curve, and if the stenosis position is the same as the stenosis position in step S04, the plaque is a non-calcified plaque, otherwise, the plaque is a calcified plaque position.
In a preferred embodiment, in the step S03, the method for locating the bright spots is to determine that the bright spots are bright spots when the pixel value is greater than a set threshold value.
In a preferred technical solution, the method for obtaining the coronary artery binary image after removing the calcified plaque in step S05 is to set a pixel value of which the pixel value is greater than a set threshold value to 0, otherwise to 1, and obtain the coronary artery binary image after removing the calcified plaque.
Compared with the prior art, the invention has the advantages that:
the method can detect calcified and non-calcified plaques in the CT image and automatically classify the plaques.
Drawings
The invention is further described with reference to the following figures and examples:
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a coronary extraction diagram of the present invention;
FIG. 3 is a radius graph of the present invention;
FIG. 4 is a diagram illustrating the final result of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
As shown in fig. 1, the method for classifying plaque in coronary CT image of the present invention includes the following steps.
Step S1: coronary artery segmentation is performed on the CT image to obtain a coronary artery extraction image (with calcified plaque and stenosis).
Reading CT image data, firstly framing a heart region to eliminate skeleton interference to obtain a heart extraction image, then segmenting the heart extraction image by using the gray difference between coronary artery gray and other tissues of the heart and adopting an image region growing segmentation algorithm to remove tissues such as cardiac muscle, aorta and the like to obtain a coronary artery extraction image, as shown in figure 2.
Step S2: the centerline is calculated. Extracting an isosurface from coronary artery tree data by using a MarchingCubes algorithm, generating grid model data, calculating a normal vector, performing 3D Delaunay triangulation processing on all points on a grid, positioning a starting point and all end points on a Voronoi diagram, calculating a shortest path between the starting point and the end points by using a Fast Marching algorithm, and performing equidistant sampling and point taking on an obtained curve to form standard and complete center line data;
step S3: the radius is calculated. The radius is directly obtained from the Voronoi diagram in step S2, and the radius graph is shown in fig. 3;
step S4: the bright spots (coordinates of the high bright spots in the bright spots, calcified plaques) are located from the three-dimensional vessel image. Traversing pixel values in the coronary artery extraction image, if pixel points with pixel values larger than 700 (which need to be adjusted according to the actual plaque gray value) exist, judging that calcified plaques exist, and determining points with high pixels to be calcified plaque points;
step S5: locating stenosis (three-dimensional coordinates corresponding to point ID on the centerline, non-calcified plaque) from radius curve analysis; positioning a stenosis position and a stenosis interval according to the radius curve, wherein a non-calcified plaque exists in the stenosis position;
step S6: and removing calcified plaque. Setting the pixel points higher than 700 in the coronary artery extraction graph as 0 and setting the pixel points lower than 700 as 1 by a threshold segmentation algorithm, wherein the formula is as follows:
wherein P (x, y, z) is a coronary binary image after threshold segmentation, T (x, y, z) is a coronary extraction image, and the value of T is 700; because the area of the plaque is generally not less than 2mm2The pixel pitch of the experimental image is 0.625mm, so that the extraction P (x, y, z) is connectedThe image N (x, y, z) of calcified plaque is obtained from the part with the pixels higher than 20 pixels, the coronary artery image M (x, y, z) after the calcified plaque is removed is obtained by removing the N (x, y, z) from the P (x, y, z), the formula is as follows,
step S7: the centerline is retrieved and the radius calculated. Repeating the step S2 and the step S3 on the coronary binary image obtained in the step S6 to obtain a new central line and a new radius curve;
step S8: re-locating the stenosis from the radius curve analysis (three-dimensional coordinates corresponding to the point ID on the centerline, calcified + non-calcified plaque); the stenosis position and the stenosis section are located based on the radius curve, and if the stenosis position is the stenosis position appearing in step S5, it is a non-calcified plaque, otherwise, it is a calcified plaque position, and the final result is shown in fig. 4, in which the hatched area is a calcified plaque.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (3)
1. A plaque classification method of coronary artery CT images is characterized by comprising the following steps:
s01: segmenting the coronary artery CT image to obtain a coronary artery extraction image;
s02: extracting the equivalent surface of coronary artery tree data, generating grid model data, calculating a normal vector, positioning a starting point and an ending point of all points on a grid model, calculating a shortest path between the starting point and the ending point, and performing equidistant filtering on an obtained curve to obtain a central line and a radius;
s03: locating bright spots from the coronary extraction map;
s04: positioning a narrow position and a narrow interval according to the radius and the curve;
s05: obtaining a coronary artery binary image after the calcified plaque is removed, obtaining a central line of the coronary artery binary image after the calcified plaque is removed, and calculating the radius;
s06: and (4) positioning the stenosis position and the stenosis section according to the radius curve calculated in the step S05, wherein if the stenosis position is the same as the stenosis position in the step S04, the location is the non-calcified plaque, and otherwise, the location is the calcified plaque.
2. The method for classifying plaque in coronary artery CT image according to claim 1, wherein the method for locating the bright spot in step S03 is to determine the bright spot if the pixel value is larger than the set threshold value.
3. The method for classifying coronary artery CT images according to claim 1, wherein the method for obtaining the coronary artery binary image after removing the calcified plaque in step S05 is to set a pixel value having a pixel value greater than a set threshold value to 0, and otherwise to 1, to obtain the coronary artery binary image after removing the calcified plaque.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810810078.8A CN108932714B (en) | 2018-07-23 | 2018-07-23 | Plaque classification method of coronary artery CT image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810810078.8A CN108932714B (en) | 2018-07-23 | 2018-07-23 | Plaque classification method of coronary artery CT image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108932714A CN108932714A (en) | 2018-12-04 |
| CN108932714B true CN108932714B (en) | 2021-11-23 |
Family
ID=64444341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810810078.8A Active CN108932714B (en) | 2018-07-23 | 2018-07-23 | Plaque classification method of coronary artery CT image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108932714B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109754400B (en) * | 2019-01-21 | 2020-12-29 | 数坤（北京）网络科技有限公司 | Vein removal method |
| CN109872321A (en) * | 2019-02-26 | 2019-06-11 | 数坤（北京）网络科技有限公司 | A kind of hemadostewnosis detection method and equipment |
| CN109671091B (en) * | 2019-02-27 | 2021-01-01 | 数坤（北京）网络科技有限公司 | Non-calcified plaque detection method and non-calcified plaque detection equipment |
| CN110910441A (en) * | 2019-11-15 | 2020-03-24 | 首都医科大学附属北京友谊医院 | Method and device for extracting center line |
| CN111445449B (en) * | 2020-03-19 | 2024-03-01 | 上海联影智能医疗科技有限公司 | Method, device, computer equipment and storage medium for classifying region of interest |
| CN111709925B (en) * | 2020-05-26 | 2023-11-03 | 深圳科亚医疗科技有限公司 | Devices, systems, and media for vascular plaque analysis |
| CN112472112B (en) * | 2020-11-25 | 2024-02-27 | 苏州润迈德医疗科技有限公司 | Method, system and storage medium for regulating vascular stenosis |
| CN112700421B (en) * | 2021-01-04 | 2022-03-25 | 推想医疗科技股份有限公司 | Coronary image classification method and device |
| CN113077441A (en) * | 2021-03-31 | 2021-07-06 | 上海联影智能医疗科技有限公司 | Coronary artery calcified plaque segmentation method and method for calculating coronary artery calcified score |
| CN113628193B (en) * | 2021-08-12 | 2022-07-15 | 推想医疗科技股份有限公司 | Method, device and system for determining blood vessel stenosis rate and storage medium |
| CN115690309B (en) * | 2022-09-29 | 2023-07-18 | 中国人民解放军总医院第一医学中心 | Automatic three-dimensional post-processing method and device for coronary artery CTA |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133478A (en) * | 2018-01-11 | 2018-06-08 | 苏州润心医疗器械有限公司 | A kind of method for extracting central line of coronary artery vessel |
| CN108171698A (en) * | 2018-02-12 | 2018-06-15 | 数坤（北京）网络科技有限公司 | A kind of method of automatic detection human heart Coronary Calcification patch |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030190063A1 (en) * | 2002-03-08 | 2003-10-09 | Acharya Kishore C. | Method and system for performing coronary artery calcification scoring |
-
2018
- 2018-07-23 CN CN201810810078.8A patent/CN108932714B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133478A (en) * | 2018-01-11 | 2018-06-08 | 苏州润心医疗器械有限公司 | A kind of method for extracting central line of coronary artery vessel |
| CN108171698A (en) * | 2018-02-12 | 2018-06-15 | 数坤（北京）网络科技有限公司 | A kind of method of automatic detection human heart Coronary Calcification patch |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108932714A (en) | 2018-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108932714B (en) | Plaque classification method of coronary artery CT image | |
| US10115039B2 (en) | Method and system for machine learning based classification of vascular branches | |
| US10157467B2 (en) | System and method for detecting central pulmonary embolism in CT pulmonary angiography images | |
| US8411927B2 (en) | Marker detection in X-ray images | |
| JP6058093B2 (en) | Computer-aided analysis device for medical images and computer program for medical image analysis | |
| US9715637B2 (en) | Method and system for automatic aorta segmentation | |
| JP4682091B2 (en) | Method, apparatus and storage medium for detecting heart boundary, rib cage boundary and diaphragm boundary | |
| CN105279759B (en) | The abdominal cavity aortic aneurysm outline dividing method constrained with reference to context information arrowband | |
| KR102050649B1 (en) | Method for extracting vascular structure in 2d x-ray angiogram, computer readable medium and apparatus for performing the method | |
| KR102251830B1 (en) | Systems and methods for registration of ultrasound and ct images | |
| CN110910370B (en) | CTA image coronary stenosis detection method and device | |
| CN107633514B (en) | Pulmonary nodule peripheral blood vessel quantitative evaluation system and method | |
| US8422753B2 (en) | Method and system for automatic extraction of personalized left atrium models | |
| JP2018134393A (en) | Method and apparatus for segmentation of blood vessels | |
| WO2011093921A1 (en) | Automated vascular region separation in medical imaging | |
| JP2009211138A (en) | Target area extraction method, device and program | |
| Zheng et al. | Fast and automatic heart isolation in 3D CT volumes: Optimal shape initialization | |
| Maitra et al. | Accurate breast contour detection algorithms in digital mammogram | |
| US8050470B2 (en) | Branch extension method for airway segmentation | |
| Soltaninejad et al. | Robust lung segmentation combining adaptive concave hulls with active contours | |
| JP2013223674A (en) | Image processor, and image processing method | |
| KR101126224B1 (en) | Prostate segmentation method using dynamic mr images and system thereof | |
| Kusumaningtyas et al. | Feature extraction for application of heart abnormalities detection through iris based on mobile devices | |
| CN111295665A (en) | Determining regions of high density lung tissue in lung images | |
| CN111739026B (en) | Blood vessel center line-based adhesion cutting method and device |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210430 Address after: Room nw-05-502, Northwest District, Suzhou nano City, 99 Jinjihu Avenue, Suzhou Industrial Park, 215000, Jiangsu Province Applicant after: SUZHOU RAINMED MEDICAL TECHNOLOGY Co.,Ltd. Address before: Room 502, building 5, northwest Suzhou nano City, 99 Jinjihu Avenue, Suzhou Industrial Park, Jiangsu Province, 215123 Applicant before: SUZHOU RUNXIN MEDICAL EQUIPMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |