WO2022228463A1 - 冠状动脉斑块状态评估方法、装置、电子设备 - Google Patents

冠状动脉斑块状态评估方法、装置、电子设备 Download PDF

Info

Publication number
WO2022228463A1
WO2022228463A1 PCT/CN2022/089544 CN2022089544W WO2022228463A1 WO 2022228463 A1 WO2022228463 A1 WO 2022228463A1 CN 2022089544 W CN2022089544 W CN 2022089544W WO 2022228463 A1 WO2022228463 A1 WO 2022228463A1
Authority
WO
WIPO (PCT)
Prior art keywords
lipid
plaque
cap
optical coherence
load
Prior art date
Application number
PCT/CN2022/089544
Other languages
English (en)
French (fr)
Inventor
常云霄
李泽杭
涂泽璇
洪恢宏
Original Assignee
上海博动医疗科技股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 上海博动医疗科技股份有限公司 filed Critical 上海博动医疗科技股份有限公司
Priority to JP2023557182A priority Critical patent/JP2024513722A/ja
Publication of WO2022228463A1 publication Critical patent/WO2022228463A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • 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
    • G06N3/08—Learning methods
    • 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
    • G06T2207/10101—Optical tomography; Optical coherence tomography [OCT]
    • 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
    • G06T2207/20081—Training; Learning
    • 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

Definitions

  • the present invention relates to the technical field of medical imaging, in particular to a method, device, electronic device and computer-readable storage medium for evaluating the state of coronary plaque.
  • Cardiac death is currently the leading cause of death in the population, and acute coronary syndrome caused by unstable plaques in the coronary arteries is a major factor. Therefore, the early detection of plaque stability status in patients with coronary heart disease is crucial for the determination of the patient's treatment plan and the evaluation of long-term prognosis.
  • Intracoronary imaging technology is currently the main method to assess the stability of coronary plaque in patients with coronary heart disease.
  • IVUS intravascular ultrasound
  • NIRS near-infrared spectroscopy
  • Optical coherence tomography has unique advantages in coronary plaque assessment due to its high resolution, but it is still deficient in complete imaging of the entire plaque due to its limited scanning depth.
  • OCT imaging technology can clearly display the thickness of the fibrous cap of coronary plaque, it cannot display the true size of the lipid components in the plaque due to optical attenuation.
  • fibrous cap thickness ⁇ 65um and the lipid angle ⁇ 180° can be used as the evaluation criteria for unstable plaques based on OCT imaging technology, while the size of lipid components, which has been proven to be important for stability, is ignored.
  • Sexual status-related factors, resulting in the above assessment criteria are not accurate enough.
  • the inventors have repeatedly studied and proved through pathological and clinical studies that the composition of the plaque itself, that is, the thickness of the plaque fibrous cap, the size of the lipid, etc., jointly determine the stability of the plaque, and on this basis The present invention has been completed.
  • the present invention provides a coronary plaque state assessment method that comprehensively considers the fibrous cap and lipid components of the plaque to more accurately assess the plaque stability state.
  • the present invention also provides a coronary plaque state assessment device that can comprehensively consider the fibrous cap and lipid components of the plaque to more accurately assess the plaque stability state.
  • the present invention also provides an electronic device capable of executing the coronary plaque state assessment method according to the present invention.
  • the present invention also provides a kind of computer-readable storage medium, its described computer-readable storage medium is stored with computer program instruction, when described computer program instruction is run by processor, makes described processor carry out the corona according to the present invention Methods for assessing arterial plaque status.
  • the present invention adopts the following technical solutions:
  • Step S1 obtaining an optical coherence tomographic image of the coronary plaque to be evaluated
  • Step S2 identifying the optical coherence tomography image to determine fiber components and lipid plaques
  • Step S3 evaluating the state of the coronary plaque based on the fiber component and the lipid load of the lipid plaque.
  • step S3 includes:
  • Step S31 calculating the thickness of the fibrous cap covering the surface of the lipid plaque and the lipid load of the lipid plaque in the fiber component respectively;
  • Step S32 determining the state of the coronary plaque based on the thickness of the fibrous cap and the lipid load.
  • step S32 includes:
  • Step S321 based on the lipid load and the thickness of the fiber cap, calculate the lipid cap ratio according to the following formula,
  • Lipid cap ratio (LCR) lipid load/fibrous cap thickness
  • Step S322 evaluating the state of the coronary plaque based on the fat cap ratio.
  • the step S1 for the optical coherence tomography image of the target frame, several consecutive frames of images before the frame image and after the frame image are respectively acquired,
  • the fiber cap thickness and lipid load of the fiber components of the multiple consecutive frames of the optical coherence tomography images are calculated respectively, and the median fiber cap thickness and lipid load of the multiple frames of the optical coherence tomography images are determined.
  • the lipid-cap ratio is calculated based on the average lipid load and the median thickness of the fibrous cap
  • step S322 the state of the coronary plaque is evaluated by using the maximum lipid cap ratio calculated for the entire plaque as the lipid cap ratio of the coronary plaque.
  • step S322 when the fat-cap ratio is above a first threshold, it is determined that the coronary plaque is an unstable plaque.
  • the LCR value will also change accordingly, and accordingly, the first threshold will also change.
  • the first threshold can be set to 0.33.
  • the state of the coronary plaque may also be evaluated in combination with the blood flow reserve fraction.
  • the blood flow reserve fraction is a blood flow reserve fraction obtained based on an optical coherence tomography image.
  • the blood flow reserve fraction is the first When the two thresholds are below, the coronary plaque is determined to be unstable plaque.
  • the fractional blood flow reserve is negatively correlated with the lipid load of lipid components, that is, the larger the fractional blood flow reserve, the smaller the load of the lipid plaque, and the more stable the plaque is.
  • the second threshold value of the blood flow reserve fraction obtained based on the optical coherence tomography image for example, it can be set to 0.84.
  • the optical coherence tomography image is identified through a patch identification model, wherein the patch identification model is obtained through deep learning and training based on samples.
  • the fiber composition can be trained by a deep learning model to identify the internal elastic plate, and based on the deep learning model, it can be completed, and the completed lipid plaque and all the lipid plaques covered on the lipid plaque can be identified. the fiber composition.
  • the plaque recognition model trained by deep learning can infer the lack of signal in the current layer of the OCT image due to the optical attenuation of lipid plaques based on the upper and lower layer images and the previously trained data, and can more accurately analyze the lipid plaques the size of the lipid load.
  • an image acquisition module for acquiring several optical coherence tomographic images of the coronary plaque to be evaluated
  • an identification module for identifying fiber components and lipid plaques based on a plurality of the optical coherence tomography images
  • An evaluation module for evaluating the state of the coronary plaque based on the fibrous composition and the lipid load of the lipid plaque.
  • Step S1 obtaining an optical coherence tomographic image of the coronary plaque to be evaluated
  • Step S2 identifying the optical coherence tomography image to determine fiber components and lipid plaques
  • Step S3 evaluating the state of the coronary plaque based on the fiber component and the lipid load of the lipid plaque.
  • the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the processor performs the following steps:
  • Step S1 obtaining an optical coherence tomographic image of the coronary plaque to be evaluated
  • Step S2 identifying the optical coherence tomography image to determine fiber components and lipid plaques
  • Step S3 evaluating the state of the coronary plaque based on the fiber component and the lipid load of the lipid plaque.
  • a tomographic image of the blood vessel to be evaluated is obtained by optical coherence tomography, based on the obtained tomographic image, fiber components and lipid components therein are identified, and based on the identified fibers
  • the composition and lipid size can comprehensively evaluate the stability of coronary plaques, which can achieve quantitative evaluation with higher repeatability;
  • the state of the coronary plaque is evaluated by comprehensively considering the thickness of the fibrous cap and the lipid load. Compared with the prior art, the influence of the lipid size on the stability state is considered, and the confidence of the evaluation results is obtained. higher degree;
  • the plaque recognition model is trained by deep learning, which realizes the fully automatic and comprehensive morphological evaluation of coronary plaque in vivo, improves the reproducibility of the evaluation, and reduces the subjectivity of the evaluation.
  • the plaque recognition model can infer the lack of signal in the current layer of the OCT image due to the optical attenuation of lipid plaques based on the upper and lower layer images and the previously trained data, and can more accurately analyze the lipid load of the lipid plaques. size;
  • the combination of the morphological index of the LCR index and the physiological index of the fractional blood flow reserve can effectively improve the positive predictive value and obtain a better evaluation effect.
  • FIG. 1 is a schematic flowchart of a method for evaluating coronary plaque status according to an embodiment of the present invention
  • FIG. 2 is a block diagram of a coronary plaque state assessment device 10 according to an embodiment of the present invention.
  • FIG. 3 is a block diagram of an electronic device 1400 according to an embodiment of the present invention.
  • Figure 4 shows a simplified schematic representation of patches for 4 different patterns.
  • FIG. 5 is the original image of the optical coherence tomography image obtained in Example 1 of the present invention and its identification image, wherein (a) represents the original image, and (b) represents the identification image.
  • the method for evaluating coronary plaque status includes:
  • Step S1 providing an optical coherence tomographic image of the coronary plaque to be evaluated.
  • an optical coherence tomograph can be connected, whereby a region of interest of a blood vessel can be acquired to identify coronary plaques therein.
  • Step S2 identifying the optical coherence tomography image to determine fiber components and lipid plaques.
  • optical coherence tomography images After optical coherence tomography images are obtained, they are identified to determine fibrous components and lipid plaques.
  • the above-mentioned identification of the optical coherence tomography image may be performed by a plaque identification model, wherein the plaque identification model may be obtained based on sample training, for example, by deep learning.
  • the fiber composition can be trained by a deep learning model to identify the internal elastic plate, and based on the deep learning model, it can be completed, and the completed lipid plaque and all the lipid plaques covered on the lipid plaque can be identified. the fiber composition.
  • the plaque identification model is trained by deep learning, which realizes the fully automatic and comprehensive morphological evaluation of coronary plaque in vivo, improves the reproducibility of the evaluation, and reduces the subjectivity of the evaluation.
  • the block recognition model can infer the lack of signal in the current layer of the OCT image due to the optical attenuation of lipid plaques based on the upper and lower layer images and the previously trained data, and can more accurately analyze the lipid load of the lipid plaques.
  • Step S3 evaluating the stability state of the coronary plaque based on the fiber component and the lipid load of the lipid plaque.
  • lipid load refers to the percentage of lipid plaques in the cross-sectional area of the entire blood vessel, which reflects the size of lipids.
  • the evaluation method of the present invention comprehensively considers the fibrous components and the lipids of the lipid plaques load to evaluate the status of the coronary plaque.
  • the step S3 may include:
  • Step S31 respectively calculating the thickness of the fiber cap covering the surface of the lipid plaque and the lipid load of the lipid component in the fiber component;
  • Step S32 determining the state of the coronary plaque based on the thickness of the fibrous cap and the lipid load.
  • step S32 may include:
  • Step S321 based on the lipid load and the thickness of the fibrous cap, calculate the lipid cap ratio (LCR) according to the following formula,
  • LCR lipid load/fibrous cap thickness
  • Step S322 evaluating the state of the coronary plaque based on the fat cap ratio.
  • the state of coronary plaque is evaluated by introducing the LCR index.
  • the LCR value will also change accordingly, and accordingly, the first threshold will also change.
  • the lipid load is taken as a percentage and the thickness of the fiber cap is taken in ⁇ m, according to a large number of experimental results, it is found that the stability of the lipid cap is worse than that of 0.33. Therefore, it can be set as follows: when the lipid cap ratio is 0.33 In the above cases, the coronary plaques are determined to be unstable plaques.
  • the state of coronary plaque may also be evaluated in combination with the blood flow reserve fraction.
  • the evaluation method of the present invention is based on the analysis of optical coherence tomography images
  • the blood flow reserve fraction is obtained based on the optical coherence tomography image
  • the blood flow reserve fraction is based on the An optical coherence tomography scanner is used to determine the blood flow velocity, and the intraluminal structure is obtained based on the optical coherence tomography image, and the blood flow reserve fraction is calculated based on this. Therefore, the optical coherence tomography image and the blood flow reserve fraction can be obtained with one retraction, which is more efficient.
  • the coronary plaque When evaluating the stability of coronary plaque by combining the lipid cap ratio and the blood flow reserve fraction, it is determined according to a large number of experimental results that when the lipid cap ratio is the first threshold (for example, in the above case, the first threshold is 0.33 ) and above, and the fractional blood flow reserve is below the second threshold (shown by a lot of experimental analysis, for example, it can be taken as 0.84) or less, the coronary plaque can be judged to be unstable plaque.
  • the first threshold for example, in the above case, the first threshold is 0.33
  • the fractional blood flow reserve shown by a lot of experimental analysis, for example, it can be taken as 0.84
  • combining the morphological index of the LCR index and the physiological index of the fractional blood flow reserve can effectively improve the sensitivity, positive predictive value and negative predictive value, and obtain a better evaluation effect.
  • the fiber components and lipid plaques therein are identified, and based on the lipid size and the fiber The components are used to comprehensively evaluate the stability state of the coronary plaque, and the accuracy is higher.
  • step S1 for the optical coherence tomography image of the target frame, several consecutive frames of images before the frame image and after the frame image are respectively obtained,
  • the fiber cap thickness and lipid load of the fiber components of the multiple consecutive frames of the optical coherence tomography images are calculated respectively, and the median fiber cap thickness and lipid load of the multiple frames of the optical coherence tomography images are determined.
  • the lipid-cap ratio is calculated based on the average lipid load and the median thickness of the fibrous cap
  • step S322 the state of the coronary plaque is evaluated by using the maximum lipid cap ratio calculated for the entire plaque as the lipid cap ratio of the coronary plaque.
  • the stability state of the plaque is evaluated by combining the optical coherence tomography images of multiple consecutive frames, thereby reducing the influence caused by the recognition error of a single frame image.
  • FIG. 2 shows a coronary plaque state assessment device 10 according to an embodiment of the present invention.
  • the coronary plaque state assessment device 10 includes: an image acquisition module 100 , an identification module 200 , and an evaluation module 300 .
  • the image acquisition module 100 is used to acquire the optical coherence tomography image of the coronary plaque to be evaluated.
  • the image acquisition module 100 may receive an optical coherence tomography image scanned by the optical coherence tomography scanner through an interface for connecting with the optical coherence tomography scanner.
  • the identification module 200 is used to identify fiber components and lipid plaques based on several of the optical coherence tomography images.
  • the identification module 200 may be, for example, a plaque identification model formed by deep learning and training based on samples.
  • the evaluation module 300 is used to evaluate the state of the coronary plaque based on the fibrous component and lipid plaque.
  • the evaluation module 300 may include:
  • a calculation submodule for calculating the thickness of the fibrous cap of the fibrous component and the lipid load of the lipid plaque, respectively;
  • determining submodule is used for:
  • the lipid cap ratio (LCR) is calculated according to the following formula,
  • LCR lipid load/fibrous cap thickness
  • the image acquisition module 100 is configured to, for the optical coherence tomography image of the target frame, acquire several consecutive frames of images before the frame image and after the frame image, respectively,
  • the calculation sub-module in the evaluation module 300 calculates the fiber cap thickness of the fiber component and the lipid load of the lipid plaque in the consecutive multiple frames of the optical coherence tomography image, and determines the multiple frames of the optical coherence tomography image.
  • the determination sub-module in the evaluation module 300 calculates the lipid cap ratio based on the average lipid load and the median thickness of the fibrous cap, and takes the maximum lipid cap ratio calculated from the entire plaque as the coronary plaque The lipid-cap ratio of the block was used to evaluate the status of coronary plaque.
  • the determination sub-module determines that the coronary plaque is an unstable plaque.
  • the determination sub-module can also evaluate the state of the coronary plaque in combination with the fractional flow reserve in addition to the lipid cap ratio. As a result, a more reliable evaluation result can be obtained.
  • the blood flow reserve fraction may be, for example, a blood flow reserve fraction obtained based on an optical coherence tomography image, the determination submodule is when the lipid cap ratio is above a first threshold, and the blood flow reserve fraction is the first When the two thresholds are below, the coronary plaque is determined to be unstable plaque.
  • the identification module 200 may identify the optical coherence tomographic image through a patch identification model, wherein the patch identification model is obtained through deep learning and training based on samples.
  • the present invention also provides an electronic device 1400 .
  • an embodiment of the present invention provides an electronic device 1400, including: a processor 1401 and a memory 1402, where computer program instructions are stored in the memory 1402, wherein the computer program instructions are described in the When the processor is running, the processor 1401 is caused to perform the following steps:
  • Step S1 obtaining an optical coherence tomographic image of the coronary plaque to be evaluated
  • Step S2 identifying the optical coherence tomography image to determine fiber components and lipid plaques
  • Step S3 evaluating the state of the coronary plaque based on the fiber component and the lipid load of the lipid plaque.
  • the electronic device 1400 of the present invention is connected to the optical coherence tomography scanner, and the processor of the electronic device 1400 receives the optical coherence tomography image scanned by the optical coherence tomography scanner, and performs the optical coherence tomography image recognition, and based on the recognition result , to evaluate the stability status of plaques.
  • the electronic device further includes a network interface 1403 , an input device 1404 , a hard disk 1405 , and a display device 1406 .
  • the above-mentioned various interfaces and devices may be interconnected through a bus architecture.
  • the bus architecture can be a bus and bridge that can include any number of interconnects.
  • the various circuits of one or more central processing units (CPUs), particularly represented by processor 1401, and one or more memories, represented by memory 1402, are connected together.
  • the bus architecture can also connect together various other circuits such as peripherals, voltage regulators, and power management circuits. It can be understood that the bus architecture is used to realize the connection communication between these components.
  • the bus architecture also includes a power bus, a control bus, and a status signal bus, which are well known in the art, and therefore will not be described in detail herein.
  • the network interface 1403 can be connected to a network (such as the Internet, a local area network, etc.), obtain relevant data from the network, and can save it in the hard disk 1405 .
  • a network such as the Internet, a local area network, etc.
  • the input device 1404 can receive various instructions input by the operator and send them to the processor 1401 for execution.
  • the input device 1404 may include a keyboard or pointing device (eg, mouse, trackball, touch pad or touch screen, etc.).
  • the display device 1406 can display the result obtained by the processor 1401 executing the instruction.
  • the memory 1402 is used to store programs and data necessary for the operation of the operating system, as well as data such as intermediate results in the calculation process of the processor 1401 .
  • the memory 1402 in the embodiment of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory can be read only memory (ROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM) or flash.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • memory 1402 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set of them: operating system 14021 and applications 14014.
  • the operating system 14021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks.
  • the application program 14014 includes various application programs, such as a browser (Browser), etc., for implementing various application services.
  • a program for implementing the method of the embodiment of the present invention may be included in the application program 14014 .
  • the methods disclosed in the foregoing embodiments of the present invention may be applied to the processor 1401 or implemented by the processor 1401 .
  • the processor 1401 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above-mentioned method may be completed by an integrated logic circuit of hardware in the processor 1401 or an instruction 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), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, which can implement or execute the methods, steps, and logical block diagrams disclosed in the embodiments of the present invention.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present invention may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory 1402, and the processor 1401 reads the information in the memory 1402, and completes the steps of the above method in combination with its hardware.
  • the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof.
  • 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 herein, or combinations thereof.
  • ASICs Application Specific Integrated Circuits
  • DSPs Digital Signal Processors
  • DSPDs Digital Signal Processing Devices
  • PLDs Programmable Logic Devices
  • FPGAs Field Programmable Gate Arrays
  • the techniques described herein may be implemented through modules (eg, procedures, functions, etc.) that perform the functions described herein.
  • Software codes may be stored in memory and executed by a processor.
  • the memory can be implemented in the processor or external to the processor.
  • processor 1401 is also used to read the computer program, and perform the following steps:
  • Step S1 obtaining an optical coherence tomographic image of the coronary plaque to be evaluated
  • Step S2 identifying the optical coherence tomography image to determine fiber components and lipid plaques
  • Step S3 evaluating the state of the coronary plaque based on the fiber component and the lipid load of the lipid plaque.
  • an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor performs the following steps:
  • Step S1 providing an optical coherence tomographic image of the coronary plaque to be evaluated
  • Step S2 identifying the optical coherence tomography image to determine fiber components and lipid plaques
  • Step S3 evaluating the state of the coronary plaque based on the fiber component and the lipid load of the lipid plaque.
  • the disclosed method and apparatus may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • 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-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional units.
  • the above-mentioned integrated units implemented in the form of software functional units can be stored in a computer-readable storage medium.
  • the above software functional unit is stored in a storage medium, and includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute part of the steps of the transceiving method described in the various embodiments of the present invention.
  • the aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM for short), Random Access Memory (RAM for short), magnetic disk or CD, etc. that can store program codes medium.
  • Figure 4 shows a schematic diagram of several simplified plaques.
  • a and b respectively, show the case where the lipid angle is ⁇ 180°, and the thickness of the fiber cap is greater than 65 ⁇ m (both are 90 ⁇ m), that is to say, according to the existing OCT imaging technology, both modes are judged for stable plaques.
  • the LCR index can describe the vulnerability more accurately and quantitatively.
  • c and d show plaques judged to be unstable and stable, respectively, based on existing OCT imaging techniques.
  • the judgment result obtained based on the LCR index proposed by the evaluation method of the present invention can not only be more intuitive, but also overcome the problem of judgment errors caused by ignoring the size of lipids.
  • Fig. 5(a) shows 5 frames of optical coherence tomography images. They are the original image of the target frame and the original images near the front 1, near the front 2, near the back 1, and near the back 2.
  • the recognition model is used for recognition, and the recognition result is shown in (b) of FIG. 5 .
  • the fiber cap thickness and lipid load in each frame image were calculated respectively.
  • the LCR of the target frame was calculated by taking the average of the lipid load in the 5 frames and the median of the thickness of the fibrous cap.
  • Table 1 shows the calculation results of the fiber cap thickness and lipid load of each frame of images.
  • Table 2 shows the evaluation results obtained by various evaluation methods.
  • the LCR index evaluation method provided by the present invention can better and quantitatively evaluate the stability of plaque, and in the case of LCR index combined with the evaluation of blood flow reserve fraction, by evaluating the LCR index form Comprehensive consideration of the physiological index of the biological index and the fractional blood flow reserve can effectively improve the sensitivity, positive predictive value and negative predictive value, and obtain a better evaluation effect.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
  • Endoscopes (AREA)
  • Image Analysis (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

本发明提供一种冠状动脉斑块状态评估方法、装置、电子设备及计算机可读存储介质。其中，冠状动脉斑块状态评估方法，包括如下步骤：步骤S1，提供待评估的冠状动脉斑块的光学相干断层图像；步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。根据本发明实施例的冠状动脉斑块状态评估方法，通过光学相干断层成像技术获取待评估血管的断层影像，基于所获得的断层影像，识别其中的纤维成分与脂质斑块，基于所识别的纤维成分与脂质大小，综合评价冠状动脉斑块的状态，能够实现定量化评估，且可重复性更高。

Description

冠状动脉斑块状态评估方法、装置、电子设备 技术领域
本发明涉及医学成像技术领域，具体涉及一种冠状动脉斑块状态评估方法、装置、电子设备及计算机可读存储介质。
背景技术
心源性死亡是目前人群死亡的首要原因，由冠状动脉内的不稳定斑块引起的急性冠脉综合症更是其中的主要因素。因此，冠心病患者斑块稳定性状态的早期检测对患者的治疗方案的确定及长期预后的评估至关重要。
冠状动脉内成像技术是当前评估冠心病患者冠脉内斑块稳定性状态的主要手段。其中，血管内超声(IVUS)和近红外光谱(NIRS)技术虽能纵深评估斑块的大小，但成像机制本身仍限制了其实现对斑块各成分的明确区分及综合性评估。
光学相干断层扫描成像技术(OCT)以其较高的分辨率在冠状动脉斑块评估方面有独特优势，但因其扫描深度有限，对整个斑块的完整成像仍有缺陷。另外，OCT成像技术虽能清晰的显示冠状动脉斑块的纤维帽厚度，但因为光学衰减的原因，其无法显示斑块内脂质成分的真实大小。目前，临床实践中，基于OCT成像技术只能以纤维帽厚度＜65um且脂质角度≥180°来作为不稳定斑块的评估标准，而忽视脂质成分大小这一已被证实的重要的稳定性状态相关因素，导致上述评估标准并不够准确。
因此，需要开发一种更加准确的评估方法。
发明内容
本发明人等经过反复研究，并通过病理学及临床研究证明，斑块的构成本身，即斑块纤维帽的厚度、脂质的大小等共同决定了斑块的稳定性，并在此基础上完成本发明。
有鉴于此，本提供一种综合考虑斑块的纤维帽以及脂质成分，更准确地评估斑块稳定性状态的冠状动脉斑块状态评估方法。
本发明还提供一种能够综合考虑斑块的纤维帽以及脂质成分，更准确地评估斑块稳定性状态的冠状动脉斑块状态评估装置。
从外，本发明还提供过一种电子设备，其能够执行根据本发明的冠状动脉斑块状态评估方法。
并且，本发明还提供一种计算机可读存储介质，其所述计算机可读存储介质存储有计算机程序指令，所述计算机程序指令被处理器运行时，使得所述处理器执行根据本发明的冠状动脉斑块状态评估方法。
为解决上述技术问题，本发明采用以下技术方案：
根据本发明第一方面实施例的冠状动脉斑块状态评估方法，包括如下步骤：
步骤S1，获取待评估的冠状动脉斑块的光学相干断层图像；
步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
进一步地，所述步骤S3包括：
步骤S31，分别计算所述纤维成分中覆盖在所述脂质斑块表面的纤维帽厚度以及所述脂质斑块的脂质负荷；
步骤S32，基于所述纤维帽厚度以及所述脂质负荷，确定所述冠状动脉斑块的状态。
更进一步地，所述步骤S32包括：
步骤S321，基于所述脂质负荷与所述纤维帽厚度，根据下述公式计算脂帽比，
脂帽比(LCR)＝脂质负荷/纤维帽厚度，
步骤S322，基于所述脂帽比，评价所述冠状动脉斑块的状态。根据本发明的一些实施例，所述步骤S1中，针对目标帧所述光学相干断层图像，分别获取该帧图像前、以及该帧图像后的若干帧连续图像，
所述步骤S31中，分别计算连续多帧所述光学相干断层图像的所述纤维成 分的纤维帽厚度以及脂质负荷，并确定多帧所述光学相干断层图像的纤维帽厚度中位数以及脂质负荷平均值，
所述步骤S321中，以脂质负荷平均值以及所述纤维帽厚度中位数，计算所述脂帽比，
步骤S322中，以整个斑块计算得到的最大脂帽比作为该冠状动脉斑块的脂帽比，评价该冠状动脉斑块的状态。
进一步地，所述步骤S322中，当所述脂帽比为第一阈值以上时，判断所述冠状动脉斑块为不稳定斑块。
此处，需要说明的是，根据脂质负荷、纤维帽厚度所采用的单位不同，LCR数值也会相应发生变化，相应地，第一阈值也会发生变化。例如，在脂质负荷取百分数，且纤维帽厚度取μm单位时，根据大量实验结果，例如可以设定第一阈值为0.33。进一步地，所述步骤S322中，除了所述脂帽比之外，还可以结合血流储备分数评价所述冠状动脉斑块的状态。
更进一步地，所述血流储备分数是基于光学相干断层影像得到的血流储备分数，所述步骤S322中，当所述脂帽比为第一阈值以上，且所述血流储备分数为第二阈值以下时，判断所述冠状动脉斑块为不稳定斑块。
通常，血流储备分数与脂质成分的脂质负荷呈负相关，也就是说，血流储备分数越大，则说明脂质斑块的负荷越小，说明斑块相对越稳定。
因此，综合考虑脂帽比、以及血流储备分数来评价该斑块的状态，将形态学与生理学数据相结合，更加准确。
作为基于光学相干断层影像得到的血流储备分数的第二阈值，例如，可以设定为0.84。
当然，需要说明的是，本申请对于第一阈值、第二阈值的具体数值不作特殊限定，本领域技术人员可以结合具体要求进行适当设置。进一步地，通过斑块识别模型对所述光学相干断层图像进行识别，其中，所述斑块识别模型通过深度学习，基于样本训练得到。
具体而言，例如可以通过深度学习模型训练其识别内部弹性板，并基于深度学习模型对其进行补全，并识别补全后的脂质斑块以及覆盖在所述脂质斑块上的所述纤维成分。
通过深度学习训练得到的斑块识别模型，可以根据上下层图像以及之前训练的数据推测出OCT图像当前层由于脂质斑块对光学衰减引起的信号缺失，能更加准确地分析出脂质斑块的脂质负荷的大小。
根据本发明第二方面实施例的冠状动脉斑块状态评估装置，包括：
图像获取模块，用于获取待评估的冠状动脉斑块的若干光学相干断层图像；
识别模块，用于基于若干所述光学相干断层图像，识别纤维成分与脂质斑块；
评价模块，用于基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
根据本发明第三方面实施例的电子设备，包括：
处理器；和
存储器，在所述存储器中存储有计算机程序指令，
其中，在所述计算机程序指令被所述处理器运行时，使得所述处理器执行以下步骤：
步骤S1，获取待评估的冠状动脉斑块的光学相干断层图像；
步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
根据本发明第四方面实施例的计算机可读存储介质，所述计算机可读存储介质存储有计算机程序指令，所述计算机程序指令被处理器运行时，使得所述处理器执行以下步骤：
步骤S1，获取待评估的冠状动脉斑块的光学相干断层图像；
步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
本发明的上述技术方案至少具有如下有益效果之一：
根据本发明实施例的冠状动脉斑块状态评估方法，通过光学相干断层成像 技术获取待评估血管的断层影像，基于所获得的断层影像，识别其中的纤维成分与脂质成分，基于所识别的纤维成分与脂质大小，综合评价冠状动脉斑块的稳定性状态，能够实现定量化评估，且可重复性更高；
进一步地，通过综合考虑纤维帽厚度以及脂质负荷，来评价该冠状动脉斑块的状态，相比于现有技术而言，考虑了脂质大小对于稳定性状态的影响，其评价结果的置信度更高；
并且，通过引入LCR这一评价指数，提供了一个连续性定量指标，避免了既往二分类的半定量评价标准所存在的诊断缺陷；
此外，通过深度学习来训练斑块识别模型，实现了冠状动脉斑块在体内的全自动、全面的形态评价，提高了评价的重现性，减少了评价的主观性，且通过深度学习训练得到的斑块识别模型，可以根据上下层图像以及之前训练的数据推测出OCT图像当前层由于脂质斑块对光学衰减引起的信号缺失，能更加准确地分析出脂质斑块的脂质负荷的大小；
另外，结合上述LCR指数这一形态学指数与血流储备分数这一生理学指数进行综合考虑，能够有效提高阳性预测值，获得更好的评价效果。
附图说明
图1为本发明实施例的冠状动脉斑块状态评估方法的流程示意图；
图2为本发明实施例的冠状动脉斑块状态评估装置10的模块图；
图3为本发明实施例的电子设备1400的模块图；
图4示出了4种不同模式的简化斑块示意图。
图5为本发明实施例1中获得的光学相干断层图像的原始图及其识别图，其中(a)表示原始图，(b)表示识别图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例的附图，对本发明实施例的技术方案进行清楚、完整地描述。显然，所描述的实施例是本发明的一部分实施例，而不是全部的实施例。基于所描述的本发明的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本发 明保护的范围。
下面首先结合附图具体描述根据本发明实施例的冠状动脉斑块状态评估方法。
如图1所示，根据本发明实施例的冠状动脉斑块状态评估方法包括：
步骤S1，提供待评估的冠状动脉斑块的光学相干断层图像。
例如可以连接光学相干断层图像仪，由此来获取血管的感兴趣区域，以识别其中的冠状动脉斑块。
步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块。
在获得光学相干断层图像之后，对其进行识别，以确定纤维成分与脂质斑块。
例如可以通过斑块识别模型对所述光学相干断层图像进行上述识别，其中，所述斑块识别模型例如可以通过深度学习，基于样本训练得到。
具体而言，例如可以通过深度学习模型训练其识别内部弹性板，并基于深度学习模型对其进行补全，并识别补全后的脂质斑块以及覆盖在所述脂质斑块上的所述纤维成分。
通过深度学习来训练斑块识别模型，实现了冠状动脉斑块在体内的全自动、全面的形态评价，提高了评价的重现性，减少了评价的主观性，且通过深度学习训练得到的斑块识别模型，可以根据上下层图像以及之前训练的数据推测出OCT图像当前层由于脂质斑块对光学衰减引起的信号缺失，能更加准确地分析出脂质斑块的脂质负荷的大小。
步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的稳定性状态。
其中，脂质负荷指脂质斑块占整个血管的横截面积的百分比，其反映了脂质的大小。
在识别出其中的纤维成分与脂质斑块之后，考虑到脂质大小是影响斑块状态的一个因素，本发明的评估方法，综合考虑所述纤维成分以及所述脂质斑块的脂质负荷，来评价所述冠状动脉斑块的状态。
具体地，所述步骤S3可以包括：
步骤S31，分别计算所述纤维成分中覆盖在所述脂质斑块表面的纤维帽厚度以及所述脂质成分的脂质负荷；
步骤S32，基于所述纤维帽厚度以及所述脂质负荷，确定所述冠状动脉斑块的状态。
也就是说，在识别出所述纤维成分与所述脂质斑块之后，分别计算纤维帽厚度以及所述脂质斑块的脂质负荷，此后基于纤维帽厚度以及所述脂质斑块的脂质负荷来确定所述冠状动脉斑块的状态。
更具体而言，所述步骤S32可以包括：
步骤S321，基于所述脂质负荷与所述纤维帽厚度，根据下述公式计算脂帽比(LCR)，
LCR＝脂质负荷/纤维帽厚度，
步骤S322，基于所述脂帽比，评价所述冠状动脉斑块的状态。
也就是说，通过引入LCR指数来评价冠状动脉斑块的状态。
此处，需要说明的是，根据脂质负荷、纤维帽厚度所采用的单位不同，LCR数值也会相应发生变化，相应地，第一阈值也会发生变化。例如，在脂质负荷取百分数，且纤维帽厚度取μm单位时，根据大量实验结果，分析发现脂帽比0.33以上则稳定性更差，因此可以设定为：当所述脂帽比为0.33以上时，判断冠状动脉斑块为不稳定斑块。
另外，在所述步骤S322中，除了所述脂帽比之外，还可以结合血流储备分数评价冠状动脉斑块的状态。
考虑到本发明的评估方法是基于光学相干断层图像进行的分析，优选地，所述血流储备分数是基于光学相干断层影像得到的血流储备分数，也就是说所述血流储备分数是基于光学相干断层扫描仪来确定血流速度、以及基于光学相干断层图像获取腔内结构，基于此来计算得到血流储备分数。由此，通过一次回撤即可得到光学相干断层图像以及血流储备分数，效率更高。
在结合脂帽比与血流储备分数来评价冠状动脉斑块的稳定性状态时，根据大量实验结果确定，当所述脂帽比为第一阈值(例如上述情况下，取第一阈值为0.33)以上，且所述血流储备分数为第二阈值(经过大量实验分析表明，例如可以取0.84)以下时，可以判断所述冠状动脉斑块为不稳定斑块。
由此，结合上述LCR指数这一形态学指数与血流储备分数这一生理学指数进行综合考虑，能够有效提高灵敏度、阳性预测值和阴性预测值，获得更好的评价效果。
如上所述，根据本发明实施例的冠状动脉斑块状态评估方法，基于待评估的冠状动脉斑块的光学相干断层图像，识别其中的纤维成分与脂质斑块，并基于脂质大小以及纤维成分来综合评价所述冠状动脉斑块稳定性状态，其准确性更高。
作为一个优选实施例，例如：
所述步骤S1中，针对目标帧所述光学相干断层图像，分别获取该帧图像前、以及该帧图像后的若干帧连续图像，
所述步骤S31中，分别计算连续多帧所述光学相干断层图像的所述纤维成分的纤维帽厚度以及脂质负荷，并确定多帧所述光学相干断层图像的纤维帽厚度中位数以及脂质负荷平均值，
所述步骤S321中，以脂质负荷平均值以及所述纤维帽厚度中位数，计算所述脂帽比，
步骤S322中，以整个斑块计算得到的最大脂帽比作为该冠状动脉斑块的脂帽比，评价该冠状动脉斑块的状态。
也就是说，结合连续多帧的光学相干断层图像对斑块的稳定性状态进行评估，由此可以减小因单帧图像的识别误差造成的影响。
图2示出了根据本发明实施例的冠状动脉斑块状态评估装置10。
如图2所示，根据本发明实施例的冠状动脉斑块状态评估装置10包括：图像获取模块100、识别模块200、以及评价模块300。
其中，图像获取模块100用于获取待评估的冠状动脉斑块的光学相干断层图像。例如图像获取模块100可以通过为连接光学相干断层扫描仪的接口，以接收来自光学相干断层扫描仪扫描得到的光学相干断层图像。
识别模块200用于基于若干所述光学相干断层图像，识别纤维成分与脂质斑块。识别模块200例如可以是通过深度学习，基于样本训练形成的斑块识别模型。
评价模块300用于基于所述纤维成分与脂质斑块，评价所述冠状动脉斑块 的状态。
其中，评价模块300可以包括：
计算子模块，用于分别计算所述纤维成分的纤维帽厚度以及所述脂质斑块的脂质负荷；
确定子模块，用于基于所述纤维帽厚度以及所述脂质负荷，确定所述冠状动脉斑块的状态。
进一步地，所述确定子模块用于：
基于所述脂质负荷与所述纤维帽厚度，根据下述公式计算脂帽比(LCR)，
LCR＝脂质负荷/纤维帽厚度；
基于所述脂帽比，评价冠状动脉斑块的状态。
进一步地，图像获取模块100用于针对目标帧的所述光学相干断层图像，分别获取该帧图像前、以及该帧图像后的若干帧连续图像，
此后评价模块300中的计算子模块，分别计算连续多帧所述光学相干断层图像的所述纤维成分的纤维帽厚度以及脂质斑块的脂质负荷，并确定多帧所述光学相干断层图像的纤维帽厚度中位数以及脂质负荷平均值，
接着评价模块300中的额确定子模块，以脂质负荷平均值以及所述纤维帽厚度中位数，计算所述脂帽比，以整个斑块计算得到的最大脂帽比作为该冠状动脉斑块的脂帽比，评价冠状动脉斑块的状态。
作为评价标准，例如确定子模块在所述脂帽比为第一阈值以上时，判断所述冠状动脉斑块为不稳定斑块。
此外，确定子模块除了所述脂帽比之外，还可以结合血流储备分数评价所述冠状动脉斑块的状态。由此能够得到置信度更高的评价结果。
具体地，所述血流储备分数例如可以是基于光学相干断层影像得到的血流储备分数，所述确定子模块在所述脂帽比为第一阈值以上，且所述血流储备分数为第二阈值以下时，判断所述冠状动脉斑块为不稳定斑块。
进一步地，识别模块200可以通过斑块识别模型对所述光学相干断层图像进行识别，其中，所述斑块识别模型通过深度学习，基于样本训练得到。
此外，本发明还提供了一种电子设备1400。
如图3所示，本发明实施例提供了一种电子设备1400，包括：处理器1401 和存储器1402，在所述存储器1402中存储有计算机程序指令，其中，在所述计算机程序指令被所述处理器运行时，使得所述处理器1401执行以下步骤：
步骤S1，获取待评估的冠状动脉斑块的光学相干断层图像；
步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
具体应用时，本发明的电子设备1400连接光学相干断层扫描仪，电子设备1400的处理器接收来自光学相干断层扫描仪扫描得到的光学相干断层图像，并进行光学相干断层图像识别，并基于识别结果，对斑块的稳定性状态进行评价。
进一步地，如图3所示，电子设备还包括网络接口1403、输入设备1404、硬盘1405、和显示设备1406。
上述各个接口和设备之间可以通过总线架构互连。总线架构可以是可以包括任意数量的互联的总线和桥。具体由处理器1401代表的一个或者多个中央处理器(CPU)，以及由存储器1402代表的一个或者多个存储器的各种电路连接在一起。总线架构还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其它电路连接在一起。可以理解，总线架构用于实现这些组件之间的连接通信。总线架构除包括数据总线之外，还包括电源总线、控制总线和状态信号总线，这些都是本领域所公知的，因此本文不再对其进行详细描述。
所述网络接口1403，可以连接至网络(如因特网、局域网等)，从网络中获取相关数据，并可以保存在硬盘1405中。
所述输入设备1404，可以接收操作人员输入的各种指令，并发送给处理器1401以供执行。所述输入设备1404可以包括键盘或者点击设备(例如，鼠标，轨迹球(trackball)、触感板或者触摸屏等。
所述显示设备1406，可以将处理器1401执行指令获得的结果进行显示。
所述存储器1402，用于存储操作系统运行所必须的程序和数据，以及处理器1401计算过程中的中间结果等数据。
可以理解，本发明实施例中的存储器1402可以是易失性存储器或非易失 性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(ROM)、可编程只读存储器(PROM)、可擦除可编程只读存储器(EPROM)、电可擦除可编程只读存储器(EEPROM)或闪存。易失性存储器可以是随机存取存储器(RAM)，其用作外部高速缓存。本文描述的装置和方法的存储器1402旨在包括但不限于这些和任意其它适合类型的存储器。
在一些实施方式中，存储器1402存储了如下的元素，可执行模块或者数据结构，或者他们的子集，或者他们的扩展集：操作系统14021和应用程序14014。
其中，操作系统14021，包含各种系统程序，例如框架层、核心库层、驱动层等，用于实现各种基础业务以及处理基于硬件的任务。应用程序14014，包含各种应用程序，例如浏览器(Browser)等，用于实现各种应用业务。实现本发明实施例方法的程序可以包含在应用程序14014中。
本发明上述实施例揭示的方法可以应用于处理器1401中，或者由处理器1401实现。处理器1401可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器1401中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器1401可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件，可以实现或者执行本发明实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本发明实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1402，处理器1401读取存储器1402中的信息，结合其硬件完成上述方法的步骤。
可以理解的是，本文描述的这些实施例可以用硬件、软件、固件、中间件、微码或其组合来实现。对于硬件实现，处理单元可以实现在一个或多个专用集成电路(ASIC)、数字信号处理器DSP)、数字信号处理设备(DSPD)、可编程逻辑设备(PLD)、现场可编程门阵列(FPGA)、通用处理器、控制器、微控制器、 微处理器、用于执行本申请所述功能的其它电子单元或其组合中。
对于软件实现，可通过执行本文所述功能的模块(例如过程、函数等)来实现本文所述的技术。软件代码可存储在存储器中并通过处理器执行。存储器可以在处理器中或在处理器外部实现。
具体地，处理器1401还用于读取所述计算机程序，执行如下步骤:
步骤S1，获取待评估的冠状动脉斑块的光学相干断层图像；
步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
另外，本发明实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器运行时，使得所述处理器执行以下步骤：
步骤S1，提供待评估的冠状动脉斑块的光学相干断层图像；
步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
在本申请所提供的几个实施例中，应该理解到，所揭露方法和装置，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理包括，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述收发方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，简称ROM)、随机存取存储器(Random Access Memory，简称RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
下面，结合简化斑块图来进一步说明根据本发明的冠状动脉斑块状态评估方法。
图4示出了几种简化斑块的示意图。
其中，a和b，分别示出了脂质角度<180°，且纤维帽厚度大于65μm(均为90μm)的情况，也就是说，根据现有的OCT成像技术，这两种模式均被判断为稳定斑块。
然而，观察发现，b所示斑块中，其脂质明显大于a所示斑块，也就是说，a与b所示斑块的稳定性存在显著差异。
对于这两种斑块，根据本发明提出的LCR指数，a图的斑块的LCR＝20/90＝0.222，b图的斑块的LCR＝35/90＝0.389。
由此可知，LCR指数能够更加准确、定量地描述易损性。
另外，c和d示出了基于现有的OCT成像技术分别判断为不稳定、稳定的斑块。
然而，经过观察发现，d斑块的脂质占比更大，经过计算发现：c图的斑块的LCR＝15/60＝0.25，d图的斑块的LCR＝35/90＝0.389，也就是说，d图的斑块LCR显著大于c图的斑块的LCR，相比于c斑块而言，d斑块更不稳定。
也就是说，基于本发明的评估方法提出的LCR指数获得的判断结果，不仅能够更加直观，而且能够克服由于忽视脂质大小所引起的判断错误问题。
下面，结合具体实施例进一步详细说明根据本发明的冠状动脉斑块状态评估方法。
实施例1
首先，获取待评估的冠状动脉斑块的若干帧光学相干断层图像。图5中(a) 示出了5帧光学相干断层图像。分别为目标帧原始图以及临近前1、临近前2、临近后1、临近后2的原始图。
接着，对于该5帧原始图，通过识别模型进行识别，识别结果如图5中(b)所示。
经过识别后，确定了其中的纤维成分、脂质斑块。
接下来，基于识别图中的纤维成分、脂质斑块，分别计算各帧图片中的纤维帽厚度以及脂质负荷。
取该5帧图像中的脂质负荷的平均值，以及纤维帽厚度的中位数，计算目标帧的LCR。
表1示出了各帧图像的纤维帽厚度、脂质负荷的计算结果。
Figure PCTCN2022089544-appb-000001
根据表1可知，该5帧图像的脂质负荷的百分数平均值为：34.3，且纤维帽厚度的中位数为86，因此目标帧LCR＝34.3/86＝0.40。
此外，对于随访2年的临床病例共计604例病例，分别进行LCR指数评估、LCR结合血流储备分数评估、以及现有的基于OCT成像技术的二分法评估进行评估，结果如表2所示。
表2示出了各种不同评估方法得到的评估结果。
Figure PCTCN2022089544-appb-000002
根据表2可知，根据本发明提供的LCR指数评估法，能够更好地、定量地评估斑块的稳定性，且在LCR指数结合血流储备分数评估的情况下，通过对LCR指数这一形态学指数与血流储备分数这一生理学指数进行综合考虑，能够有效提高灵敏度、阳性预测值和阴性预测值，获得更好的评价效果。
以上所述是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明所述原理的前提下，还可以作出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。

Claims (18)

  1. 一种冠状动脉斑块状态评估方法，其特征在于，包括如下步骤：
    步骤S1，获取待评估的冠状动脉斑块的光学相干断层图像；
    步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
    步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
  2. 根据权利要求1所述的方法，其特征在于，所述步骤S3包括：
    步骤S31，分别计算所述纤维成分中覆盖在所述脂质斑块表面的纤维帽厚度以及所述脂质斑块的脂质负荷；
    步骤S32，基于所述纤维帽厚度以及所述脂质负荷，确定所述冠状动脉斑块的状态。
  3. 根据权利要求2所述的方法，其特征在于，所述步骤S32包括：
    步骤S321，基于所述脂质负荷与所述纤维帽厚度，根据下述公式计算脂帽比，
    脂帽比＝脂质负荷/纤维帽厚度；
    步骤S322，基于所述脂帽比，评价所述冠状动脉斑块的状态。
  4. 根据权利要求3所述的方法，其特征在于，
    所述步骤S1中，针对目标帧的所述光学相干断层图像，分别获取该帧图像前、以及该帧图像后的若干帧连续图像，
    所述步骤S31中，分别计算连续多帧所述光学相干断层图像的所述纤维成分的纤维帽厚度以及脂质负荷，并确定多帧所述光学相干断层图像的纤维帽厚度中位数以及脂质负荷平均值，
    所述步骤S321中，以脂质负荷平均值以及所述纤维帽厚度中位数，计算所述脂帽比，
    步骤S322中，以整个斑块计算得到的最大脂帽比作为该冠状动脉斑块的脂帽比，评价该冠状动脉斑块的状态。
  5. 根据权利要求4所述的方法，其特征在于，所述步骤S322中，当所述 脂帽比为第一阈值以上时，判断所述冠状动脉斑块为不稳定斑块。
  6. 根据权利要求4所述的方法，其特征在于，所述步骤S322中，除了所述脂帽比之外，还结合血流储备分数评价所述冠状动脉斑块的状态。
  7. 根据权利要求6所述的方法，其特征在于，所述血流储备分数是基于光学相干断层影像得到的血流储备分数，
    所述步骤S322中，当所述脂帽比为第一阈值以上，且所述血流储备分数第二阈值以下时，判断所述冠状动脉斑块为不稳定斑块。
  8. 根据权利要求2所述的方法，其特征在于，通过斑块识别模型对所述光学相干断层图像进行识别，其中，所述斑块识别模型通过深度学习，基于样本训练得到。
  9. 一种冠状动脉斑块状态评估装置，其特征在于，包括：
    图像获取模块，用于获取待评估的冠状动脉斑块的光学相干断层图像；
    识别模块，用于基于若干所述光学相干断层图像，识别纤维成分与脂质斑块；
    评价模块，用于基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
  10. 根据权利要求9所述的装置，其特征在于，所述评价模块包括：
    计算子模块，用于分别计算所述纤维成分中覆盖在所述脂质斑块表面的纤维帽厚度以及所述脂质斑块的脂质负荷；
    确定子模块，用于基于所述纤维帽厚度以及所述脂质负荷，确定所述冠状动脉斑块的状态。
  11. 根据权利要求10所述的装置，其特征在于，所述确定子模块用于：
    基于所述脂质负荷与所述纤维帽厚度，根据下述公式计算脂帽比，
    脂帽比＝脂质负荷/纤维帽厚度；
    基于所述脂帽比，评价所述冠状动脉斑块的状态。
  12. 根据权利要求11所述的装置，其特征在于，
    所述图像获取模块用于针对目标帧的所述光学相干断层图像，分别获取该帧图像前、以及该帧图像后的若干帧连续图像，
    所述计算子模块，分别计算连续多帧所述光学相干断层图像的所述纤维成 分的纤维帽厚度以及脂质负荷，并确定多帧所述光学相干断层图像的纤维帽厚度中位数以及脂质负荷平均值，
    所述确定子模块，以脂质负荷平均值以及所述纤维帽厚度中位数，计算所述脂帽比，以整个斑块计算得到的最大脂帽比作为该冠状动脉斑块的脂帽比，评价该冠状动脉斑块的状态。
  13. 根据权利要求12所述的装置，其特征在于，所述确定子模块在所述脂帽比为第一阈值以上时，判断所述冠状动脉斑块为不稳定斑块。
  14. 根据权利要求13所述的装置，其特征在于，所述确定子模块除了所述脂帽比之外，还结合血流储备分数评价所述状态。
  15. 根据权利要求14所述的装置，其特征在于，所述血流储备分数是基于光学相干断层影像得到的血流储备分数，
    所述确定子模块在所述脂帽比为第一阈值以上，且所述血流储备分数第二阈值以下时，判断所述冠状动脉斑块为不稳定斑块。
  16. 根据权利要求10所述的装置，其特征在于，所述识别模块通过斑块识别模型对所述光学相干断层图像进行识别，其中，所述斑块识别模型通过深度学习，基于样本训练得到。
  17. 一种电子设备，其特征在于，包括：
    处理器；和
    存储器，在所述存储器中存储有计算机程序指令，
    其中，在所述计算机程序指令被所述处理器运行时，使得所述处理器执行以下步骤：
    步骤S1，获取待评估的冠状动脉斑块的光学相干断层图像；
    步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
    步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
  18. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序指令，所述计算机程序指令被处理器运行时，使得所述处理器执行以下步骤：
    步骤S1，获取待评估的冠状动脉斑块的光学相干断层图像；
    步骤S2，对于所述光学相干断层图像进行识别，确定纤维成分与脂质斑块；
    步骤S3，基于所述纤维成分以及所述脂质斑块的脂质负荷，评价所述冠状动脉斑块的状态。
PCT/CN2022/089544 2021-04-28 2022-04-27 冠状动脉斑块状态评估方法、装置、电子设备 WO2022228463A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2023557182A JP2024513722A (ja) 2021-04-28 2022-04-27 冠動脈プラークの状態の評価方法、装置、電子機器

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110466164.3A CN113096115B (zh) 2021-04-28 2021-04-28 冠状动脉斑块状态评估方法、装置、电子设备
CN202110466164.3 2021-04-28

Publications (1)

Publication Number Publication Date
WO2022228463A1 true WO2022228463A1 (zh) 2022-11-03

Family

ID=76681337

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/089544 WO2022228463A1 (zh) 2021-04-28 2022-04-27 冠状动脉斑块状态评估方法、装置、电子设备

Country Status (3)

Country Link
JP (1) JP2024513722A (zh)
CN (1) CN113096115B (zh)
WO (1) WO2022228463A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113096115B (zh) * 2021-04-28 2024-06-04 上海博动医疗科技股份有限公司 冠状动脉斑块状态评估方法、装置、电子设备
CN115063504B (zh) * 2022-08-05 2022-11-18 全景恒升（北京）科学技术有限公司 动脉粥样化斑块识别方法、装置、计算机设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6419659B1 (en) * 2000-02-10 2002-07-16 Medventure Technology Corp Lipid pool aspiration arrangement for the treatment of vulnerable atherosclerosis plaque
CN106056126A (zh) * 2015-02-13 2016-10-26 西门子公司 医学成像中的斑块易损性评定
CN106974622A (zh) * 2017-04-06 2017-07-25 上海交通大学 基于光学相干断层成像的斑块稳定性测量方法及系统
CN111145173A (zh) * 2019-12-31 2020-05-12 上海联影医疗科技有限公司 一种冠脉造影图像的斑块识别方法、装置、设备及介质
CN113096115A (zh) * 2021-04-28 2021-07-09 博动医学影像科技（上海）有限公司 冠状动脉斑块状态评估方法、装置、电子设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107993221B (zh) * 2017-11-16 2021-11-02 济南大学 心血管光学相干断层oct图像易损斑块自动识别方法
CN108109149A (zh) * 2017-12-14 2018-06-01 河北大学 一种冠状动脉oct图像自动分割方法
CN108052909B (zh) * 2017-12-15 2021-02-02 中国人民解放军总医院 一种基于心血管oct影像的薄纤维帽斑块自动检测方法和装置
US11205264B2 (en) * 2019-10-15 2021-12-21 GE Precision Healthcare LLC Systems and methods for multi-label segmentation of cardiac computed tomography and angiography images using deep neural networks

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6419659B1 (en) * 2000-02-10 2002-07-16 Medventure Technology Corp Lipid pool aspiration arrangement for the treatment of vulnerable atherosclerosis plaque
CN106056126A (zh) * 2015-02-13 2016-10-26 西门子公司 医学成像中的斑块易损性评定
CN106974622A (zh) * 2017-04-06 2017-07-25 上海交通大学 基于光学相干断层成像的斑块稳定性测量方法及系统
CN111145173A (zh) * 2019-12-31 2020-05-12 上海联影医疗科技有限公司 一种冠脉造影图像的斑块识别方法、装置、设备及介质
CN113096115A (zh) * 2021-04-28 2021-07-09 博动医学影像科技（上海）有限公司 冠状动脉斑块状态评估方法、装置、电子设备

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
YIN YUNZHI , CHEN YANHAO , JIN CHAOLIN: "Correlation Analysis of CT Arteriography in Carotid Plaque Characteristics and Risk Factors of Ischemic Cerebrovascular Disease", THE JOURNAL OF PRACTICAL MEDICINE, vol. 29, no. 10, 25 May 2013 (2013-05-25), pages 1616 - 1618, XP055982654, ISSN: 1006-5725, DOI: 10.3969/j.issn.1006-5725.2013.10.029 *
ZHANG LI-WEI;GAI LU-YUE: "Intravascular Optical Coherence Tomography in Detecting Vulnerable Coronary Plaque:an Update", ACADEMIC JOURNAL OF SECOND MILITARY MEDICAL UNIVERSITY, vol. 35, no. 6, 20 June 2014 (2014-06-20), pages 662 - 667, XP055982652, ISSN: 0258-879X, DOI: 10.3724/sp.J.1008.2014.00662 *

Also Published As

Publication number Publication date
JP2024513722A (ja) 2024-03-27
CN113096115B (zh) 2024-06-04
CN113096115A (zh) 2021-07-09

Similar Documents

Publication Publication Date Title
WO2022228463A1 (zh) 冠状动脉斑块状态评估方法、装置、电子设备
ES2715013T3 (es) Medición automática de lesiones en imágenes médicas
JP6235583B2 (ja) 画像獲得データから肝線維症を検出及びステージ決定する方法
Cuspidi et al. Reduced nocturnal fall in blood pressure, assessed by two ambulatory blood pressure monitorings and cardiac alterations in early phases of untreated essential hypertension
Saba et al. Accurate cloud-based smart IMT measurement, its validation and stroke risk stratification in carotid ultrasound: A web-based point-of-care tool for multicenter clinical trial
KR20170017614A (ko) 의료 영상 기반의 질환 진단 정보 산출 방법 및 장치
Yoon et al. A pilot trial to evaluate the clinical usefulness of contrast-enhanced ultrasound in predicting renal outcomes in patients with acute kidney injury
Ge et al. Clinical value of real‑time elastography quantitative parameters in evaluating the stage of liver fibrosis and cirrhosis
Wang et al. Evaluation of the regional ventricular systolic function by two-dimensional strain echocardiography in gestational diabetes mellitus (GDM) fetuses with good glycemic control
Cahill et al. Wave reflections in the umbilical artery measured by Doppler ultrasound as a novel predictor of placental pathology
Rahaghi et al. Quantification of arterial and venous morphologic markers in pulmonary arterial hypertension using CT imaging
US20220215542A1 (en) Method, device and computer-readable medium for automatically detecting hemodynamically significant coronary stenosis
Okamoto et al. Predictors of confirmatory test results for the diagnosis of primary hyperaldosteronism in hypertensive patients with an aldosterone-to-renin ratio greater than 20. The SHRIMP study
Sabatino et al. Echocardiographic normal reference ranges for non-invasive myocardial work parameters in pediatric age: results from an international multi-center study
Olaisen et al. Automatic measurements of left ventricular volumes and ejection fraction by artificial intelligence: clinical validation in real time and large databases
Pellikka Stress echocardiography for the diagnosis of coronary artery disease: progress towards quantification
Liu et al. Quantitative assessment of cardiac function in fetuses of women with maternal gestational thyroid dysfunction using VVI echocardiography
Maragna et al. Artificial intelligence based multimodality imaging: a new frontier in coronary artery disease management
Sunyecz et al. Defining coronary flow patterns: comprehensive automation of transthoracic Doppler coronary blood flow
Revathi et al. A deep learning based approach for diagnosing coronary inflammation with multi-scale coronary response dynamic balloon tracking (MSCAR-DBT) based artery segmentation in coronary computed tomography angiography (CCTA)
Liu et al. Characteristics of myocardial perfusion in type 2 diabetes mellitus and its association with left ventricular diastolic dysfunction: a study of myocardial contrast echocardiography
Tosuwan et al. Assessment of left atrial myocardial deformation using two-dimensional speckle-tracking echocardiography in cats with cardiogenic and non-cardiogenic arterial thromboembolism
Bossenbroek et al. Improvement of automated analysis of coronary Doppler echocardiograms
Zhang et al. Calculation of left ventricular ejection fraction using an 8-layer residual U-Net with deep supervision based on cardiac CT angiography images versus echocardiography: a comparative study
Wu et al. Computed tomography myocardial perfusion imaging of patients with left ventricular hypertrophy in hypertension: A retrospective study

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22794933

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023557182

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22794933

Country of ref document: EP

Kind code of ref document: A1