CN117455878A - CCTA image-based coronary vulnerable plaque identification method and system - Google Patents
CCTA image-based coronary vulnerable plaque identification method and system Download PDFInfo
- Publication number
- CN117455878A CN117455878A CN202311473400.XA CN202311473400A CN117455878A CN 117455878 A CN117455878 A CN 117455878A CN 202311473400 A CN202311473400 A CN 202311473400A CN 117455878 A CN117455878 A CN 117455878A
- Authority
- CN
- China
- Prior art keywords
- image
- vulnerable plaque
- plaque
- model
- coronary
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 101000666730 Homo sapiens T-complex protein 1 subunit alpha Proteins 0.000 title claims abstract 13
- 102100038410 T-complex protein 1 subunit alpha Human genes 0.000 title claims abstract 13
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 33
- 210000004351 coronary vessel Anatomy 0.000 claims abstract description 31
- 230000011218 segmentation Effects 0.000 claims abstract description 17
- 230000007246 mechanism Effects 0.000 claims abstract description 11
- 239000000523 sample Substances 0.000 claims abstract description 10
- 230000002792 vascular Effects 0.000 claims abstract description 7
- 238000001514 detection method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 230000002308 calcification Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 208000024891 symptom Diseases 0.000 abstract description 8
- 238000003745 diagnosis Methods 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 208000004476 Acute Coronary Syndrome Diseases 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 206010057469 Vascular stenosis Diseases 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010968 computed tomography angiography Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 208000037804 stenosis Diseases 0.000 description 1
- 230000036262 stenosis Effects 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0499—Feedforward networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention relates to the field of medical engineering, and discloses a method and a system for identifying vulnerable plaque of coronary artery based on CCTA image. The method comprises the steps of firstly obtaining segmented vascular masks based on the existing coronary artery segmentation model, and obtaining SCPR images after extracting the central line of the blood vessels. Then, for each plaque on the SCPR image, converting each layer of probe image in the plaque range into a common image format, inputting the coronary vulnerable plaque identification model based on the ViT model, outputting the probability of vulnerable plaque symptoms, and then obtaining the vulnerable plaque identification result. The coronary vulnerable plaque identification model provided by the invention can capture all information in the whole image, wherein the attention mechanism can focus on areas of different probe images of the plaque, thereby being beneficial to efficiently acquiring visual features of vulnerable plaque symptoms and improving the robustness of vulnerable plaque identification. Provides possibility for clinical application and improves the integrity and richness of the diagnosis report.
Description
Technical Field
The invention relates to the field of medical engineering, in particular to a method and a system for identifying vulnerable plaque of coronary artery based on CCTA image.
Background
Acute Coronary Syndromes (ACS) have a high mortality rate and account for a significant proportion of cardiovascular death, and studies have shown that nearly 70% of ACS is caused by vulnerable plaque rupture. Coronary artery computed tomography angiography (CCTA) is a well-known noninvasive imaging modality for diagnosing coronary arteries, and is an important method for early screening and definitive diagnosis of coronary heart disease in clinic at present, and can be used for identifying coronary plaque and evaluating the degree of vascular stenosis. However, in the current clinical application and diagnostic report, CCTA assessment is mainly focused on lumen stenosis, and risk assessment for vulnerable plaque (vulnerable plaque contains four signs, namely positive reconstitution, low density, napkin ring and punctiform calcification, and contains two or more signs, namely, is considered as vulnerable plaque) is insufficient. The reasons are that doctors need subjective interpretation aiming at vulnerable plaque characteristics, the characteristic evaluation is complex, the diagnosis process is time-consuming and labor-consuming, and the professional requirements on the doctors are high. Internationally, CCTA-based detection of coronary plaque is more studied, and Maj et al use RCNN to detect coronary plaque, and the results can distinguish calcification, non-calcification and mixed plaque according to their spatial distribution. The model has good accuracy for the detection and characterization of coronary artery plaque, but has low reliability.
Disclosure of Invention
Aiming at the problems, the invention provides a method and a system for identifying coronary vulnerable plaque based on a CCTA image.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, the present invention provides a CCTA image-based coronary artery vulnerable plaque identification method, comprising the steps of:
s1, segmenting blood vessels of an original coronary artery image;
s2, extracting a central line of the segmented blood vessel to obtain an SCPR image;
s3, carrying out plaque detection on each segment of blood vessel based on the SCPR image;
s4, converting images;
s5, constructing a coronary vulnerable plaque identification model and carrying out model training;
s6, inputting the converted image into a trained model to obtain a vulnerable plaque recognition result.
Further, the S1 specifically includes: and inputting the original coronary artery image into an existing coronary artery segmentation model to obtain segmented vascular masks.
Further, the S2 specifically is: and (3) extracting a central line of the segmented vascular mask of the S1 by using a skeletonizing algorithm, and obtaining an SCPR image based on a CPR curved surface reconstruction technology.
Further, the step S3 specifically includes: plaque detection is carried out in the central point area by the developed plaque detection model on the SCPR image of each blood vessel segment to obtain the plaque on the blood vessel, and the position of the starting central point and the position of the ending central point represent the range of each plaque.
Further, the image conversion in S4 specifically includes: and mapping the pixel value of each layer of three-dimensional probe image to a common picture format in the plaque range, wherein the third dimension is 1.
Further, the identification model of the vulnerable plaque of the coronary artery in the S5 is constructed based on a ViT model, and the specific structure is as follows, and the identification model comprises:
an input encoder: the method comprises the steps of dividing an input image into a group of image blocks with fixed sizes, and then extracting features of each image block through a convolutional neural network CNN to obtain a group of vector representations serving as an input sequence;
position encoder: adding a position embedding vector to represent relative and absolute position information for each position in the input sequence;
an encoder: each coding layer comprises a multi-head self-attention mechanism and a feedforward full-connection network; the self-attention mechanism can pay attention to the dependency relationship between different positions in the sequence at the same time, and the characteristic extraction can be carried out from different subspaces through the multi-head mechanism; the feedforward full-connection network is responsible for nonlinear transformation of the characteristics;
normalization layer: the method is used for carrying out normalization processing on the output of the coding layer;
a classifier: a linear layer is connected after the coding layer, and the output of the coding layer is mapped to the predictive probabilities of four signs.
Further, the model training process in S7 is as follows: pre-training and model fine tuning is performed through the natural image dataset, the model is initialized with trained parameters, and then retrained on the vulnerable plaque dataset.
Further, the specific process of obtaining the vulnerable plaque identification result by the root in S7 is: first, the model will output four signs of vulnerable plaque: positive reconstruction, low density, napkin ring and punctiform calcification, and obtaining the identification result of the sign according to different probabilities, and then obtaining the identification result of vulnerable plaque according to whether two or more signs are identified, if two or more signs exist, the vulnerable plaque is considered, otherwise, the vulnerable plaque is not vulnerable plaque.
In a second aspect, the present invention provides a CCTA image-based coronary artery vulnerable plaque identification system, the system is used for implementing the CCTA image-based coronary artery vulnerable plaque identification method described above, the system includes a blood vessel segmentation and segmentation unit, a blood vessel centerline extraction unit, a plaque detection unit, an image conversion unit and an identification unit, wherein the blood vessel segmentation and segmentation unit is used for segmenting and segmenting blood vessels of an original coronary artery image; the blood vessel central line extraction unit is used for extracting a segmented blood vessel central line to obtain an SCPR image; the plaque detection unit is used for carrying out plaque detection on each segment of blood vessel in the SCPR image; the image conversion unit is used for converting each layer of three-dimensional probe image into a common picture format in the plaque range; the identification unit is used for obtaining a vulnerable plaque identification result by passing the converted image through a coronary vulnerable plaque identification model.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a CCTA image based coronary vulnerable plaque identification method as described above when executing the computer program.
In a fourth aspect, the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program for implementing a CCTA image based coronary vulnerable plaque identification method as described above when executed by a processor.
Compared with the prior art, the invention has the following advantages:
compared with the traditional CNN network, the coronary vulnerable plaque identification model based on the ViT model can capture all information in the whole image, and because the lengths and the components of different plaques are different, even the difference is large, and the positions of vulnerable plaque symptoms are difficult to determine, the attention mechanism of the coronary vulnerable plaque identification model constructed based on the ViT model can focus on the areas of different probe images of the plaque, thereby being beneficial to efficiently acquiring the visual characteristics of vulnerable plaque symptoms and improving the robustness of vulnerable plaque identification.
The CCTA image-based coronary artery vulnerable plaque identification method provided by the invention does not need a doctor to subjectively judge vulnerable plaque characteristics, so that diagnosis time and energy are greatly saved, possibility is provided for clinical application, and the completeness and richness of a diagnosis report are improved.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a flow chart of the operation of the input encoder.
FIG. 3 is a schematic diagram of the system of the present invention.
Detailed Description
The technical scheme of the invention is specifically and specifically described below with reference to the embodiment of the invention and the attached drawings. It should be noted that the following examples are only for illustrating the present invention and are not intended to limit the scope of the present invention. The technical means used in the examples are conventional means well known to those skilled in the art unless otherwise indicated.
As shown in step 1, a method for identifying vulnerable plaque of coronary artery based on CCTA image comprises the following specific steps:
1. and inputting the original coronary artery image into an existing coronary artery segmentation model to obtain segmented vascular masks.
2. And extracting a central line of the segmented vascular mask by using a skeletonizing algorithm, and obtaining an SCPR image based on a CPR curved surface reconstruction technology.
3. Plaque detection is carried out in the central point area by the developed plaque detection model on the SCPR image of each blood vessel segment to obtain the plaque on the blood vessel, and the position of the starting central point and the position of the ending central point represent the range of each plaque.
4. Within the plaque range, the pixel values of each layer of three-dimensional probe image (third dimension 1) are mapped to a common picture format.
5. Constructing a ViT model-based coronary vulnerable plaque identification model, wherein the model structure comprises the following steps:
an input encoder: for segmenting an input image into a set of image blocks of a fixed size, and then extracting features from each image block through a convolutional neural network CNN (see fig. 2) to obtain a set of vector representations as an input sequence. Because each patch length is different, the number of the acquired SCPR probe images is also different, the number of the images before encoding is fixed to N through linear interpolation, and then N two-dimensional images are processed through an encoder to obtain an image vector of N multiplied by M dimensions.
Position encoder: for adding position embedding vectors to represent the relative and absolute position information of each position in the input sequence.
An encoder: the method comprises the steps that the method comprises a plurality of coding layers, each coding layer comprises a multi-head self-attention mechanism and a feedforward fully-connected network, the self-attention mechanism can pay attention to the dependency relationship between different positions in a sequence at the same time, and feature extraction can be carried out from different subspaces through the multi-head mechanism; the feedforward fully-connected network is responsible for nonlinear transformation of the features.
Normalization layer: for normalizing the output of the coding layer, such as Layer Normalization or Batch Normalization.
A classifier: a linear layer is connected after the coding layer, and the output of the coding layer is mapped to the predictive probabilities of four signs.
6. And (3) carrying out model pre-training and model fine-tuning on the constructed coronary vulnerable plaque identification model through a natural image data set, and then initializing the model by using trained parameters, and retraining on the vulnerable plaque data set.
7. Inputting the image converted in the step 4 into the coronary vulnerable plaque recognition model trained in the step 6, and outputting the probability of each sign (positive reconstruction, low density, napkin ring and punctiform calcification) of vulnerable plaque. And setting probability threshold values for different symptoms, if the probability output by a certain symptom model is greater than or equal to the threshold value, the model is considered to recognize the symptom, if the model recognizes two or more symptoms, the plaque is considered to be vulnerable plaque, otherwise, the plaque is not vulnerable plaque.
In another embodiment of the present invention, a CCTA image-based coronary artery vulnerable plaque identification system is provided, the system is used for implementing the CCTA image-based coronary artery vulnerable plaque identification method described above, the system includes a blood vessel segmentation and segmentation unit, a blood vessel centerline extraction unit, a plaque detection unit, an image conversion unit and an identification unit, wherein the blood vessel segmentation and segmentation unit is used for performing segmentation and segmentation of blood vessels on an original coronary artery image; the blood vessel central line extraction unit is used for extracting a segmented blood vessel central line to obtain an SCPR image; the plaque detection unit is used for carrying out plaque detection on each segment of blood vessel in the SCPR image; the image conversion unit is used for converting each layer of three-dimensional probe image into a common picture format in the plaque range; the identification unit is used for obtaining the vulnerable plaque identification result by the coded image through the coronary vulnerable plaque identification model.
In a third embodiment of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing a CCTA image-based coronary vulnerable plaque identification method as described above when executing the computer program.
A fourth embodiment of the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program for implementing a CCTA image based coronary vulnerable plaque identification method as described above when executed by a processor.
While the invention has been described in detail in the foregoing general description and with reference to specific embodiments thereof, it will be apparent to one skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (10)
1. A coronary vulnerable plaque identification method based on CCTA images is characterized by comprising the following steps:
s1, segmenting blood vessels of an original coronary artery image;
s2, extracting a central line of the segmented blood vessel to obtain an SCPR image;
s3, carrying out plaque detection on each segment of blood vessel based on the SCPR image;
s4, converting images;
s5, constructing a coronary vulnerable plaque identification model and carrying out model training;
s6, inputting the converted image into a trained model to obtain a vulnerable plaque recognition result.
2. The CCTA image-based coronary artery vulnerable plaque identification method of claim 1, wherein S2 is specifically: and (3) extracting a central line of the segmented vascular mask of the S1 by using a skeletonizing algorithm, and obtaining an SCPR image based on a CPR curved surface reconstruction technology.
3. The CCTA image-based coronary artery vulnerable plaque identification method of claim 1, wherein S1 is specifically: inputting an original coronary artery image into an existing coronary artery segmentation model to obtain segmented vascular masks; the step S3 is specifically as follows: plaque detection is carried out in the central point area by the developed plaque detection model on the SCPR image of each blood vessel segment to obtain the plaque on the blood vessel, and the position of the starting central point and the position of the ending central point represent the range of each plaque.
4. The CCTA image-based coronary artery vulnerable plaque identification method of claim 1, wherein the image conversion in S4 is specifically: and mapping the pixel value of each layer of three-dimensional probe image to a common picture format in the plaque range, wherein the third dimension is 1.
5. The CCTA image-based coronary vulnerable plaque identification method of claim 1, wherein the coronary vulnerable plaque identification model in S5 is constructed based on a ViT model, and the specific structure thereof is as follows:
an input encoder: the method comprises the steps of dividing an input image into a group of image blocks with fixed sizes, and then extracting features of each image block through a convolutional neural network CNN to obtain a group of vector representations serving as an input sequence;
position encoder: adding a position embedding vector to represent relative and absolute position information for each position in the input sequence;
an encoder: each coding layer comprises a multi-head self-attention mechanism and a feedforward full-connection network; the self-attention mechanism can pay attention to the dependency relationship between different positions in the sequence at the same time, and the characteristic extraction can be carried out from different subspaces through the multi-head mechanism; the feedforward full-connection network is responsible for nonlinear transformation of the characteristics;
normalization layer: the method is used for carrying out normalization processing on the output of the coding layer;
a classifier: a linear layer is connected after the coding layer, and the output of the coding layer is mapped to the predictive probabilities of four signs.
6. The CCTA image-based coronary vulnerable plaque identification method of claim 1, wherein the model training process of S7 is: pre-training and model fine tuning is performed through the natural image dataset, the model is initialized with trained parameters, and then retrained on the vulnerable plaque dataset.
7. The CCTA image-based coronary artery vulnerable plaque identification method of claim 1, wherein the specific process of obtaining vulnerable plaque identification results in S7 is: first, the model will output four signs of vulnerable plaque: positive reconstruction, low density, napkin ring and punctiform calcification, and obtaining the identification result of the sign according to different probabilities, and then obtaining the identification result of vulnerable plaque according to whether two or more signs are identified, if two or more signs exist, the vulnerable plaque is considered, otherwise, the vulnerable plaque is not vulnerable plaque.
8. A CCTA image-based coronary artery vulnerable plaque identification system, which is characterized in that the system is used for realizing the CCTA image-based coronary artery vulnerable plaque identification method according to any one of claims 1-7, and comprises a blood vessel segmentation and segmentation unit, a blood vessel center line extraction unit, a plaque detection unit, an image conversion unit and an identification unit; the blood vessel segmentation and sectioning unit is used for segmenting and sectioning the blood vessel of the original coronary artery image; the blood vessel central line extraction unit is used for extracting a segmented blood vessel central line to obtain an SCPR image; the plaque detection unit is used for carrying out plaque detection on each segment of blood vessel in the SCPR image; the image conversion unit is used for converting each layer of three-dimensional probe image into a common picture format in the plaque range; the identification unit is used for obtaining a vulnerable plaque identification result by passing the converted image through a coronary vulnerable plaque identification model.
9. An electronic device, characterized in that: a computer program comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the CCTA image-based coronary vulnerable plaque identification method of any one of claims 1-7 when the computer program is executed.
10. A non-transitory computer readable storage medium characterized by: the medium has stored thereon a computer program for implementing a CCTA image-based coronary vulnerable plaque identification method as claimed in any of claims 1-7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311473400.XA CN117455878A (en) | 2023-11-08 | 2023-11-08 | CCTA image-based coronary vulnerable plaque identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311473400.XA CN117455878A (en) | 2023-11-08 | 2023-11-08 | CCTA image-based coronary vulnerable plaque identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117455878A true CN117455878A (en) | 2024-01-26 |
Family
ID=89583326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311473400.XA Pending CN117455878A (en) | 2023-11-08 | 2023-11-08 | CCTA image-based coronary vulnerable plaque identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117455878A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110074756A (en) * | 2013-12-18 | 2019-08-02 | 哈特弗罗公司 | For the system and method according to the specific anatomical image data prediction coronary plaque vulnerability of patient |
| CN110222759A (en) * | 2019-06-03 | 2019-09-10 | 中国医科大学附属第一医院 | A kind of Plaque Vulnerability in Coronary Artery automatic recognition system |
| CN113486990A (en) * | 2021-09-06 | 2021-10-08 | 北京字节跳动网络技术有限公司 | Training method of endoscope image classification model, image classification method and device |
| CN114387464A (en) * | 2021-12-01 | 2022-04-22 | 杭州脉流科技有限公司 | Vulnerable plaque identification method based on IVUS image, computer device, readable storage medium and program product |
| CN116977352A (en) * | 2023-07-26 | 2023-10-31 | 上海联影智能医疗科技有限公司 | Plaque segmentation method, plaque segmentation apparatus and computer readable storage medium |
-
2023
- 2023-11-08 CN CN202311473400.XA patent/CN117455878A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110074756A (en) * | 2013-12-18 | 2019-08-02 | 哈特弗罗公司 | For the system and method according to the specific anatomical image data prediction coronary plaque vulnerability of patient |
| CN110222759A (en) * | 2019-06-03 | 2019-09-10 | 中国医科大学附属第一医院 | A kind of Plaque Vulnerability in Coronary Artery automatic recognition system |
| CN113486990A (en) * | 2021-09-06 | 2021-10-08 | 北京字节跳动网络技术有限公司 | Training method of endoscope image classification model, image classification method and device |
| CN114387464A (en) * | 2021-12-01 | 2022-04-22 | 杭州脉流科技有限公司 | Vulnerable plaque identification method based on IVUS image, computer device, readable storage medium and program product |
| CN116977352A (en) * | 2023-07-26 | 2023-10-31 | 上海联影智能医疗科技有限公司 | Plaque segmentation method, plaque segmentation apparatus and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shamshad et al. | Transformers in medical imaging: A survey | |
| Zreik et al. | Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis | |
| Zreik et al. | Deep learning analysis of coronary arteries in cardiac CT angiography for detection of patients requiring invasive coronary angiography | |
| Biffi et al. | Explainable anatomical shape analysis through deep hierarchical generative models | |
| Cong et al. | BCS-Net: Boundary, context, and semantic for automatic COVID-19 lung infection segmentation from CT images | |
| Zhang et al. | Multi-task learning with multi-view weighted fusion attention for artery-specific calcification analysis | |
| Cao et al. | A robust shape-aware rib fracture detection and segmentation framework with contrastive learning | |
| CN116862877A (en) | Scanning image analysis system and method based on convolutional neural network | |
| WO2022086910A1 (en) | Anatomically-informed deep learning on contrast-enhanced cardiac mri | |
| US20220138936A1 (en) | Systems and methods for calcium-free computed tomography angiography | |
| CN112617770A (en) | Intracranial aneurysm risk prediction method based on artificial intelligence and related device | |
| Salahuddin et al. | Multi-resolution 3d convolutional neural networks for automatic coronary centerline extraction in cardiac CT angiography scans | |
| CN114511581A (en) | Multi-task multi-resolution collaborative esophageal cancer lesion segmentation method and device | |
| Dong et al. | A novel end‐to‐end deep learning solution for coronary artery segmentation from CCTA | |
| KR102436035B1 (en) | Apparatus and method for diagnosing skeletal muscle condition from ultrasound images using deep neural network | |
| Yang et al. | Lesion classification of wireless capsule endoscopy images | |
| CN117455878A (en) | CCTA image-based coronary vulnerable plaque identification method and system | |
| CN115294023A (en) | Liver tumor automatic segmentation method and device | |
| Hou et al. | Boosting Ultrasonic Image Classification via Self-Supervised Representation Learning | |
| Zhang et al. | An Anatomy-and Topology-Preserving Framework for Coronary Artery Segmentation | |
| CN111598870A (en) | Method for calculating coronary artery calcification ratio based on convolutional neural network end-to-end reasoning | |
| Wu et al. | A multi-stage DCNN method for liver tumor segmentation | |
| Van Herten et al. | Automatic Coronary Artery Plaque Quantification and CAD-RADS Prediction using Mesh Priors | |
| CN116740041B (en) | CTA scanning image analysis system and method based on machine vision | |
| CN116994067B (en) | Method and system for predicting fractional flow reserve based on coronary artery calcification |
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 |