Method, apparatus, and electronic device for evaluating the state of coronary artery plaque

Abstract

The present invention provides a method, device, electronic device, and computer-readable storage medium for evaluating the state of coronary plaque. The method for evaluating the state of coronary plaque includes the steps of: providing an optical coherence tomography image of a coronary plaque to be evaluated (S1); identifying the optical coherence tomography image and determining fibrous components and lipid plaque (S2); and evaluating the state of the coronary plaque based on the lipid load of the fibrous components and lipid plaque (S3). According to the method for evaluating the state of coronary plaque of an embodiment of the present invention, a tomography image of a blood vessel to be evaluated is obtained by an optical coherence tomography imaging technique, and the fibrous components and lipid plaque therein are identified based on the obtained tomography image. Based on the size of the identified fibrous components and lipids, the state of the coronary plaque is evaluated comprehensively, so that a quantitative evaluation can be realized and the repeatability is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of medical imaging, and in particular, to a method, apparatus, electronic device, and computer-readable storage medium for evaluating the state of coronary artery plaques.

Background Art

[0002] Cardiogenic death is currently the most major cause of death among people. In particular, acute coronary syndrome caused by unstable plaques in the coronary arteries is a major factor among them. Therefore, early detection of the stable state of plaques in patients with coronary artery disease is extremely important for determining the treatment plan of the patients and evaluating the long-term prognosis.

[0003] Intracoronary imaging technology is the main means for evaluating the stable state of intracoronary plaques in current coronary artery disease patients. Among them, intravascular ultrasound (IVUS) and near-infrared spectroscopy (NIRS) technologies can evaluate the depth of plaque size, but the imaging mechanism itself still limits the clear classification and comprehensive evaluation of each component of the plaque.

[0004] Optical coherence tomography (OCT) imaging technology has unique advantages in evaluating coronary artery plaques due to its relatively high resolution. However, since there is a limit to the depth of its scanning, there are defects in the complete imaging of the entire plaque. In addition, OCT imaging technology can clearly display the thickness of the fibrous capsule of coronary artery plaques, but due to the cause of optical attenuation, it cannot display the actual size of the lipid component within the plaque. Currently, in clinical practice, based on OCT imaging technology, only the evaluation standard of fibrous capsule thickness <65 μm and lipid angle ≥ 180° can be used as the evaluation standard for unstable plaques, ignoring the proven important related element of the size of the lipid component in the stable state. Therefore, the above evaluation standard is not accurate enough.

[0005] Therefore, it is necessary to develop a more accurate evaluation method.

Summary of the Invention

[0006] The inventors repeated the research and proved through pathological and clinical studies that both the composition of the plaque itself, i.e., the thickness of the fibrous capsule of the plaque and the size of the lipid, etc., determine the stability of the plaque, and thus completed the present invention.

[0007] In view of this, the present invention provides a method for evaluating the state of a coronary plaque that comprehensively considers the fibrous capsule and lipid components of the plaque and more accurately evaluates the stable state of the plaque.

[0008] In addition, the present invention provides an apparatus for evaluating the state of a coronary plaque that comprehensively considers the fibrous capsule and lipid components of the plaque and more accurately evaluates the stable state of the plaque.

[0009] Furthermore, the present invention provides an electronic device capable of executing the method for evaluating the state of a coronary plaque according to the present invention.

[0010] Moreover, the present invention further provides a computer-readable storage medium, in which computer program instructions are stored, and when the computer program instructions are executed by a processor, the processor executes the method for evaluating the state of a coronary plaque according to the present invention.

[0011] To solve the above technical problems, the present invention uses the following technical means.

[0012] The method for evaluating the state of a coronary plaque according to an embodiment of the first aspect of the present invention includes: step S1 of obtaining an optical coherence tomography image of a coronary plaque waiting to be evaluated; step S2 of identifying the optical coherence tomography image and determining the fibrous component and lipid plaque; step S3 of evaluating the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque.

[0013] Furthermore, step S3 includes: Step S31 of calculating the thickness of the fibrous capsule covering the surface of the lipid plaque and the lipid load of the lipid plaque among the fiber components, respectively; Step S32 of determining the state of the coronary plaque based on the thickness of the fibrous capsule and the lipid load, and includes.

[0014] Furthermore, in step S32, Step S321 of calculating a lipid capsule ratio by the following formula based on the lipid load and the thickness of the fibrous capsule; Lipid capsule ratio (LCR) = lipid load / thickness of fibrous capsule Step S322 of evaluating the state of the coronary plaque based on the lipid capsule ratio. According to some embodiments of the present invention, in step S1, for the optical coherence tomography image of the target frame, continuous images of several frames before and after the frame image are respectively obtained. In step S31, the thickness of the fibrous capsule and the lipid load of the fiber components of the optical coherence tomography images of a plurality of consecutive frames are respectively calculated, and the median value of the thickness of the fibrous capsule and the average value of the lipid load of the optical coherence tomography images of the plurality of frames are determined. In step S321, the lipid capsule ratio is calculated using the average value of the lipid load and the median value of the thickness of the fibrous capsule. In step S322, the maximum lipid capsule ratio obtained by calculating for the entire plaque is used as the lipid capsule ratio of the coronary plaque, and the state of the coronary plaque is evaluated.

[0015] Furthermore, in step S322, when the lipid capsule ratio is equal to or greater than the first threshold value, it is determined that the coronary plaque is an unstable plaque.

[0016] Note that, since the units used for lipid load and the thickness of the fibrous capsule are different, the LCR values will correspondingly change, and accordingly, the first threshold value will also change. For example, when the lipid load is expressed as a percentage and the thickness of the fibrous capsule is in μm units, based on a large number of experimental results, the first threshold value may be set to 0.33, for example. Further, in step S322, in addition to the lipid capsule ratio, the state of the coronary plaque may be evaluated in association with the blood flow reserve ratio.

[0017] Furthermore, the blood flow reserve ratio is the blood flow reserve ratio obtained based on the optical coherence tomography image. In step S322, when the lipid capsule ratio is greater than or equal to the first threshold value and the blood flow reserve ratio is less than or equal to the second threshold value, it is determined that the coronary plaque is an unstable plaque.

[0018] Normally, there is a negative correlation between the blood flow reserve ratio and the lipid load of the lipid component, that is, the larger the blood flow reserve ratio, the smaller the lipid plaque load, indicating that the plaque becomes relatively stable.

[0019] Therefore, by comprehensively considering the lipid capsule ratio and the blood flow reserve ratio to evaluate the state of the plaque and linking morphology and physiological data, it becomes more accurate.

[0020] The second threshold value of the blood flow reserve ratio obtained based on the optical coherence tomography image may be set to 0.84, for example.

[0021] Note that the present application is not particularly limited to the specific numerical values of the first threshold value and the second threshold value. Needless to say, those skilled in the art can appropriately set them according to specific requirements. Further, the optical coherence tomography image is identified by a plaque identification model, and among them, the plaque identification model is obtained by deep learning based on sample training.

[0022] Specifically, for example, it is trained to identify the internal elastic lamina by a deep learning model, complemented based on the deep learning model, and the complemented lipid plaque and the fibrous component covered by the lipid plaque can be identified.

[0023] The plaque identification model obtained by training with deep learning can infer the signal loss due to optical attenuation by lipid plaques in the current layer of the OCT image from the upper and lower layer images and the previously trained data, and can more accurately analyze the magnitude of the lipid load of the lipid plaque.

[0024] The coronary plaque state evaluation device according to the embodiment of the second aspect of the present invention An image acquisition module for acquiring some optical coherence tomography images of coronary plaques awaiting evaluation, An identification module for identifying fibrous components and lipid plaques based on some of the optical coherence tomography images, An evaluation module for evaluating the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque, is provided.

[0025] The electronic device according to the embodiment of the third aspect of the present invention A processor, A memory in which computer program instructions are stored, is provided, When the computer program instructions are executed by the processor, the processor Performs step S1 of acquiring an optical coherence tomography image of a coronary plaque awaiting evaluation, Identifies the optical coherence tomography image and determines fibrous components and lipid plaques in step S2, Evaluates the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque in step S3.

[0026] The computer-readable storage medium according to the embodiment of the fourth aspect of the present invention stores computer program instructions, and when the computer program instructions are executed by a processor, the processor Step S1 of acquiring an optical coherence tomography image of a coronary plaque to be evaluated; Step S2 of identifying the optical coherence tomography image and determining a fibrous component and a lipid plaque; Step S3 of evaluating the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque is executed.

[0027] The above technical means of the present invention has at least one of the following beneficial effects.

[0028] The method for evaluating the state of a coronary plaque according to an embodiment of the present invention acquires a tomographic image of a blood vessel to be evaluated by optical coherence tomography imaging technology, and based on the acquired tomographic image, identifies the fibrous component and the lipid component therein, and based on the identified fibrous component and the size of the lipid, comprehensively evaluates the stable state of the coronary plaque, thereby realizing quantitative evaluation and having higher repeatability.

[0029] Furthermore, by comprehensively considering the thickness of the fibrous capsule and the lipid load, the state of the coronary plaque is evaluated. Therefore, compared with the prior art, the influence of the size of the lipid on the stable state is considered, and the reliability of the evaluation result is even higher.

[0030] Moreover, by introducing an evaluation index of LCR, a continuous quantitative index is provided, avoiding the diagnostic defects existing in the conventional semi-quantitative evaluation standard of binary classification.

[0031] In addition, a plaque identification model is trained by deep learning to realize full-automatic and comprehensive morphological evaluation of coronary plaques in the body, improve the reproducibility of the evaluation, reduce the subjectivity of the evaluation, and the plaque identification model trained by deep learning can infer the signal loss due to optical attenuation caused by lipid plaques in the current layer of the OCT image from the upper and lower layer images and the previously trained data, and can more accurately analyze the size of the lipid load of the lipid plaque.

[0032] In addition, by comprehensively considering the morphological index of the above LCR index and the physiological index of the blood flow reserve ratio, the positive predictive value can be effectively increased, and a better evaluation effect can be achieved.

Brief Description of the Drawings

[0033]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Modes for Carrying Out the Invention

[0034] In order to make the objectives, technical means, and advantages of the embodiments of the present invention clearer, hereinafter, with reference to the accompanying drawings of the embodiments of the present invention, the technical means of the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are some of the embodiments of the present invention, not all of them. Based on the described embodiments of the present invention, any other embodiments obtained by those skilled in the art all belong to the protection scope of the present invention.

[0035] Hereinafter, first, with reference to the accompanying drawings, a method for evaluating the state of a coronary plaque according to an embodiment of the present invention will be specifically described.

[0036] As shown in FIG. 1, the method for evaluating the state of a coronary plaque according to an embodiment of the present invention includes the following steps.

[0037] In step S1, an optical coherence tomography image of a coronary plaque waiting for evaluation is provided.

[0038] For example, it may be connected to an optical coherence tomography device to obtain a region of interest of blood vessels thereby and identify coronary plaques therein.

[0039] In step S2, the optical coherence tomography image is identified to determine the fibrous component and the lipid plaque.

[0040] After obtaining the optical coherence tomography image, by identifying it, the fibrous component and the lipid plaque are determined.

[0041] For example, the above identification may be performed on the optical coherence tomography image by a plaque identification model, and the plaque identification model may be obtained based on sample training by, for example, deep learning.

[0042] Specifically, for example, it may be trained to identify the internal elastic lamina by a deep learning model, complement it based on the deep learning model, and identify the complemented lipid plaque and the fibrous component covering the lipid plaque.

[0043] Train a plaque identification model by deep learning to realize the fully automatic and comprehensive morphological evaluation of coronary plaques in vivo, improve the repeatability of the evaluation, reduce the subjectivity of the evaluation, and the plaque identification model obtained by training by deep learning can infer the signal loss due to optical attenuation caused by lipid plaques in the current layer of the OCT image from the upper and lower layer images and the previously trained data, and can more accurately analyze the size of the lipid load of the lipid plaque.

[0044] In step S3, based on the fibrous component and the lipid load of the lipid plaque, the stable state of the coronary plaque is evaluated.

[0045] Among them, the lipid load refers to the percentage of the lipid plaque occupying the cross-sectional area of the entire blood vessel and reflects the size of the lipid.

[0046] After identifying the fibrous components and lipid plaques therein, considering that the size of the lipid is one of the factors affecting the plaque state, the evaluation method of the present invention comprehensively considers the fibrous components and the lipid load of the lipid plaques to evaluate the state of the coronary artery plaque.

[0047] Specifically, step S3 includes: step S31 of calculating the thickness of the fibrous capsule covering the surface of the lipid plaque among the fibrous components and the lipid load of the lipid component respectively; step S32 of determining the state of the coronary artery plaque based on the thickness of the fibrous capsule and the lipid load may be included.

[0048] That is, after identifying the fibrous components and the lipid plaques, the thickness of the fibrous capsule and the lipid load of the lipid plaques are calculated respectively, and then the state of the coronary artery plaque is determined based on the thickness of the fibrous capsule and the lipid load of the lipid plaque.

[0049] More specifically, step S32 includes: step S321 of calculating the lipid capsule ratio (LCR) by the following formula based on the lipid load and the thickness of the fibrous capsule; LCR = lipid load / thickness of fibrous capsule step S322 of evaluating the state of the coronary artery plaque based on the lipid capsule ratio may be included.

[0050] That is, by introducing the LCR index, the state of the coronary artery plaque is evaluated.

[0051] Here, since the units used for lipid load and the thickness of the fibrous capsule are different, the LCR value will also change accordingly, and the first threshold value will also change accordingly. For example, when the lipid load is expressed as a percentage and the thickness of the fibrous capsule is in μm units, based on a large number of experimental results, through analysis, it is found that when the lipid capsule ratio is 0.33 or more, the stability is even worse. Therefore, when the lipid capsule ratio is 0.33 or more, it may be set to determine that the coronary plaque is an unstable plaque.

[0052] In addition, in step S322, in addition to the lipid capsule ratio, the state of the coronary plaque may be evaluated in association with the blood flow reserve ratio.

[0053] Considering that the evaluation method of the present invention is an analysis performed based on an optical coherence tomography image, preferably, the blood flow reserve ratio is the blood flow reserve ratio obtained based on an optical coherence tomography video. That is, the blood flow reserve ratio is obtained by determining the blood flow velocity based on an optical coherence tomography scanner and acquiring the intracavitary structure based on an optical coherence tomography image, and calculating based on these. Thereby, in one scan, an optical coherence tomography image and a blood flow reserve ratio can be obtained, and the efficiency is even higher.

[0054] When evaluating the stable state of the coronary plaque by combining the lipid capsule ratio and the blood flow reserve ratio, from a large number of experimental results, when the lipid capsule ratio is equal to or higher than the first threshold value (for example, in the above case, the first threshold value is 0.33), and the blood flow reserve ratio is equal to or lower than the second threshold value (obviously from a large number of experimental analyses, for example, it may be 0.84), it can be determined that the coronary plaque is an unstable plaque.

[0055] Thereby, when comprehensively considering the morphological index of the LCR index and the physiological index of the blood flow reserve ratio, the sensitivity, positive predictive value, and negative predictive value can be effectively increased, and a better evaluation effect can be obtained.

[0056] As described above, according to the method for evaluating the state of a coronary plaque according to an embodiment of the present invention, based on the optical coherence tomography image of the coronary plaque to be evaluated, the fiber component and lipid plaque therein are identified, and the stability state of the coronary plaque is comprehensively evaluated based on the size of the lipid and the fiber component, so the accuracy is further improved.

[0057] As one preferred embodiment, for example, In step S1, for the optical coherence tomography image of the target frame, continuous images of several frames before and after the frame image are respectively acquired. In step S31, the thickness of the fibrous capsule and the lipid load of the fiber component of the optical coherence tomography images of a plurality of consecutive frames are respectively calculated, and the median value of the thickness of the fibrous capsule and the average value of the lipid load of the optical coherence tomography images of the plurality of frames are determined. In step S321, the lipid capsule ratio is calculated using the average value of the lipid load and the median value of the thickness of the fibrous capsule. In step S322, the maximum lipid capsule ratio calculated for the entire plaque is used as the lipid capsule ratio of the coronary plaque to evaluate the state of the coronary plaque.

[0058] That is, by combining the optical coherence tomography images of a plurality of consecutive frames to evaluate the stability state of the plaque, the influence of the identification error of the single-frame image can be reduced.

[0059] FIG. 2 shows an evaluation device 10 for the state of a coronary plaque according to an embodiment of the present invention.

[0060] As shown in FIG. 2, the evaluation device 10 for the state of a coronary plaque according to an embodiment of the present invention includes an image acquisition module 100, an identification module 200, and an evaluation module 300.

[0061] Among them, the image acquisition module 100 is for acquiring optical coherence tomography (OCT) images of coronary plaques awaiting evaluation. For example, the image acquisition module 100 is an interface for connecting an OCT scanner and receives OCT images obtained by scanning of the OCT scanner.

[0062] The identification module 200 is for identifying fiber components and lipid plaques based on some of the OCT images. The identification module 200 may be, for example, a plaque identification model formed based on sample training by deep learning.

[0063] The evaluation module 300 is for evaluating the state of the coronary plaque based on the fiber components and lipid plaques.

[0064] Among them, the evaluation module 300 includes a calculation sub-module for calculating the thickness of the fibrous capsule of the fiber component and the lipid load of the lipid plaque respectively, and a determination sub-module for determining the state of the coronary plaque based on the thickness of the fibrous capsule and the lipid load.

[0065] Furthermore, the determination sub-module calculates a lipid capsule ratio (LCR) according to the following formula based on the lipid load and the thickness of the fibrous capsule, LCR = lipid load / thickness of fibrous capsule and is used to evaluate the state of the coronary plaque based on the lipid capsule ratio.

[0066] Furthermore, the image acquisition module 100 is for acquiring, for the OCT image of the target frame, consecutive images of several frames before and after the frame image respectively. After that, the calculation sub-module in the evaluation module 300 calculates the thickness of the fibrous capsule of the fibrous component and the lipid load of the lipid plaque in the optical coherence tomography images of a plurality of consecutive frames, respectively, and determines the median value of the thickness of the fibrous capsule and the average value of the lipid load in the optical coherence tomography images of the plurality of frames. Next, the determination sub-module in the evaluation module 300 calculates the lipid capsule ratio using the average value of the lipid load and the median value of the thickness of the fibrous capsule, and evaluates the state of the coronary artery plaque by using the maximum lipid capsule ratio obtained by calculating over the entire plaque as the lipid capsule ratio of the coronary artery plaque.

[0067] As an evaluation criterion, for example, when the lipid capsule ratio is equal to or greater than a first threshold value, the determination sub-module determines that the coronary artery plaque is an unstable plaque.

[0068] In addition to the lipid capsule ratio, the determination sub-module may further evaluate the state of the coronary artery plaque in combination with the blood flow reserve ratio. Thereby, a more reliable evaluation result can be obtained.

[0069] Specifically, the blood flow reserve ratio may be, for example, a blood flow reserve ratio obtained based on an optical coherence tomography video. When the lipid capsule ratio is equal to or greater than a first threshold value and the blood flow reserve ratio is equal to or less than a second threshold value, the determination sub-module determines that the coronary artery plaque is an unstable plaque.

[0070] Furthermore, the identification module 200 may identify the optical coherence tomography image using a plaque identification model, wherein the plaque identification model is obtained based on sample training by deep learning.

[0071] In addition, the present invention further provides an electronic device 1400.

[0072] As shown in FIG. 3, an embodiment of the present invention provides an electronic device 1400 including a processor 1401 and a memory 1402 storing computer program instructions. When the computer program instructions are executed by the processor, the processor 1401 performs step S1 of acquiring an optical coherence tomography image of a coronary plaque awaiting evaluation; performs step S2 of identifying the optical coherence tomography image and determining a fibrous component and a lipid plaque; performs step S3 of evaluating the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque.

[0073] When specifically applied, the electronic device 1400 of the present invention is connected to an optical coherence tomography scanner, and the processor of the electronic device 1400 receives an optical coherence tomography image obtained by scanning of the optical coherence tomography scanner, identifies the optical coherence tomography image, and evaluates the stable state of the plaque based on the identification result.

[0074] Furthermore, as shown in FIG. 3, the electronic device further includes a network interface 1403, an input device 1404, a hard disk 1405, and a display device 1406.

[0075] Each of the above interfaces and devices may be interconnected via a bus architecture. The bus architecture may include any number of interconnected buses and bridges. Specifically, one or more central processing units (CPUs) represented by the processor 1401 and various circuits of one or more memories represented by the memory 1402 are connected together. The bus architecture may further connect together various other circuits such as peripheral devices, regulators, and power management circuits. It should be noted that the bus architecture is for realizing connection communication between these assemblies. The bus architecture further includes a power bus, a control bus, and a status signal bus in addition to the data bus, all of which are known in the art and thus will not be described in detail herein.

[0076] The network interface 1403 may be connected to a network (e.g., the Internet, a local area network, etc.), obtain relevant data from the network, and store it in the hard disk 1405.

[0077] The input device 1404 may receive various instructions input by an operator, send them to the processor 1401, and provide them for execution. The input device 1404 may include a keyboard or a pointing device (e.g., a mouse, a trackball, a touch pad, or a touch panel, etc.).

[0078] The display device 1406 can display the results obtained when the processor 1401 executes instructions.

[0079] The memory 1402 is for storing programs and data necessary for the execution of the operating system, and data such as intermediate results in the process calculated by the processor 1401.

[0080] It should be noted that the memory 1402 in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM) used as an external high-speed buffer memory. It is intended that the memory 1402 of the devices and methods described herein includes these and any other suitable types of memory, but is not limited thereto.

[0081] In some embodiments, the memory 1402 stores executable modules or data structures, or subsets or extended sets thereof, as well as the operating system 14021 and application programs 14014, as the following elements.

[0082] Among them, the operating system 14021 includes various system programs for realizing various basic operations and processing hardware-based tasks, such as a framework layer, a core library layer, a driver layer, etc. The application programs 14014 include various application programs for realizing various application operations, such as a browser. The program for realizing the method of the embodiment of the present invention may be included in the application programs 14014.

[0083] The method disclosed in the above embodiments of the present invention may be used in the processor 1401 or may be implemented by the processor 1401. The processor 1401 is an integrated circuit chip and may have the ability to process signals. In the process of implementation, each step of the above method may be achieved by the integrated logic circuit of the hardware in the processor 1401 or by the instructions in the form of software. The above-mentioned processor 1401 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-made programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute each method, step and logic block diagram disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may be any ordinary processor or the like. The steps in accordance with the method disclosed in the embodiments of the present invention may be directly and specifically embodied as those executed by a hardware decoder processor or as a combination of hardware and software modules in the decoder processor. The software module may exist in a storage medium established in the art such as random memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register, etc. The storage medium is in the memory 1402, and the processor 1401 reads the information in the memory 1402 and accomplishes the steps of the above method in combination with its hardware.

[0084] Note that these embodiments described in the present text may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For the hardware implementation, the processing unit may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in this application, or a combination thereof.

[0085] For the software implementation, the techniques described in the present text may be realized by modules (e.g., processes, functions, etc.) that execute the functions described in the present text. The software code may be stored in a memory and executed by a processor. The memory may be realized within the processor or external to the processor. Specifically, the processor 1401 further reads the computer program, step S1 of acquiring an optical coherence tomography image of a coronary plaque awaiting evaluation, step S2 of identifying the optical coherence tomography image and determining a fibrous component and a lipid plaque, and step S3 of evaluating the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque, are used to execute. In addition, the embodiments of the present invention further provide a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the processor performs step S1 of providing an optical coherence tomography image of a coronary plaque awaiting evaluation, step S2 of identifying the optical coherence tomography image and determining a fibrous component and a lipid plaque, and step S3 of evaluating the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque.

[0086] It should be understood that in some embodiments provided in the present application, the disclosed methods and apparatuses may be implemented in other ways. For example, the above apparatus embodiments are merely illustrative. For example, the division of the above units is only a division of one logical function. In actual implementation, there may be other division methods. For example, a plurality of units or modules may be combined with another system, or integrated into another system, or some features may be ignored or not executed. In addition, the couplings, direct couplings, or communication connections shown or discussed may be realized through some interfaces. The indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0087] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included individually, or two or more units may be integrated into one unit. The above integrated units may be realized in the form of hardware, or in the form of a hardware + software functional unit.

[0088] The integrated unit realized in the form of the above software functional unit may be stored in a computer-readable storage medium. The above software functional unit is stored in a storage medium and includes some instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute some steps of the transmission and reception methods described in each embodiment of the present invention. The above storage medium includes various media capable of storing program codes, such as USB disks, removable disks, read-only memories (abbreviated as ROM), random access memories (abbreviated as RAM), magnetic disks, or optical disks.

[0089] Hereinafter, the method for evaluating the state of coronary artery plaques according to the present invention will be further described with reference to the schematic diagrams of plaques.

[0090] Figure 4 shows schematic diagrams of several plaques.

[0091] Among them, a and b each have a lipid angle <180° and a fibrous cap thickness greater than 65 μm (both are 90 μm), that is, according to the conventional OCT imaging technology, both of these two patterns are determined to be stable plaques.

[0092] However, through observation, it was found that the lipid in the plaque shown in b is significantly larger than that in the plaque shown in a. That is, there are significant differences in the stability of the plaques shown in a and b.

[0093] For these two plaques, according to the LCR index proposed by the present invention, the LCR of the plaque in Figure a is 20 / 90 = 0.222, and the LCR of the plaque in Figure b is 35 / 90 = 0.389.

[0094] As can be seen, the LCR index can more accurately and quantitatively describe vulnerability.

[0095] Also, c and d indicate that based on the conventional OCT imaging technology, they were respectively determined to be unstable and stable plaques.

[0096] However, through observation, it was found that the proportion of lipid occupied by the plaque in Figure d is even larger. Through calculation, it was found that the LCR of the plaque in Figure c is 15 / 60 = 0.25, and the LCR of the plaque in Figure d is 35 / 90 = 0.389. That is, the LCR of the plaque in Figure d is significantly larger than that of the plaque in Figure c. Compared with the plaque in Figure c, the plaque in Figure d is more unstable.

[0097] That is, the judgment result obtained based on the LCR index submitted to the evaluation method of the present invention is not only more intuitive, but also can overcome the problem of judgment errors due to neglect of the size of lipids.

[0098] Hereinafter, the evaluation method for the state of coronary artery plaques according to the present invention will be described in more detail with specific examples. [Example 1]

[0099] First, obtain some frame optical coherence tomography images of the coronary artery plaque waiting for evaluation. (a) in FIG. 5 shows optical coherence tomography images of 5 frames. They are the original figure of the target frame and the original figures of 1 before approach, 2 before approach, 1 after approach, and 2 after approach, respectively.

[0100] Next, perform identification on the original figures of the 5 frames by means of an identification model, and the identification result is shown in (b) in FIG. 5.

[0101] After identification, the fibrous components and lipid plaques therein were determined.

[0102] Next, based on the fibrous components and lipid plaques in the identified figure, calculate the thickness of the fibrous capsule and the lipid burden in each frame figure, respectively.

[0103] Take the average value of the lipid burden and the median value of the thickness of the fibrous capsule in the 5-frame images to calculate the LCR of the target frame.

[0104] [Table 1]

[0105] As can be seen from Table 1, the percentage average value of the lipid burden of the 5-frame images is 34.3, and the median value of the thickness of the fibrous capsule is 86. Therefore, the target frame LCR = 34.3 / 86 = 0.40.

[0106] Furthermore, for a total of 604 clinical cases followed up for two years, the results of LCR index evaluation, combined evaluation of LCR and blood flow reserve ratio, and dichotomous evaluation based on conventional OCT imaging technology were respectively shown in Table 2.

[0107]

Table 2

[0108] As can be seen from Table 2, according to the LCR index evaluation method provided by the present invention, plaque stability can be evaluated better and quantitatively. Moreover, in the case of combined evaluation of the LCR index and blood flow reserve ratio, by comprehensively considering the morphological index of the LCR index and the physiological index of the blood flow reserve ratio, the sensitivity, positive predictive value, and negative predictive value can be effectively increased, achieving a better evaluation effect.

[0109] The above are the preferred embodiments of the present invention. It should be noted that for those skilled in the art, on the premise of not departing from the principles described in the present invention, some further improvements and refinements may be made. These improvements and refinements should also be regarded as within the protection scope of the present invention.

Claims

1. Step S1 of obtaining an optical coherence tomography image of a coronary plaque awaiting evaluation; Step S2 of identifying the optical coherence tomography image and determining a fibrous component and a lipid plaque; Including step S3 of evaluating the state of the coronary plaque based on the fibrous component and the lipid burden of the lipid plaque; The step S3 includes: Step S31 of calculating the thickness of the fibrous capsule covering the surface of the lipid plaque among the fibrous components and the lipid burden of the lipid plaque respectively; Including step S32 of determining the state of the coronary plaque based on the thickness of the fibrous capsule and the lipid burden; The step S32 includes: Step S321 of calculating a lipid capsule ratio by the following formula based on the lipid burden and the thickness of the fibrous capsule; Lipid capsule ratio = lipid burden / thickness of fibrous capsule Including step S322 of evaluating the state of the coronary plaque based on the lipid capsule ratio; In step S1, for the optical coherence tomography image of the target frame, continuous images of several frames before and after the optical coherence tomography image of the target frame are respectively obtained; In step S31, the thickness of the fibrous capsule and the lipid burden of the fibrous component of the optical coherence tomography images of a plurality of consecutive frames are respectively calculated, and the median value of the thickness of the fibrous capsule and the average value of the lipid burden of the optical coherence tomography images of the plurality of frames are determined; In step S321, the lipid capsule ratio is calculated using the average value of the lipid burden and the median value of the thickness of the fibrous capsule; In step S322, the maximum lipid capsule ratio calculated for the entire plaque is used as the lipid capsule ratio of the coronary plaque to evaluate the state of the coronary plaque A method for evaluating the state of a coronary plaque, characterized by the above.

2. In step S322, in addition to the lipid capsule ratio, the state of the coronary plaque is evaluated in combination with a blood flow reserve ratio. The blood flow reserve ratio is a blood flow reserve ratio obtained based on an optical coherence tomography video. When the lipid capsule ratio is greater than or equal to a first threshold and the blood flow reserve ratio is less than or equal to a second threshold, it is determined that the coronary plaque is an unstable plaque. The method according to claim 1, characterized by the above.

3. The method according to claim 1, wherein the optical coherence tomography image is identified by a plaque identification model, and the plaque identification model is obtained based on sample training by deep learning.

4. An image acquisition module for acquiring an optical coherence tomography image of a coronary plaque awaiting evaluation, An identification module for identifying fibrous components and lipid plaques based on the optical coherence tomography image, An evaluation module for evaluating the state of the coronary plaque based on the fibrous components and the lipid load of the lipid plaque, comprising: The evaluation module includes: A calculation sub-module for calculating the thickness of the fibrous capsule covering the surface of the lipid plaque among the fibrous components and the lipid load of the lipid plaque respectively; A determination sub-module for determining the state of the coronary plaque based on the thickness of the fibrous capsule and the lipid load; The determination sub-module includes: Based on the lipid load and the thickness of the fibrous capsule, calculate the lipid capsule ratio according to the following formula: Lipid capsule ratio = lipid load / thickness of fibrous capsule It is for evaluating the state of the coronary plaque based on the lipid capsule ratio; The image acquisition module is for respectively acquiring consecutive images of several frames before and after the optical coherence tomography image of the target frame for the optical coherence tomography image of the target frame; The calculation sub-module calculates the thickness of the fibrous capsule and the lipid load of the fibrous components of the optical coherence tomography images of a plurality of consecutive frames respectively, and determines the median value of the thickness of the fibrous capsule and the average value of the lipid load of the optical coherence tomography images of the plurality of frames; The determination sub-module calculates the lipid capsule ratio with the average value of the lipid load and the median value of the thickness of the fibrous capsule, and evaluates the state of the coronary plaque by using the maximum lipid capsule ratio obtained by calculating over the entire plaque as the lipid capsule ratio of the coronary plaque. An apparatus for evaluating the state of a coronary plaque, characterized in that. **Claim 5**: The determination sub-module further associates with a blood flow reserve ratio in addition to the lipid capsule ratio to evaluate the state of the coronary plaque. The blood flow reserve ratio is a blood flow reserve ratio obtained based on an optical coherence tomography image. When the lipid capsule ratio is equal to or greater than a first threshold value and the blood flow reserve ratio is equal to or less than a second threshold value, it is determined that the coronary plaque is an unstable plaque. The apparatus according to claim 4, characterized in that. **Claim 6** The identification module identifies the optical coherence tomography image by a plaque identification model, and the plaque identification model is obtained based on sample training by deep learning. The apparatus according to claim 4, characterized in that. **Claim 7** A processor, A memory storing computer program instructions, and comprising: When the computer program instructions are executed by the processor, the processor Performs step S1 of acquiring an optical coherence tomography image of a coronary plaque waiting for evaluation; Performs step S2 of identifying the optical coherence tomography image and determining a fibrous component and a lipid plaque; Performs step S3 of evaluating the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque. Step S3 includes: Step S31 of calculating the thickness of the fibrous capsule covering the surface of the lipid plaque among the fibrous components and the lipid load of the lipid plaque respectively; Step S32 of determining the state of the coronary plaque based on the thickness of the fibrous capsule and the lipid load. Step S32 includes: Step S321 of calculating a lipid capsule ratio by the following formula based on the lipid load and the thickness of the fibrous capsule; Lipid capsule ratio = lipid load / thickness of fibrous capsule Step S322 of evaluating the state of the coronary plaque based on the lipid capsule ratio. In step S1, for the optical coherence tomography image of the target frame, consecutive images of several frames before and after the optical coherence tomography image of the target frame are respectively acquired. In step S31, the thickness of the fibrous capsule and the lipid load of the fibrous component of the optical coherence tomography images of a plurality of consecutive frames are respectively calculated, and the median value of the thickness of the fibrous capsule and the average value of the lipid load of the optical coherence tomography images of the plurality of frames are determined. In step S321, the lipid coating ratio is calculated using the average value of the lipid load and the median value of the thickness of the fibrous capsule. In step S322, the maximum lipid coating ratio obtained by calculating for the entire plaque is taken as the lipid coating ratio of the coronary plaque, and the state of the coronary plaque is evaluated. An electronic device characterized by the above. **Claim 8** A computer-readable storage medium storing computer program instructions, wherein when the computer program instructions are executed by a processor, the processor performs step S1 of acquiring an optical coherence tomography image of a coronary plaque awaiting evaluation; performs step S2 of identifying the optical coherence tomography image and determining a fibrous component and a lipid plaque; performs step S3 of evaluating the state of the coronary plaque based on the fibrous component and the lipid load of the lipid plaque; Step S3 includes step S31 of calculating the thickness of the fibrous capsule covering the surface of the lipid plaque and the lipid load of the lipid plaque among the fibrous components respectively; step S32 of determining the state of the coronary plaque based on the thickness of the fibrous capsule and the lipid load; Step S32 includes step S321 of calculating a lipid coating ratio by the following formula based on the lipid load and the thickness of the fibrous capsule; Lipid coating ratio = lipid load / thickness of fibrous capsule step S322 of evaluating the state of the coronary plaque based on the lipid coating ratio; In step S1, for the optical coherence tomography image of the target frame, consecutive images of a few frames before and after the optical coherence tomography image of the target frame are acquired respectively. In step S31, the thickness of the fibrous capsule and the lipid load of the fibrous components in the optical coherence tomography images of a plurality of consecutive frames are calculated respectively, and the median value of the thickness of the fibrous capsule and the average value of the lipid load in the optical coherence tomography images of the plurality of frames are determined. In step S321, the lipid coating ratio is calculated using the average value of the lipid load and the median value of the thickness of the fibrous capsule. In step S322, the maximum lipid coating ratio obtained by calculating for the entire plaque is taken as the lipid coating ratio of the coronary plaque, and the state of the coronary plaque is evaluated. A computer-readable storage medium characterized by the above.

Images