Automatic coronary artery Syntax scoring method and system based on coronary artery CTA

Abstract

The invention discloses an automatic coronary artery Syntab scoring method and system based on coronary artery CTA, and relates to the technical field of medical image processing and intelligent diagnosis, and the method comprises the steps: obtaining the image data of a patient, and uploading the image data to a coronary artery automatic processing platform; the coronary artery automatic processing platform automatically identifies coronary artery advantage types; coronary artery segments are identified, and segment weight factors are calculated; automatically identifying plaque segments, and determining a stenosis degree multiplication factor; identifying undesirable feature factors of the plaques, and recording scores; calculating a lesion score based on the segment weight factor and the stenosis degree multiplication factor; a total score is calculated based on the lesion score and the score of the plaque undesirable feature factor. According to the method, the computer technology and the artificial intelligence algorithm are introduced, the coronary artery anatomical features are combined, the blood flow weight factors are given to different blood vessel segments, the actual influence of lesions on the health of the patient is scientifically quantified, the limitation that a traditional method is only based on simple classification scoring is overcome, and the scoring accuracy and individuation degree are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing and intelligent diagnosis, and in particular to an automated coronary artery Syntax scoring method based on coronary CTA. Background Art

[0002] In the field of diagnosis and treatment of coronary artery disease (CAD), coronary angiography (CAG) is widely used to assess the degree of coronary artery stenosis. However, traditional CAG is an invasive method with certain risks and high costs, which limits its widespread application in clinical screening. Coronary CT angiography (CTA), as a non-invasive imaging technology, has gradually gained attention in the initial diagnosis of CAD in recent years. Although CTA can provide anatomical information of the coronary arteries, the accuracy of CTA diagnosis alone is still limited due to the lack of functional evaluation. The current study introduced the coronary artery fractional flow reserve (FFR) technology based on CCTA, and realized automatic image analysis through deep learning and artificial intelligence algorithms to evaluate the functional significance of stenosis. However, these methods still have many shortcomings in clinical application. The accuracy and consistency of the automated scoring system are easily affected by image quality, noise and algorithm performance; the existing algorithms have large computational complexity and complex operation, making it difficult to achieve efficient clinical application; at the same time, the existing technology cannot fully consider the individual differences of patients in risk assessment. In addition, manual Syntax scoring, as a traditional method for assessing the severity of coronary heart disease, relies on the experience and judgment of professional physicians, and is mainly characterized by strong subjectivity, long time consumption, and a long learning curve.

[0003] Therefore, the existing technology has obvious deficiencies in accuracy, personalization, efficiency and consistency. An improved automated coronary syndrome scoring method is urgently needed to overcome the limitations of manual scoring and meet the clinical needs for rapid and objective CAD risk assessment. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the present invention proposes an improved automated coronary Syntax scoring method in view of the limitations of the traditional coronary Syntax scoring method, such as strong subjectivity, long time consumption, long learning curve, etc., and the deficiencies of the existing automated scoring system based on CTA and artificial intelligence algorithms in terms of image quality, noise interference, algorithm performance, computational complexity, and personalized evaluation. The method aims to improve the accuracy, consistency, and efficiency of the scoring, while fully considering the personalized differences of patients, and meeting the clinical demand for rapid and objective assessment of coronary heart disease risk.

[0006] To solve the above technical problems, the present invention provides the following technical solution: an automated coronary artery Syntax scoring method based on coronary CTA, comprising the following steps:

[0007] Acquire patient image data and upload them to the coronary automated processing platform; the coronary automated processing platform automatically identifies the dominant type of coronary arteries; identifies coronary artery segments and calculates segment weight factors; automatically identifies plaque segments and determines stenosis multiplication factors; identifies plaque adverse characteristic factors and records scores; calculates lesion scores based on segment weight factors and stenosis multiplication factors; and calculates total scores based on lesion scores and scores of plaque adverse characteristic factors.

[0008] As a preferred embodiment of the automated coronary artery Syntax scoring method based on coronary CTA described in the present invention, the coronary artery dominance type is divided into left-side dominance and right-side dominance.

[0009] As a preferred embodiment of the automated coronary artery Syntax scoring method based on coronary CTA described in the present invention, the coronary artery segments are identified based on the coronary artery dominant type and the segment weight factor is calculated.

[0010] As a preferred embodiment of the automated coronary artery Syntax scoring method based on coronary CTA described in the present invention, the determination of the stenosis degree multiplication factor includes that if the stenosis rate is greater than 50% and less than or equal to 99%, the stenosis degree multiplication factor is 2; if the stenosis rate is equal to 100%, the stenosis degree multiplication factor is 5.

[0011] As a preferred embodiment of the automated coronary artery Syntax scoring method based on coronary CTA described in the present invention, the factors for identifying adverse plaque characteristics include factors that can be automatically identified and factors that require manual identification.

[0012] As a preferred embodiment of the automated coronary artery Syntax scoring method based on coronary CTA described in the present invention, wherein: the calculated lesion score is expressed as,

[0013] S=W×D

[0014] Wherein, W represents the segment weight factor, and D represents the stenosis multiplication factor.

[0015] As a preferred embodiment of the automated coronary artery Syntax scoring method based on coronary CTA described in the present invention, wherein: the calculated total score is expressed as,

[0016] X=S+V

[0017] Where V represents the score of the adverse plaque characteristic factor.

[0018] Another object of the present invention is to provide an automated coronary artery Syntax scoring system based on coronary CTA, which can automatically identify coronary segments, plaque characteristics and stenosis degree, calculate coronary artery Syntax scores and generate personalized risk assessment reports, thereby solving the problems of existing scoring methods that are highly subjective, time-consuming, difficult to achieve efficient consistency analysis and lack of personalized assessment capabilities.

[0019] To solve the above technical problems, the present invention provides the following technical solutions: an automated coronary artery Syntax scoring system based on coronary CTA, comprising an image data acquisition and upload module, a coronary artery automated processing module, a lesion score calculation module and a total score calculation module.

[0020] The image data acquisition and upload module is responsible for receiving the patient's coronary CTA image data and uploading it to the coronary automation processing platform.

[0021] The coronary artery automation processing module automatically analyzes coronary CTA images, completes coronary artery dominant type identification, automatic coronary artery segment identification and segment weight factor calculation, plaque identification and stenosis multiplication factor calculation, and plaque adverse characteristic factor identification and scoring.

[0022] The lesion score calculation module calculates the lesion score based on the segment weight factor and the stenosis degree multiplication factor.

[0023] The total score calculation module calculates the final Syntax total score based on the lesion score and the score of the plaque adverse characteristic factor.

[0024] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the automated coronary artery Syntax scoring method based on coronary CTA as described above are implemented.

[0025] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the automated coronary artery Syntax scoring method based on coronary CTA as described above.

[0026] Beneficial effects of the present invention: The present invention introduces computer technology and artificial intelligence algorithms, combines coronary anatomical features, assigns blood flow weight factors to different vascular segments, and scientifically quantifies the actual impact of lesions on patient health, overcoming the limitations of traditional methods based only on simple classification scores, significantly improving the accuracy and personalization of scores, and providing more practical quantitative basis for clinical diagnosis and treatment. At the same time, the present invention realizes the full automation of the scoring process, from image data processing to lesion identification and score calculation, which are all completed by the system, significantly reducing subjective interference, improving scoring efficiency and consistency, and meeting the clinical needs for rapid, accurate, and objective coronary heart disease risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0028] Figure 1 This is an overall flow chart of the automated coronary artery Syntax scoring method based on coronary CTA provided in the first embodiment of the present invention.

[0029] Figure 2 This is a display diagram of the right dominant type in the automated coronary artery Syntax scoring method based on coronary CTA provided in the first embodiment of the present invention.

[0030] Figure 3 This is a left-side dominant type display diagram of the automated coronary artery Syntax scoring method based on coronary CTA provided in the first embodiment of the present invention.

[0031] Figure 4 The weight factors of different left-dominant coronary artery segments in the automated coronary artery Syntax scoring method based on coronary CTA provided in the first embodiment of the present invention.

[0032] Figure 5 The weight factors of different right-dominant coronary artery segments in the automated coronary artery Syntax scoring method based on coronary CTA provided in the first embodiment of the present invention.

[0033] Figure 6 This is an overall framework diagram of an automated coronary artery Syntax scoring system based on coronary CTA provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0035] Example 1, reference Figure 1 to Figure 5 , is an embodiment of the present invention, providing an automated coronary artery Syntax scoring method based on coronary CTA, characterized in that:

[0036] S1: Obtain patient image data and upload it to the coronary automated processing platform.

[0037] S2: The coronary artery automated processing platform automatically identifies the coronary artery dominant type.

[0038] The types of coronary artery dominance are divided into left-sided dominance and right-sided dominance.

[0039] Specifically, Figure 2 The figure shows the right-side dominant type. The posterior descending branch originates from the right coronary artery (segment 4), that is, the posterior interventricular groove is completely supplied by the right coronary artery or by the right coronary artery and the circumflex branch.

[0040] like Figure 3 The figure shows the left-side dominant type. The posterior descending branch originates from the left coronary artery (segment 15), that is, the posterior interventricular groove is completely supplied by the circumflex branch. There is no balanced coronary artery option in the SYNTAX score.

[0041] S3: Identify coronary artery segments and calculate segment weight factors.

[0042] The coronary segments are identified based on the coronary artery dominance type and segment weight factors are calculated.

[0043] Specifically, Figure 4 As shown in the figure, it is the weight factor of different coronary artery segments of the left dominant type, such as Figure 5 Shown are the weight factors of different coronary artery segments of the right-sided dominant type.

[0044] S4: Automatically identify plaque segments and determine the stenosis multiplication factor.

[0045] Determining the stenosis degree multiplication factor includes: if the stenosis rate is greater than 50% and less than or equal to 99%, the stenosis degree multiplication factor is 2; if the stenosis rate is equal to 100%, the stenosis degree multiplication factor is 5.

[0046] The basis of the Syntax scoring system is the need to accurately identify 18 branch blood segments and the 3D spatial position relationship between plaques and each branch vessel segment. Compared with traditional 2D DSA angiography, it has incomparable advantages. Coronary CTA can provide a more complete 3D vascular network image, which helps to more accurately identify and name vascular branches. Traditional 2D DSA may not provide enough depth information, resulting in inaccurate identification and naming of vascular branches. 3D CTA can clearly display the three-dimensional structure of blood vessels through three-dimensional reconstruction technology, making the identification and naming of vascular branches more intuitive and accurate. At the same time, based on 3D CTA scanning images, deep learning technology can be used to perform high-precision 3D segmentation and reconstruction of vascular lumen and plaques, which is very necessary for the accurate measurement of 3D spatial position relationship. For example, some definitions of branch vessel lesions in the Syntax score require that the lesion plaque is within a certain distance from the vascular bifurcation, such as within 10 mm, and for example, aortic ostium lesions require that the lesion is within 3 mm of the aortic ostium.

[0047] S5: Calculate the lesion score based on the segment weight factor and the stenosis degree multiplication factor.

[0048] The lesion score was calculated as,

[0049] S=W×D

[0050] Wherein, W represents the segment weight factor, and D represents the stenosis multiplication factor.

[0051] Specifically, lesions were defined as coronary vessels with a diameter of ≥1.5 mm and a visual stenosis of ≥50% in the lumen diameter, and each lesion was scored.

[0052] Each lesion may involve ≥1 diseased segment.

[0053] If consecutive stenoses are separated by less than 3 vessel reference diameters, they should be scored as one lesion. However, stenoses that are more than 3 vessel reference diameters apart are considered separate lesions.

[0054] S6: Identify plaque adverse characteristic factors and record the scores.

[0055] Identification of adverse plaque characteristic factors includes factors that can be automatically identified and factors that require manual identification.

[0056] Furthermore, coronary CTA can calculate the 3D tortuosity of blood vessels, which is very important for evaluating the pathological state of blood vessels. For example, increased vascular tortuosity may be associated with diseases such as atherosclerosis. 3D CTA can more accurately evaluate the tortuosity of blood vessels by calculating the difference between the centerline of the blood vessel and the actual path, while 2D DSA is difficult to perform such analysis due to the lack of depth information. The calculation of the adverse feature of severely tortuous lesions in the Syntax score requires information on the curvature of the blood vessels in 3D space, which cannot be provided on DSA.

[0057] Coronary CTA can also calculate 3D bifurcation angles, which is important for assessing the risk of branch vessel occlusion during interventional treatment of coronary bifurcation lesions. 3D reconstruction can provide more accurate bifurcation angle measurements, while 2D DSA may not accurately reflect the three-dimensional spatial relationship of the vessels.

[0058] Coronary CTA can more accurately assess the 3D proportion of calcified plaques in the lumen. The 3D distribution of calcified plaques is crucial for the selection of interventional treatment strategies. 3D CTA can provide detailed information on the volume and distribution of calcified plaques, while 2DDSA can only provide a two-dimensional projection of calcified plaques and cannot accurately reflect their three-dimensional proportion in the lumen.

[0059] Specifically, the adverse feature scores of coronary artery lesions are shown in Table 1.

[0060] Table 1

[0061]

[0062]

[0063] Among them, complete occlusion is TIMI blood flow grade 0.

[0064]

[0065] S7: A total score was calculated based on the lesion score and the score of the plaque adverse characteristic factor.

[0066] The total score is calculated as,

[0067] X=S+V

[0068] Where V represents the score of the adverse plaque characteristic factor.

[0069] By using computer technology and artificial intelligence algorithms, combined with the actual coronary anatomy, weight factors are assigned to blood flow in different vascular segments to reflect the actual impact of the diseased segments. The traditional coronary scoring method only performs a simple binary classification score based on the coronary artery type, which cannot accurately reflect the patient's actual lesion condition. By adding the re-scoring of blood flow weight factors, this system can more scientifically and reasonably quantify the specific impact of lesions on patients' health, making the scoring more accurate and personalized, and providing a more practical reference for clinical diagnosis and treatment.

[0070] Example 2, reference Figure 6 , which is an embodiment of the present invention, provides a system for an automated coronary artery Syntax scoring method based on coronary CTA, characterized in that it includes an image data acquisition and upload module 100, a coronary artery automated processing module 200, a lesion score calculation module 300 and a total score calculation module 400.

[0071] The image data acquisition and upload module 100 is responsible for receiving the patient's coronary CTA image data and uploading it to the coronary automation processing platform.

[0072] The coronary artery automation processing module 200 automatically analyzes the coronary CTA images, completes the recognition of the dominant type of coronary arteries, the automatic recognition of coronary artery segments and the calculation of segment weight factors, the recognition of plaques and the calculation of stenosis multiplication factors, and the recognition and recording of plaque adverse characteristic factors.

[0073] The lesion score calculation module 300 calculates the lesion score based on the segment weight factor and the stenosis degree multiplication factor.

[0074] The total score calculation module 400 calculates the final Syntax total score based on the lesion score and the score of the plaque adverse characteristic factor.

[0075] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0076] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0077] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0078] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0079] Embodiment 3, in this embodiment, in order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0080] Specifically, DSA confirmed that patient 1 had a stenosis rate of >50% and a complex lesion. After a coronary CTA examination, the images were uploaded to the Shukun post-processing platform. The coronary artery type was identified as "right-sided dominant type", and the vessels were segmented and named according to the AHA classification of the coronary artery tree. Lesions were identified and the vascular stenosis rate was automatically analyzed at >50%. The patient had four lesions, located in the distal anterior descending branch (dLAD), the first diagonal branch (D1), the proximal circumflex branch (pCx), and the proximal right coronary artery (pRCA). The stenosis rates were all moderate or above, and the stenosis multiplication factors were all 2. Before re-scoring, the weights of each segment were dLAD: 1, D1: 1, pCx: 1.5, and pRCA: 1. Identify adverse vascular features. The patient had bifurcation lesions (+2), severe calcification (+2), and lesion length >20mm (+1). The total score was calculated as follows: X = 1×2+1×1+1.5×2+1×2+2+2+1=13, which is a low-risk group (<22). However, the patient's dLAD was relatively long and D1 was thin. After recalculating the score based on the actual distribution of blood flow, the results were dLAD: 1.7, D1: 0.3. After recalculation, X' = 1.7×2+0.3×1+1.5×2+1×2+2+2+1=13.7, which is a low-risk group. The automated scoring process took 43 seconds. At the same time, the patient underwent manual Syntax scoring, which took 103 seconds.

[0081] Patient 2 was confirmed by DSA to have a stenosis rate of >50% and a complex lesion with occluded vessels. After coronary CTA examination, the images were uploaded to the Shukun post-processing platform. The coronary artery type was identified as "right dominant type", and the vessels were segmented and named according to the AHA classification of the coronary artery tree. Lesions were identified and the vascular stenosis rate was >50% was automatically analyzed. The patient had 4 lesions, lesion 1 involved 2 segments: the proximal segment of the anterior descending branch and the first diagonal branch (mLAD, D1), and the other 3 involved the proximal segment of the circumflex branch (pCx), the middle segment of the right coronary artery (mRCA), and the posterior descending branch (PDA), of which pCx was completely occluded with a stenosis multiplication factor of 5. Before re-scoring, the weights of each segment were mLAD: 2.5, D1: 1, pCx: 1.5, pRCA: 1, and PDA: 1. Adverse factors at the occluded lesions (+3). The total score was calculated as follows: X = 2.5 × 2 + 1 × 2 + 1.5 × 5 + 1 × 2 + 1 × 2 + 3 = 21.5, which is the low-risk group. After recalculating the score according to the actual distribution of blood flow, mLAD: 3.5, D1: 1.2, PDA: 1.5. After recalculation, X' = 3.5 × 2 + 1.2 × 2 + 1.5 × 5 + 1 × 2 + 1.5 × 2 + 3 = 24.9, which is the medium-risk group (22-32). The automated scoring process took 50 seconds. At the same time, the patient underwent manual Syntax scoring, which took 203 seconds.

[0082] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An automated coronary artery Syntax scoring method based on coronary CTA, characterized in that: include: Obtain patient image data and upload it to the coronary automated processing platform; The coronary artery automated processing platform automatically identifies the dominant type of coronary artery; Identify coronary segments and calculate segment weight factors; Automatically identify plaque segments and determine the stenosis multiplication factor; Identify adverse plaque characteristic factors and record scores; The lesion score was calculated based on the segment weight factor and the stenosis degree multiplication factor; A total score was calculated based on the lesion score and the score of the plaque adverse characteristics factor.

2. The automated coronary artery Syntax scoring method based on coronary CTA according to claim 1, characterized in that: The coronary artery dominance types are divided into left-side dominance and right-side dominance.

3. The automated coronary artery Syntax scoring method based on coronary CTA according to claim 2, characterized in that: The coronary segments are identified based on the coronary artery dominance type and segment weight factors are calculated.

4. The automated coronary artery Syntax scoring method based on coronary CTA according to claim 3, characterized in that: The determination of the stenosis degree multiplication factor includes: if the stenosis rate is greater than 50% and less than or equal to 99%, the stenosis degree multiplication factor is 2; if the stenosis rate is equal to 100%, the stenosis degree multiplication factor is 5.

5. The automated coronary artery Syntax scoring method based on coronary CTA according to claim 4, characterized in that: The identification of plaque adverse characteristic factors includes factors that can be automatically identified and factors that require manual identification.

6. The automated coronary artery Syntax scoring method based on coronary CTA according to claim 5, characterized in that: The calculated lesion score is expressed as, S=W×D Wherein, W represents the segment weight factor, and D represents the stenosis multiplication factor.

7. The automated coronary artery Syntax scoring method based on coronary CTA according to claim 6, characterized in that: The calculated total score is expressed as, X=S+V Where V represents the score of the adverse plaque characteristic factor.

8. A system using the automated coronary artery Syntax scoring method based on coronary CTA as claimed in any one of claims 1 to 7, characterized in that: It comprises an image data acquisition and uploading module (100), a coronary artery automation processing module (200), a lesion score calculation module (300) and a total score calculation module (400); The image data acquisition and upload module (100) is responsible for receiving the patient's coronary CTA image data and uploading it to the coronary automation processing platform; The coronary artery automated processing module (200) automatically analyzes the coronary artery CTA images, completes the recognition of the dominant type of coronary arteries, the automatic recognition of coronary artery segments and the calculation of segment weight factors, the recognition of plaques and the calculation of stenosis multiplication factors, and the recognition and recording of plaque adverse characteristic factors. The lesion score calculation module (300) calculates the lesion score based on the segment weight factor and the stenosis degree multiplication factor; The total score calculation module (400) calculates the final Syntax total score based on the lesion score and the score of the plaque adverse characteristic factor.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the automated coronary artery Syntax scoring method based on coronary CTA according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automated coronary artery Syntax scoring method based on coronary CTA according to any one of claims 1 to 7 are implemented.

Images