CN108932714A - The patch classification method of coronary artery CT image - Google Patents
The patch classification method of coronary artery CT image Download PDFInfo
- Publication number
- CN108932714A CN108932714A CN201810810078.8A CN201810810078A CN108932714A CN 108932714 A CN108932714 A CN 108932714A CN 201810810078 A CN201810810078 A CN 201810810078A CN 108932714 A CN108932714 A CN 108932714A
- Authority
- CN
- China
- Prior art keywords
- coronary artery
- image
- radius
- calcified plaque
- narrow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a kind of patch classification methods of coronary artery CT image, comprising: is split to coronary artery CTA sequence original graph, obtains coronary artery and extract figure；Coronary artery tree data contour surface is extracted, generates grid model data, and calculate normal vector, to point location starting point and end point all on grid model, the shortest path between starting point and end point is calculated, curve obtained is equidistantly filtered, center line and radius are obtained；Speck is positioned from coronary artery extraction figure；According to radius and laying-out curve narrow location and narrow range；The coronary artery bianry image after removal calcified plaque is obtained, the center line of the coronary artery bianry image after removal calcified plaque is obtained and calculates radius；It is noncalcified plaques if narrow location is identical as the narrow location in step S04 according to radius, laying-out curve narrow location and narrow range, is otherwise calcified plaque position.Calcification and noncalcified plaques can be detected in CTA image and classify automatically.
Description
Technical field
The present invention relates to technical field of medical image processing, more particularly to a kind of patch classification side of coronary artery CT image
Method can be applied to X in clinical research and penetrate coronary angiography image analysis.
Background technique
A kind of method for finding safe and reliable inspection coronary artery disease is the main target of clinical future development, so energy
Enough accurately extraction patch carrys out evaluation of coronary artery disease from CTA image sequence, with important clinical value and practical meaning
Justice.The past during the decade, coronary artery disease causes dead ratio to rise year by year, therefore accurately extracts artery vessel disease quantization very
It is necessary to especially patch early detection and quantitative analysis is more prominent.However the early detection of patch and quantization need very
Experienced doctor's cost is very long to carry out manual patch segmentation and analysis in this world, it is therefore necessary to which proposition automatically and rapidly detects the heart
The method of dirty coronary artery patch is to promote the working efficiency of doctor.
In the detection direction of coronary plaque, there are certain methods to be proposed for improving the detection of patch at present, but several
All it is the detection to calcified plaque, is lost the noncalcified plaques not exclusively to develop in CTA image.
Calcified plaque logarithm big absolutely is transformed by noncalcified plaques, so non-calcified plate can be detected as early as possible
Block, the prediction for coronary artery disease, it appears more valuable.The present invention is therefore.
Summary of the invention
In order to solve above-mentioned technical problem, the object of the present invention is to provide a kind of patches of coronary artery CT image
Classification method can detect calcification and noncalcified plaques in CTA image and classify automatically.
The technical scheme is that
A kind of patch classification method of coronary artery CT image, which comprises the following steps:
S01: being split coronary artery CTA sequence original graph, obtains coronary artery and extracts figure；
S02: extracting coronary artery tree data contour surface, grid model data is generated, and calculate normal vector, to institute on grid model
Some point location starting point and end points calculate the shortest path between starting point and end point, curve obtained is carried out etc.
Away from filtering, center line and radius are obtained；
S03: speck is positioned from coronary artery extraction figure；
S04: according to radius and laying-out curve narrow location and narrow range；
S05: obtaining the coronary artery bianry image after removal calcified plaque, obtains the coronary artery two-value after removal calcified plaque
The center line and calculating radius of image；
S06: according to radius, laying-out curve narrow location and narrow range, if the narrow position in narrow location and step S04
It sets identical, is then noncalcified plaques, is otherwise calcified plaque position.
In preferred technical solution, the threshold value that the method for speck is greater than setting for pixel value is positioned in the step S03 is
It is judged as speck.
In preferred technical solution, the side of the coronary artery bianry image after removal calcified plaque is obtained in the step S05
Method is that the pixel value that pixel value is greater than the threshold value of setting is set to 0, is otherwise set to 1, obtains the coronary artery after removal calcified plaque
Bianry image.
Compared with prior art, the invention has the advantages that
The method of the present invention can detect calcification and noncalcified plaques in CTA image and classify automatically.
Detailed description of the invention
The invention will be further described with reference to the accompanying drawings and embodiments:
Fig. 1 is flow chart of the method for the present invention；
Fig. 2 is that coronary artery of the invention extracts figure；
Fig. 3 is radius curve figure of the invention；
Fig. 4 is final result schematic diagram of the invention.
Specific embodiment
In order to make the objectives, technical solutions and advantages of the present invention clearer, With reference to embodiment and join
According to attached drawing, the present invention is described in more detail.It should be understood that these descriptions are merely illustrative, and it is not intended to limit this hair
Bright range.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid this is unnecessarily obscured
The concept of invention.
As shown in Figure 1, the patch classification method of coronary artery CT image of the invention, includes the following steps.
Step S1: coronary artery is carried out on CT image and divides to obtain coronary artery extraction figure (having calcified plaque, have narrow).
CT image data is read, heart area is first confined and excludes bone interference, obtain heart and extract image, recycle coronary artery
The gray difference of gray scale and the other tissues of heart extracts image to heart using image-region growth partitioning algorithm and is split, and goes
Except cardiac muscle, aorta etc. are organized, coronary artery extraction figure is obtained, as shown in Figure 2.
Step S2: center line is calculated.Coronary artery tree data are extracted into contour surface using MarchingCubes algorithm, generate net
Lattice model data, and normal vector has been calculated, the Delaunay Triangulation processing for carrying out 3D to point all on grid exists
Starting point and all end points are positioned on Voronoi diagram, then uses Fast Marching (Fast marching) algorithm, are calculated
Shortest path between starting point and end point equidistantly filters curve obtained, forms specification, carefully and neatly done center line
Data；
Step S3: radius is calculated.By the directly available radius of the Voronoi diagram in step S2, radius curve figure such as Fig. 3
It is shown；
Step S4: speck (the high coordinate of bright spot in speck, calcified plaque) is positioned from three-dimensional blood-vessel image.Traversal coronary artery mentions
The pixel value in figure is taken, if wherein there is the pixel that pixel value is greater than 700 (needing to be adjusted according to practical patch gray value)
Point is then judged as that there are calcified plaque, the point of these high pixels is exactly calcified plaque point；
Step S5: from radius curve analyzing and positioning narrow (the corresponding three-dimensional coordinate of point ID on center line, non-calcified spot
Block)；Narrow location and narrow range are positioned according to radius curve, then there are noncalcified plaques for the narrow location；
Step S6: calcified plaque is gone.The pixel for being higher than 700 in coronary artery extraction figure is set to 0 by Threshold Segmentation Algorithm,
The pixel that will be less than 700 is set to 1, and formula is as follows:
Wherein P (x, y, z) is the coronary artery bianry image after Threshold segmentation, and T (x, y, z) is that coronary artery extracts image, the value of t
It is 700；Since plaque area is typically no less than 2mm2, the pel spacing of this experimental image is 0.625mm, so extraction P (x, y,
Z) part that connected pixel is higher than 20 pixels in obtains the image N (x, y, z) of calcified plaque, and P (x, y, z) removes N (x, y, z)
Coronary artery image M (x, y, z) after the removal calcified plaque that part obtains, formula is as follows,
Step S7: it regains center line and calculates radius.Coronary artery binary image obtained in step S6 is repeated to walk
Rapid S2 and step S3, obtains new center line and radius curve；
Step S8: again from radius curve analyzing and positioning it is narrow (the corresponding three-dimensional coordinate of point ID on center line, calcification+
Noncalcified plaques)；Position narrow location and narrow range according to radius curve, if narrow location be occur in step S5 it is narrow
Position is then noncalcified plaques, is otherwise calcified plaque position, final result is as shown in figure 4, shadow region is calcified plaque.
It should be understood that above-mentioned specific embodiment of the invention is used only for exemplary illustration or explains of the invention
Principle, but not to limit the present invention.Therefore, that is done without departing from the spirit and scope of the present invention is any
Modification, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.In addition, appended claims purport of the present invention
Covering the whole variations fallen into attached claim scope and boundary or this range and the equivalent form on boundary and is repairing
Change example.
Claims (3)
1. a kind of patch classification method of coronary artery CT image, which comprises the following steps:
S01: being split coronary artery CTA sequence original graph, obtains coronary artery and extracts figure；
S02: extracting coronary artery tree data contour surface, grid model data is generated, and calculate normal vector, to all on grid model
Point location starting point and end point calculates the shortest path between starting point and end point, carries out equidistant mistake to curve obtained
Filter, obtains center line and radius；
S03: speck is positioned from coronary artery extraction figure；
S04: according to radius and laying-out curve narrow location and narrow range；
S05: obtaining the coronary artery bianry image after removal calcified plaque, obtains the coronary artery bianry image after removal calcified plaque
Center line and calculate radius；
S06: according to radius, laying-out curve narrow location and narrow range, if narrow location and the narrow location phase in step S04
Together, then it is noncalcified plaques, is otherwise calcified plaque position.
2. the patch classification method of coronary artery CT image according to claim 1, which is characterized in that fixed in the step S03
The method of position speck is that the threshold value that pixel value is greater than setting is to be judged as speck.
3. the patch classification method of coronary artery CT image according to claim 1, which is characterized in that in the step S05
The method of coronary artery bianry image after to removal calcified plaque is that the pixel value that pixel value is greater than the threshold value of setting is set to 0,
Otherwise it is set to 1, obtains the coronary artery bianry image after removal 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 true CN108932714A (en) | 2018-12-04 |
| CN108932714B 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) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109671091A (en) * | 2019-02-27 | 2019-04-23 | 数坤（北京）网络科技有限公司 | A kind of non-calcified spot detection method and non-calcified spot detection device |
| CN109754400A (en) * | 2019-01-21 | 2019-05-14 | 数坤（北京）网络科技有限公司 | Vein minimizing technology |
| CN109872321A (en) * | 2019-02-26 | 2019-06-11 | 数坤（北京）网络科技有限公司 | Method and device for detecting vascular stenosis |
| 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 |
| CN111445449A (en) * | 2020-03-19 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Region-of-interest classification method and device, computer equipment and storage medium |
| CN111709925A (en) * | 2020-05-26 | 2020-09-25 | 深圳科亚医疗科技有限公司 | Devices, systems and media for vascular plaque analysis |
| CN112700421A (en) * | 2021-01-04 | 2021-04-23 | 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 |
| CN113628193A (en) * | 2021-08-12 | 2021-11-09 | 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 |
| WO2022109908A1 (en) * | 2020-11-25 | 2022-06-02 | 苏州润迈德医疗科技有限公司 | Method and system for adjusting vascular stenosis zone, and storage medium |
| CN115690309A (en) * | 2022-09-29 | 2023-02-03 | 中国人民解放军总医院第一医学中心 | A method and device for automatic three-dimensional post-processing of coronary artery CTA |
Citations (3)
| 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 |
| 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 |
-
2018
- 2018-07-23 CN CN201810810078.8A patent/CN108932714B/en active Active
Patent Citations (3)
| 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 |
| 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 |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109754400A (en) * | 2019-01-21 | 2019-05-14 | 数坤（北京）网络科技有限公司 | Vein minimizing technology |
| 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 | Method and device for detecting vascular stenosis |
| CN109671091A (en) * | 2019-02-27 | 2019-04-23 | 数坤（北京）网络科技有限公司 | A kind of non-calcified spot detection method and non-calcified spot detection device |
| 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 |
| CN111445449A (en) * | 2020-03-19 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Region-of-interest classification method and device, computer equipment and storage medium |
| 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 |
| CN111709925A (en) * | 2020-05-26 | 2020-09-25 | 深圳科亚医疗科技有限公司 | Devices, systems and media for vascular plaque analysis |
| 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 |
| WO2022109908A1 (en) * | 2020-11-25 | 2022-06-02 | 苏州润迈德医疗科技有限公司 | Method and system for adjusting vascular stenosis zone, and storage medium |
| 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 |
| CN112700421A (en) * | 2021-01-04 | 2021-04-23 | 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 |
| CN113628193A (en) * | 2021-08-12 | 2021-11-09 | 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 |
| 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 |
| CN115690309A (en) * | 2022-09-29 | 2023-02-03 | 中国人民解放军总医院第一医学中心 | A method and device for automatic three-dimensional post-processing of coronary artery CTA |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108932714B (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108932714A (en) | The patch classification method of coronary artery CT image | |
| US9230331B2 (en) | Systems and methods for registration of ultrasound and CT images | |
| Anter et al. | Automatic computer aided segmentation for liver and hepatic lesions using hybrid segmentations techniques | |
| JP4682091B2 (en) | Method, apparatus and storage medium for detecting heart boundary, rib cage boundary and diaphragm boundary | |
| Garg et al. | Unsupervised curvature-based retinal vessel segmentation | |
| CN110866905B (en) | Rib recognition and labeling method | |
| CN109478327B (en) | A method for automatic detection of systemic arteries in any field of view computed tomography angiography (CTA) | |
| Li et al. | A novel method of vessel segmentation for X-ray coronary angiography images | |
| Maitra et al. | Accurate breast contour detection algorithms in digital mammogram | |
| JP6458166B2 (en) | MEDICAL IMAGE PROCESSING METHOD, DEVICE, SYSTEM, AND PROGRAM | |
| Ait Lbachir et al. | A new mammogram preprocessing method for Computer-Aided Diagnosis systems | |
| Soltaninejad et al. | Robust lung segmentation combining adaptive concave hulls with active contours | |
| Feudjio et al. | Automatic extraction of pectoral muscle in the MLO view of mammograms | |
| Ojo et al. | Pre-processing method for extraction of pectoral muscle and removal of artefacts in mammogram | |
| Ebrahimdoost et al. | Automatic segmentation of pulmonary artery (PA) in 3D pulmonary CTA images | |
| KR20160005256A (en) | Seed point detection method for coronary artery extraction from CCTA | |
| Pelapur et al. | Multi-focus image fusion using epifluorescence microscopy for robust vascular segmentation | |
| KR101494975B1 (en) | Nipple automatic detection system and the method in 3D automated breast ultrasound images | |
| Elmorsy et al. | K3. A region growing liver segmentation method with advanced morphological enhancement | |
| Hemalatha et al. | Computerized breast cancer detection system | |
| Kusumaningtyas et al. | Feature extraction for application of heart abnormalities detection through iris based on mobile devices | |
| Abdellatif et al. | K2. Automatic pectoral muscle boundary detection in mammograms using eigenvectors segmentation | |
| KR101484051B1 (en) | Apparatus and method for preprocessing for CAD system using active contour method | |
| Bethapudi et al. | Detection of malignancy in digital mammograms from segmented breast region using morphological techniques | |
| EP4026087A1 (en) | Method and system for image normalisation |
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 | ||
| 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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |