A plaque detection method, device and terminal device based on OCT image

Abstract

The present application is applicable to the field of image processing technology, and provides a plaque detection method, device and terminal device based on OCT images, the method comprising: acquiring a target optical coherence tomography image, calculating and determining the light attenuation coefficient of the target optical coherence tomography image, calculating an enhanced light attenuation index according to the light attenuation coefficient, calculating a true value corresponding to a mark according to the enhanced light attenuation index, and determining the target plaque type of the target optical coherence tomography image according to the true value. The present application determines the corresponding enhanced light attenuation index based on the relationship between the attenuation coefficient and a variety of unstable plaques, thereby accurately detecting and determining different types of unstable plaques, and improving the accuracy of plaque detection based on OCT images.

Description

Technical Field

[0001] The present application belongs to the field of image detection technology, and in particular, relates to a plaque detection method, apparatus and terminal device based on OCT images. Background Art

[0002] Optical Coherence Tomography (OCT) is a device that performs diagnostic imaging based on optical principles. The OCT images it generates are often used as a diagnostic tool in percutaneous coronary intervention (PCI) surgery.

[0003] Based on the imaging principle of OCT images, related studies proposed the plaque attenuation index (IPA) method and verified that IPA can be used to distinguish between fibrolipid (FA) and thin-film fibroatheroma (TCFA).

[0004] However, unstable plaques also include cholesterol crystals, macrophages, plaque rupture, plaque erosion, and calcified nodules, which may also lead to acute coronary clinical events (such as unstable angina, myocardial infarction, sudden death) and clinical events secondary to ischemic heart disease. Therefore, how to identify different types of unstable plaques based on OCT images is an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present application provide a plaque detection method, apparatus, terminal device and storage medium based on OCT images, which can solve the problem of determining different types of unstable plaques based on OCT image detection, thereby improving the detection accuracy of unstable plaque types.

[0006] In a first aspect, an embodiment of the present application provides a plaque detection method based on OCT images, comprising:

[0007] Acquire a target optical coherence tomography image; wherein the target optical coherence tomography image is a vascular optical coherence tomography image in polar coordinates carrying a marker of a plaque type; wherein the plaque type includes normal tissue, thin-film fibrous atheromatous plaque, cholesterol crystal, macrophage, plaque rupture, plaque erosion or calcified nodule;

[0008] Calculating and determining the light attenuation coefficient of the target optical coherence tomography image;

[0009] Calculate the enhanced light decay index according to the light decay coefficient;

[0010] Calculate the real value corresponding to the mark according to the enhanced light attenuation index;

[0011] A target plaque type of the target optical coherence tomography image is determined according to the true value.

[0012] Firstly, the plaque types contained in the target optical coherence tomography image are preliminarily identified and corresponding marks are added. The light attenuation coefficient of the target optical coherence tomography image is calculated, and the corresponding enhanced light attenuation index is determined based on the light attenuation coefficient. The true value corresponding to each mark is determined based on the enhanced light attenuation index. According to the true value, it is determined whether the plaque type corresponding to each mark is correct, and then the target plaque type of the target optical coherence tomography image is determined. The corresponding enhanced light attenuation index is determined based on the relationship between the attenuation coefficient and multiple unstable plaques, so that different types of unstable plaques can be accurately detected and determined, thereby improving the accuracy of plaque detection based on OCT images.

[0013] In one embodiment, the step of calculating the enhanced light decay index according to the light decay coefficient includes:

[0014] Determining a maximum light attenuation coefficient on each A line in the target optical coherence tomography image;

[0015] An enhanced light decay index of the target optical coherence tomography image is calculated based on the maximum light decay coefficient.

[0016] In one embodiment, the step of calculating the enhanced light decay index of the target optical coherence tomography image based on the maximum light decay coefficient includes:

[0017] Using the maximum light decay coefficient, updating the pixel value of the corresponding pixel point in the target optical coherence tomography image to obtain a maximum light decay coefficient map;

[0018] Performing filtering processing on the maximum light decay coefficient based on the maximum light decay coefficient map to obtain a target area image;

[0019] An enhanced light attenuation index is calculated based on the number of A lines in the target area image and a light attenuation coefficient in the target area image that meets a preset condition.

[0020] In one embodiment, the calculating and determining the light attenuation coefficient of the target optical coherence tomography image includes:

[0021] The light attenuation coefficient of each pixel in the target optical coherence tomography image is calculated based on the light attenuation model in the polar coordinate system.

[0022] In one embodiment, determining the target plaque type of the target optical coherence tomography image according to the true value comprises:

[0023] The mark of the plaque type as normal tissue is taken as false, and the mark of other plaque types is taken as true, and the true value corresponding to each mark is calculated based on the enhanced light attenuation index; wherein the other plaque types are plaque types other than the normal tissue.

[0024] In one embodiment, determining the target plaque type of the target optical coherence tomography image according to the true value comprises:

[0025] When it is detected that the true value is greater than or equal to a preset true value threshold, determining the plaque type corresponding to the mark as a correct plaque type;

[0026] When it is detected that the plaque type is normal tissue, determining that the target optical coherence tomography image does not contain unstable plaques, and generating a normal image notification;

[0027] When it is detected that the plaque type is not a normal tissue, the plaque type corresponding to the mark is used as the target plaque type, and a corresponding plaque abnormality notification is generated.

[0028] In one embodiment, determining the target plaque type of the target optical coherence tomography image according to the true value further includes:

[0029] When it is detected that the true value is less than a preset true value threshold, the plaque type corresponding to the mark is determined to be an erroneous plaque type, and the corresponding target plaque type is determined according to the enhanced light attenuation index.

[0030] In a second aspect, an embodiment of the present application provides a plaque detection device based on OCT images, comprising:

[0031] An image acquisition module, used to acquire a target optical coherence tomography image; wherein the target optical coherence tomography image is a vascular optical coherence tomography image in polar coordinates carrying a marker of a plaque type; wherein the plaque type includes normal tissue, thin-film fibrous atheromatous plaque, cholesterol crystal, macrophage, plaque rupture, plaque erosion or calcified nodule;

[0032] A first calculation module, used for calculating and determining a light attenuation coefficient of the target optical coherence tomography image;

[0033] A second calculation module, used for calculating an enhanced light decay index according to the light decay coefficient;

[0034] A third calculation module, configured to calculate a true value corresponding to the mark according to the enhanced light attenuation index;

[0035] A type determination module is used to determine the target plaque type of the target optical coherence tomography image according to the true value.

[0036] In one embodiment, the second calculation module includes:

[0037] A coefficient determination unit, used to determine the maximum light attenuation coefficient on each A line in the target optical coherence tomography image;

[0038] An index calculation unit is used to calculate the enhanced light attenuation index of the target optical coherence tomography image based on the maximum light attenuation coefficient.

[0039] In one embodiment, the index calculation unit includes:

[0040] An image updating subunit, configured to update the pixel values ​​of corresponding pixels in the target optical coherence tomography image with the maximum light decay coefficient to obtain a maximum light decay coefficient map;

[0041] An area determination subunit, configured to filter the maximum light attenuation coefficient based on the maximum light attenuation coefficient map to obtain a target area image;

[0042] The index calculation subunit is used to calculate the enhanced light attenuation index based on the number of A lines in the target area image and the light attenuation coefficient that meets the preset conditions in the target area image.

[0043] In one embodiment, the first computing module includes:

[0044] The coefficient calculation unit is used to calculate the light attenuation coefficient of each pixel in the target optical coherence tomography image based on the light attenuation model in the polar coordinate system.

[0045] In one embodiment, the third calculation module includes:

[0046] A true value calculation unit is used to take the mark of the plaque type as normal tissue as false, and the mark of other plaque types as true, and calculate the true value corresponding to each mark based on the enhanced light attenuation index; wherein the other plaque types are plaque types other than the normal tissue.

[0047] In one embodiment, the type determination module includes:

[0048] A type determination unit, configured to determine that the plaque type corresponding to the mark is a correct plaque type when it is detected that the true value is greater than or equal to a preset true value threshold;

[0049] A first type determination unit is used to determine that the target optical coherence tomography image does not contain unstable plaques when the plaque type is detected to be normal tissue, and to generate a normal image notification;

[0050] The second type determination unit is used to generate a corresponding plaque abnormality notification by taking the plaque type corresponding to the mark as the target plaque type when it is detected that the plaque type is not normal tissue.

[0051] In one embodiment, the type determination module further includes:

[0052] The second type determination unit is used to determine that the plaque type corresponding to the mark is an erroneous plaque type when it is detected that the true value is less than a preset true value threshold, and determine the corresponding target plaque type according to the enhanced light attenuation index.

[0053] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the plaque detection method based on OCT images as described in any one of the first aspects above is implemented.

[0054] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the OCT image-based plaque detection method as described in any one of the first aspects above is implemented.

[0055] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the OCT image-based plaque detection method described in any one of the first aspects above.

[0056] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 is a flow chart of a plaque detection method based on OCT images provided in an embodiment of the present application;

[0059] Figure 2 Figure A in the figure is a light attenuation coefficient diagram determined based on OCT image calculation provided in an embodiment of the present application;

[0060] Figure 2Figure B is a maximum light attenuation coefficient diagram determined based on OCT image calculation provided in an embodiment of the present application;

[0061] Figure 2 Figure C is a target area image determined by calculation based on the OCT image provided in an embodiment of the present application;

[0062] Figure 3 is a flow chart of step S103 of the plaque detection method based on OCT images provided in an embodiment of the present application;

[0063] Figure 4 is a flow chart of step S1032 of the plaque detection method based on OCT images provided in an embodiment of the present application;

[0064] Figure 5 is a schematic diagram of the true values ​​of different plaque types determined based on eIPA calculations provided in an embodiment of the present application;

[0065] Fig. 6A is a schematic diagram of the true value of plaque combination 1 determined based on eIPA calculation provided in an embodiment of the present application;

[0066] Figure 6B is a schematic diagram of the true value of plaque combination 2 determined based on eIPA calculation provided in an embodiment of the present application;

[0067] Figure 6C is a schematic diagram of the true value of plaque combination 3 determined based on eIPA calculation provided in an embodiment of the present application;

[0068] Figure 7 Schematic diagram of the structure of the plaque detection device based on OCT image provided in the embodiment of the present application

[0069] Figure 8 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0071] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0072] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0073] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0074] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0075] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0076] The OCT image-based plaque detection method provided in the embodiments of the present application can be applied to terminal devices such as mobile phones, tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). The embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0077] Figure 1 A schematic flow chart of a plaque detection method based on OCT images provided in the present application is shown. As an example but not a limitation, the method can be applied to the above-mentioned laptop computer.

[0078] S101. Acquire a target optical coherence tomography image; wherein the target optical coherence tomography image is a vascular optical coherence tomography image in polar coordinates carrying a marker of a plaque type; wherein the plaque type includes normal tissue, thin-film fibrous atherosclerotic plaque, cholesterol crystals, macrophages, plaque rupture, plaque erosion or calcified nodules.

[0079] Specifically, an optical coherence tomography (OCT) instrument is a precision measuring instrument that uses an optical measurement method, and its working principle is very similar to that of ultrasound. The OCT instrument can measure tissues and distances with a resolution of ≤10μm. First, the blood vessels are scanned by an OCT instrument that is connected to the current terminal for communication, and an optical coherence tomography image of the blood vessels in polar coordinates generated and sent by the OCT instrument (hereinafter referred to as the OCT image) is obtained. The type of plaque contained in the OCT image is determined by preliminary identification, and corresponding markers are added. Among them, plaque types include but are not limited to normal tissue, thin film fibrous atherosclerotic plaques, cholesterol crystals, macrophages, plaque ruptures, plaque erosions or calcified nodules. Among them, normal tissue includes healthy tissue (Healthy-vessel), fibrolipid (FA), that is, stable plaques. Other plaque types other than normal tissue are unstable plaques.

[0080] Specifically, when the blood vessels are scanned by an OCT device, multiple frames of blood vessel OCT images can be generated. In order to improve the stability of the detection results of plaque types, before the initial identification of the plaque type in the OCT image, the OCT images obtained by scanning need to be screened first. Since the unclear lumen or the presence of thrombus in the blood vessel can easily affect the clarity of the OCT image, it is necessary to screen the OCT images with clear blood vessel lumen and no thrombus.

[0081] As an example but not a limitation, since different plaque types in blood vessels are characterized differently, the plaque type in the OCT image can be preliminarily identified and a corresponding label can be added based on the characterization of the plaque type in the OCT image, including: healthy tissue usually has a normal three-layer membrane structure, that is, a plaque in which the inner membrane, the middle membrane and the outer membrane can be seen, and a label indicating that the plaque type is normal tissue is added accordingly. Fibrous lipid FA is a plaque containing lipids and a fibrous membrane thickness greater than 65um, and a label indicating that the plaque type is normal tissue is added accordingly; thin film fibrous atherosclerotic plaque TCFA is a plaque containing lipids and a fibrous membrane thickness less than or equal to 65um, and a label indicating that the plaque type is TCFA is added accordingly; cholesterol crystals are usually plaques with thin linear or dot-like structures with high signal intensity and low attenuation, and a label indicating that the plaque type is cholesterol crystals is added accordingly; macrophages are usually plaques with dot-like or strip-like structures with high reflectivity and strong attenuation, and radioactive light shadows are often formed behind the dot-like areas with high signals, and a label indicating that the plaque type is normal tissue is added accordingly. Plaque type is a marker for macrophages; plaque rupture is usually a plaque in which the fibrous cap of the lipid plaque is interrupted continuously, resulting in the core of the plaque that is prone to thrombosis being exposed to the blood flow, and the corresponding plaque type is added as a marker for plaque rupture; plaque erosion is usually a plaque with an intact fibrous cap, no plaque rupture, with or without thrombosis, and the plaque surface is irregular, and the corresponding plaque type is added as a marker for plaque erosion; calcified nodules are usually single or multiple calcified area plaques, which are prone to protrude into the lumen with rupture of the fibrous cap, forming sharp protruding corners, accompanied by thrombosis, and the corresponding plaque type is added as a marker for calcified nodules.

[0082] As an example but not limitation, in other cases such as failure to preliminarily identify the plaque type or identification failure, a corresponding mark may be added to the OCT image based on the plaque type input by the user.

[0083] S102: Calculate and determine the light attenuation coefficient of the target optical coherence tomography image.

[0084] Specifically, since the target optical coherence tomography image is a vascular optical coherence tomography image in polar coordinates carrying a marker of the plaque type, the light attenuation coefficient of each pixel in a single-frame target optical coherence tomography image can be calculated and determined based on the light attenuation model in polar coordinates (hereinafter referred to as the light attenuation model).

[0085] In one embodiment, the calculating and determining the light attenuation coefficient of the target optical coherence tomography image includes:

[0086] The light attenuation coefficient of each pixel in the target optical coherence tomography image is calculated based on the light attenuation model in the polar coordinate system.

[0087] Specifically, the light attenuation coefficient of each pixel in the target optical coherence tomography image is calculated based on the light attenuation model in polar coordinates, and the pixel value of each pixel is updated according to the light attenuation coefficient of each pixel in the target optical coherence tomography image, so that the light attenuation coefficient diagram corresponding to the target optical coherence tomography image can be obtained (such as Figure 2 A).

[0088] Among them, the light attenuation model is expressed as follows:

[0089]

[0090]

[0091]

[0092] In the formula, I 0 represents the scale factor, r represents the image depth, T(r) represents the longitudinal point spread function, z 0 represents the beam waist position (value is 0), z R represents the Rayleigh length (value is 3mm), z c Indicates the scanning center point (value is 0), z w Indicates the half width of the roll-off function (the value is 10um), μ t Represents the light attenuation coefficient. By taking the logarithm of both sides of formula (1) and using the least squares method, the light attenuation coefficient μ can be calculated. t .

[0093] Figure 2 A is a diagram of the light attenuation coefficient calculated based on the OCT image.

[0094] Figure 2 In A, the corresponding light attenuation coefficient is displayed by different brightness values, where the highlighted area is an area with a larger light attenuation coefficient value in the current OCT image.

[0095] S103: Calculate an enhanced light decay index according to the light decay coefficient.

[0096] Specifically, relevant studies have verified that based on the relationship between the attenuation coefficient and the relevant components of unstable plaques, it can be determined that different plaque types have different light attenuation coefficients, and the corresponding settings are based on the light attenuation coefficient to distinguish different plaque types. The plaque attenuation index (IPA) calculated based on the light attenuation coefficient can distinguish between unstable plaques - thin fibrous cap atherosclerotic plaques (TCFA) and stable plaques - atherosclerotic plaques (FA).

[0097] The calculation method of IPA is as follows:

[0098]

[0099] Where x represents the preset light attenuation threshold, the value range is [5,12], N(μ t >x) indicates the number of light decay coefficients greater than the preset light decay threshold, N total Indicates the total maximum light attenuation coefficients of all A lines in the OCT image (for example, if the OCT image contains 500 A lines, the corresponding value is 500).

[0100] Specifically, based on the calculation method and definition of IPA, it can be seen that for plaques with larger curvatures, the calculated IPA has a higher accuracy. For plaques with smaller curvatures, regardless of the type and severity of the plaque, the corresponding calculated IPA value will be affected (specifically, it will be smaller). Therefore, it is difficult for IPA to accurately detect various types of unstable plaques with inconsistent curvatures.

[0101] Specifically, in view of the above situation, a method for calculating the enhanced light decay index is proposed. The calculated enhanced light decay index eIPA is the ratio of the number of light decay coefficients greater than the preset light decay threshold in the target area image to the number of all light decay coefficients in the target area image. Based on the enhanced light decay index, it is detected whether the type of plaque corresponding to the mark is correct, so as to effectively calculate the statistical characteristics of the light decay coefficients corresponding to plaques of different curvatures, and realize the effective detection of different types of unstable plaques.

[0102] like Figure 3 As shown, in one embodiment, the step S103 of calculating the enhanced light decay index according to the light decay coefficient includes:

[0103] S1031, determining the maximum light attenuation coefficient on each A line in the target optical coherence tomography image;

[0104] S1032: Calculate an enhanced light attenuation index of the target optical coherence tomography image based on the maximum light attenuation coefficient.

[0105] Specifically, a light attenuation coefficient selection operation is first performed on the light attenuation coefficient map corresponding to the target optical coherence tomography image, and only the light attenuation coefficient value between the inner membrane and the outer elastic membrane is retained in each frame of the light attenuation coefficient map obtained by screening, and the maximum light attenuation coefficient on each A line in the light attenuation coefficient map is obtained by screening.

[0106] As an example but not limitation, it is assumed that each frame of OCT image includes 500 A lines, each A line contains multiple light attenuation coefficients, and the light attenuation coefficients on the 500 A lines can be determined through screening, corresponding to a 1*500 light attenuation coefficient matrix, which contains 500 maximum light attenuation coefficient vectors.

[0107] Specifically, the maximum light decay coefficient of each line A in the light decay coefficient diagram is processed accordingly to obtain the area with the maximum light decay coefficient in the light decay coefficient diagram (i.e., the image of the target area). Based on the image of the target area, the enhanced light decay index of the target optical coherence tomography image is calculated and determined.

[0108] like Figure 4 As shown, in one embodiment, the step S1032 of calculating the enhanced light decay index of the target optical coherence tomography image based on the maximum light decay coefficient includes:

[0109] S10321. Update the pixel value of the corresponding pixel point in the target optical coherence tomography image with the maximum light attenuation coefficient to obtain a maximum light attenuation coefficient map;

[0110] S10322, filtering the maximum light attenuation coefficient based on the maximum light attenuation coefficient map to obtain a target area image;

[0111] S10323. Calculate an enhanced light attenuation index based on the number of A lines in the target area image and the light attenuation coefficient in the target area image that meets a preset condition.

[0112] Specifically, the pixel value of the corresponding pixel point in the target optical coherence tomography image is updated with the maximum light decay coefficient on each line A in the light decay coefficient map to obtain the maximum light decay coefficient map (such as Figure 2 The annular area in B is the ring formed by the maximum light coefficient), and based on the maximum light decay coefficient map, the maximum light decay coefficient is filtered (including but not limited to mean filtering) to obtain the area with the largest light decay coefficient, and then the area with a fixed step size (the fixed step size can be set according to actual needs, for example, the fixed step size is set to 5 or 6) is taken out as the target area image (such as Figure 2 C), identify and determine the number of A lines in the target area image, and the light attenuation coefficient that meets the preset conditions in the target area image, so as to calculate the enhanced light attenuation index.

[0113] In this embodiment, the preset condition is a light decay coefficient greater than a preset light decay threshold.

[0114] Specifically, the enhanced light attenuation index is calculated as follows:

[0115]

[0116] In the formula, α×N total represents the number of A lines in the target area image, α represents the proportional coefficient of the target area image in the OCT image, and its value is 1. or Indicates the number of light attenuation coefficients in the target area image that are greater than the preset light attenuation threshold.

[0117] S104: Calculate a real value corresponding to the mark according to the enhanced light attenuation index.

[0118] Specifically, when calculating and determining the enhanced light attenuation index of the target optical coherence tomography image, it is necessary to determine the authenticity of the plaque type corresponding to each mark by enhancing the light attenuation index, that is, taking the mark of normal tissue as false, taking the mark of other plaque types except normal tissue as true, and calculating and determining the true value of the plaque type corresponding to each mark. The true value is specifically AUC-Value.

[0119] As an example but not limitation, the P-Value, sensitivity and specificity of the plaque type corresponding to each marker may also be determined based on the enhanced light attenuation index.

[0120] S105. Determine a target plaque type of the target optical coherence tomography image according to the true value.

[0121] Specifically, the true value is compared with a preset true value threshold, and whether the target plaque type of the target optical coherence tomography image is the plaque type corresponding to the mark is determined according to the comparison result.

[0122] In one embodiment, determining the target plaque type of the target optical coherence tomography image according to the true value comprises:

[0123] The mark of the plaque type as normal tissue is taken as false, and the mark of other plaque types is taken as true, and the true value corresponding to each mark is calculated based on the enhanced light attenuation index; wherein the other plaque types are plaque types other than the normal tissue.

[0124] Specifically, the P-value refers to the probability of an observed value or a value more extreme than the observed value occurring when the null hypothesis is true, and is a commonly used statistical indicator; the sensitivity value is the proportion of identified positive samples (or true samples) among the total positive samples; the specificity value is the proportion of identified negative samples among the total negative samples (or false samples); the AUC value represents the area under the receiver operating characteristic curve, which is the area under the curve drawn according to a series of different binary classification methods (cutoff values ​​or decision thresholds), with the true positive rate (sensitivity) as the ordinate and the false positive rate (1-specificity) as the abscissa. After calculating and determining the enhanced light attenuation index, based on the relationship between the light attenuation coefficient and different plaque types, the marker of the plaque type of the vascular optical coherence tomography image is normal tissue as the false (or negative sample), and the markers of other plaque types are taken as the true (or positive sample). The true value (mainly AUC value) of the plaque type corresponding to each marker under the optimal coefficient is calculated according to the enhanced light attenuation index; among which, other plaque types are plaque types other than normal tissue corresponding to the marker.

[0125] For example, when the plaque type corresponding to the marker is TCFA, normal tissue is taken as false, TCFA is taken as true, and the true value corresponding to TCFA under the optimal coefficient is calculated according to the enhanced light attenuation index. Alternatively, when the plaque type corresponding to the marker is plaque erosion, normal tissue is taken as false, plaque erosion is taken as true, and the true value corresponding to plaque erosion under the optimal coefficient is calculated according to the enhanced light attenuation index.

[0126] Specifically, the optimal coefficients include a preset light attenuation threshold x, a proportional coefficient α of the target area image in the OCT image, and an enhanced light attenuation index eIPA threshold. The optimal coefficients can be specifically set according to the plaque type corresponding to the marker. For example, if TCFA is true and the normal tissue type is false, the corresponding optimal coefficients include: x=9.5, α=1 / 4, and an enhanced light attenuation index eIPA threshold of 330 (filter kernel 30).

[0127] In one embodiment, determining the target plaque type of the target optical coherence tomography image according to the true value comprises:

[0128] When it is detected that the true value is greater than or equal to a preset true value threshold, determining the plaque type corresponding to the mark as a correct plaque type;

[0129] When it is detected that the plaque type is normal tissue, determining that the target optical coherence tomography image does not contain unstable plaques, and generating a normal image notification;

[0130] When it is detected that the plaque type is not a normal tissue, the plaque type corresponding to the mark is used as the target plaque type, and a corresponding plaque abnormality notification is generated.

[0131] Specifically, when the true value of the plaque type corresponding to the mark is detected to be greater than or equal to the preset true value threshold, it is determined that the initial identification of the plaque type is successful, that is, the plaque type corresponding to the mark is determined to be the correct plaque type. Correspondingly, when the plaque type corresponding to the mark is detected to be normal tissue, the plaque in the target optical correlation tomography image is determined to be normal tissue, that is, it does not contain unstable plaques, and a normal image notification is generated accordingly (the normal image notification includes but is not limited to text, voice or image prompt information that normal tissue is contained in the image).

[0132] The preset true value threshold is specifically set according to actual needs. In general, when the true value AUC is greater than 0.5, the detection performance is more accurate. Based on multiple experimental verifications, in this embodiment, the preset true value threshold is set to 0.7. For example, when the true value of the plaque type corresponding to the mark is detected to be 0.75, the plaque type corresponding to the mark is determined to be the correct plaque type, and the plaque type is used as the target plaque type.

[0133] Specifically, when the plaque type is detected to be other than normal tissue, the plaque in the target optical correlation tomography image is determined to be an unstable plaque, the plaque type corresponding to the above-mentioned mark is used as the target plaque type, and a corresponding plaque abnormality notification is generated (the plaque abnormality notification includes but is not limited to text, voice or image prompt information that the image contains unstable plaques and the target plaque type corresponding to the unstable plaque).

[0134] In one embodiment, determining the target plaque type of the target optical coherence tomography image according to the true value further includes:

[0135] When it is detected that the true value is less than a preset true value threshold, the plaque type corresponding to the mark is determined to be an erroneous plaque type, and the corresponding target plaque type is determined according to the enhanced light attenuation index.

[0136] Specifically, when it is detected that the true value of the plaque type corresponding to the mark is less than the preset true value threshold, it is determined that the plaque type corresponding to the mark is initially identified incorrectly, and the corresponding target plaque type is re-determined according to the enhanced light attenuation index based on the relationship between the light attenuation coefficient and the relevant components of the unstable plaque.

[0137] After multiple times of using normal tissue as false (or negative samples) and other plaque types as true (or positive samples), the authenticity of unstable plaques was calculated based on eIPA (e.g. Figure 5As shown in the figure, it can be determined that the AUC values ​​of eIPA for determining unstable plaque types are all higher than 0.75, which are significantly different from those of IPA for detecting unstable plaque types. Among them, the AUC values ​​of TCFA, cholesterol crystallization, plaque rupture and plaque erosion are all higher than 0.8. The calculation results show that the detection accuracy of eIPA for different types of unstable plaques is higher than that of IPA, and the detection accuracy of eIPA for different types of unstable plaques is higher and more stable.

[0138] Based on the importance of unstable plaques in OCT image detection projects, a variety of different types of unstable plaques are combined, and the authenticity of the test results under different unstable plaque combinations is determined by eIPA detection. First, considering that TCFA is a more dangerous unstable plaque in clinical practice, TCFA alone is used as a true (or positive sample), and other types of plaques are used as false (or negative samples) to obtain plaque combination 1; secondly, based on the correlation between plaques and before and after the event, the plaque types in which TCFA, cholesterol crystals, and macrophages appear before the event are used as plaque combination 2. In addition, on the basis of these three types of plaques, plaque types that usually appear after the event are added: plaque rupture and plaque erosion, etc., as plaque combination 3, including:

[0139] Plaque combination 1: positive: TCFA; negative: FA, healthy tissue, cholesterol crystals, macrophages, plaque rupture, plaque erosion, calcified nodules;

[0140] Plaque combination 2: Positive: TCFA, cholesterol crystals, macrophages; Negative: FA, healthy tissue, plaque rupture, plaque erosion, calcified nodules;

[0141] Plaque combination 3: Positive: TCFA, cholesterol crystals, macrophages, plaque rupture, plaque erosion; Negative: FA, healthy tissue, calcified nodules.

[0142] For plaque combination 1, the optimal parameters are: preset light attenuation threshold x = 9.5, the proportional coefficient of the target area image in the OCT image α = 1 / 4, and the enhanced light attenuation index eIPA threshold = 330 (filter kernel 30); the corresponding calculated results include AUC = 0.82, sensitivity = 0.71, specificity = 0.81, and the corresponding AUC curve is as follows Fig. 6A As shown;

[0143] For combination 2, the optimal parameters are: preset light attenuation threshold x = 10, the ratio coefficient of the target area image in the OCT image α = 1 / 2, the enhanced light attenuation index eIPA threshold = 80 (filter kernel 370), and the corresponding calculated results include AUC = 0.7491, sensitivity = 0.69, and specificity = 0.75. The corresponding AUC curve is shown in Figure 6B As shown;

[0144] For combination 3, the optimal parameters are set as follows: preset light attenuation threshold x = 10.5, the ratio coefficient of the target area image in the OCT image is α1 / 3, the enhanced light attenuation index eIPA threshold = 80 (filter kernel 310), AUC = 0.7830, sensitivity = 0.71, specificity = 0.81, and the corresponding AUC curve is shown in Figure 2. Figure 6C shown.

[0145] based on Fig. 6A , Figure 6B and Figure 6C It is found that the eIPA value can effectively detect and distinguish unstable plaques under different types of combinations, thereby improving the detection accuracy of unstable plaques.

[0146] This embodiment adds corresponding tags to the plaque types contained in the initially identified target optical coherence tomography image, calculates the light attenuation coefficient of the target optical coherence tomography image, determines the corresponding enhanced light attenuation index based on the light attenuation coefficient, determines the true value corresponding to each tag based on the enhanced light attenuation index calculation, determines whether the plaque type corresponding to each tag is correct according to the true value, and then determines the target plaque type of the target optical coherence tomography image, and determines the corresponding enhanced light attenuation index based on the relationship between the attenuation coefficient and multiple unstable plaques, thereby accurately detecting and determining different types of unstable plaques, thereby improving the accuracy of plaque detection based on OCT images.

[0147] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0148] Corresponding to the plaque detection method based on OCT images described in the above embodiment, Figure 7 A structural block diagram of a plaque detection device based on OCT images provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0149] Reference Figure 7 , the plaque detection device 100 based on OCT images includes:

[0150] The image acquisition module 101 is used to acquire a target optical coherence tomography image; wherein the target optical coherence tomography image is a vascular optical coherence tomography image in polar coordinates carrying a marker of a plaque type; wherein the plaque type includes normal tissue, thin-film fibrous atheromatous plaque, cholesterol crystal, macrophage, plaque rupture, plaque erosion or calcified nodule;

[0151] A first calculation module 102, configured to calculate and determine a light attenuation coefficient of the target optical coherence tomography image;

[0152] A second calculation module 103, configured to calculate an enhanced light decay index according to the light decay coefficient;

[0153] A third calculation module 104, configured to calculate a real value corresponding to the mark according to the enhanced light attenuation index;

[0154] The type determination module 105 is configured to determine the target plaque type of the target optical coherence tomography image according to the true value.

[0155] In one embodiment, the second calculation module includes:

[0156] A coefficient determination unit, used to determine the maximum light attenuation coefficient on each A line in the target optical coherence tomography image;

[0157] An index calculation unit is used to calculate the enhanced light attenuation index of the target optical coherence tomography image based on the maximum light attenuation coefficient.

[0158] In one embodiment, the index calculation unit includes:

[0159] An image updating subunit, configured to update the pixel values ​​of corresponding pixels in the target optical coherence tomography image with the maximum light decay coefficient to obtain a maximum light decay coefficient map;

[0160] An area determination subunit, configured to filter the maximum light attenuation coefficient based on the maximum light attenuation coefficient map to obtain a target area image;

[0161] The index calculation subunit is used to calculate the enhanced light attenuation index based on the number of A lines in the target area image and the light attenuation coefficient that meets the preset conditions in the target area image.

[0162] In one embodiment, the first computing module includes:

[0163] The coefficient calculation unit is used to calculate the light attenuation coefficient of each pixel in the target optical coherence tomography image based on the light attenuation model in the polar coordinate system.

[0164] In one embodiment, the third calculation module includes:

[0165] A true value calculation unit is used to take the mark of the plaque type as normal tissue as false, and the mark of other plaque types as true, and calculate the true value corresponding to each mark based on the enhanced light attenuation index; wherein the other plaque types are plaque types other than the normal tissue.

[0166] In one embodiment, the type determination module includes:

[0167] A type determination unit, configured to determine that the plaque type corresponding to the mark is a correct plaque type when it is detected that the true value is greater than or equal to a preset true value threshold;

[0168] A first type determination unit is used to determine that the target optical coherence tomography image does not contain unstable plaques when the plaque type is detected to be normal tissue, and to generate a normal image notification;

[0169] The second type determination unit is used to generate a corresponding plaque abnormality notification by taking the plaque type corresponding to the mark as the target plaque type when it is detected that the plaque type is not normal tissue.

[0170] In one embodiment, the type determination module further includes:

[0171] The second type determination unit is used to determine that the plaque type corresponding to the mark is an erroneous plaque type when it is detected that the true value is less than a preset true value threshold, and determine the corresponding target plaque type according to the enhanced light attenuation index.

[0172] This embodiment adds corresponding tags to the plaque types contained in the initially identified target optical coherence tomography image, calculates the light attenuation coefficient of the target optical coherence tomography image, determines the corresponding enhanced light attenuation index based on the light attenuation coefficient, determines the true value corresponding to each tag based on the enhanced light attenuation index calculation, determines whether the plaque type corresponding to each tag is correct according to the true value, and then determines the target plaque type of the target optical coherence tomography image, and determines the corresponding enhanced light attenuation index based on the relationship between the attenuation coefficient and multiple unstable plaques, thereby accurately detecting and determining different types of unstable plaques, thereby improving the accuracy of plaque detection based on OCT images.

[0173] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0174] Figure 8 This is a schematic diagram of the structure of the terminal device provided in this embodiment. Figure 8 As shown, the terminal device 8 of this embodiment includes: at least one processor 80 ( Figure 8 Only one is shown), a memory 81 and a computer program 82 stored in the memory 81 and executable on the at least one processor 80, wherein the processor 80 implements the steps in any of the above-mentioned embodiments of the plaque detection method based on OCT images when executing the computer program 82.

[0175] The terminal device 8 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that Figure 8 It is only an example of the terminal device 8 and does not constitute a limitation on the terminal device 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0176] The processor 80 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0177] In some embodiments, the memory 81 may be an internal storage unit of the terminal device 8, such as a hard disk or memory of the terminal device 8. In other embodiments, the memory 81 may also be an external storage device of the terminal device 8, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device 8. Further, the memory 81 may also include both an internal storage unit of the terminal device 8 and an external storage device. The memory 81 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 81 may also be used to temporarily store data that has been output or is to be output.

[0178] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0179] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0180] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0181] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0182] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0183] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0184] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0185] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0186] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A plaque detection method based on OCT images, characterized in that: include: Acquire a target optical coherence tomography image; wherein the target optical coherence tomography image is a vascular optical coherence tomography image in polar coordinates carrying a marker of a plaque type; wherein the plaque type includes normal tissue, thin-film fibrous atheromatous plaque, cholesterol crystal, macrophage, plaque rupture, plaque erosion or calcified nodule; Calculating and determining the light attenuation coefficient of the target optical coherence tomography image; Determining a maximum light attenuation coefficient on each A line in the target optical coherence tomography image; Using the maximum light decay coefficient, updating the pixel value of the corresponding pixel point in the target optical coherence tomography image to obtain a maximum light decay coefficient map; Performing filtering processing on the maximum light decay coefficient based on the maximum light decay coefficient map to obtain a target area image; Based on the number of A lines in the target area image and the light decay coefficient in the target area image that meets a preset condition, an enhanced light decay index is calculated; The mark of the plaque type being a normal tissue is taken as false, and the mark of other plaque types is taken as true, and the true value corresponding to each mark is calculated based on the enhanced light attenuation index; wherein the other plaque types are plaque types other than the normal tissue; A target plaque type of the target optical coherence tomography image is determined according to the true value.

2. The plaque detection method based on OCT images according to claim 1, characterized in that: The calculating and determining the light attenuation coefficient of the target optical coherence tomography image includes: The light attenuation coefficient of each pixel in the target optical coherence tomography image is calculated based on the light attenuation model in the polar coordinate system.

3. The plaque detection method based on OCT images according to any one of claims 1 to 2, characterized in that: Determining the target plaque type of the target optical coherence tomography image according to the true value includes: When it is detected that the true value is greater than or equal to a preset true value threshold, determining the plaque type corresponding to the mark as a correct plaque type; When it is detected that the plaque type is normal tissue, determining that the target optical coherence tomography image does not contain unstable plaques, and generating a normal image notification; When it is detected that the plaque type is not a normal tissue, the plaque type corresponding to the mark is used as the target plaque type, and a corresponding plaque abnormality notification is generated.

4. The plaque detection method based on OCT images according to any one of claims 1 to 2, characterized in that: The step of determining the target plaque type of the target optical coherence tomography image according to the true value further includes: When it is detected that the true value is less than a preset true value threshold, the plaque type corresponding to the mark is determined to be an erroneous plaque type, and the corresponding target plaque type is determined according to the enhanced light attenuation index.

5. A plaque detection device based on OCT images, characterized in that: include: An image acquisition module, used to acquire a target optical coherence tomography image; wherein the target optical coherence tomography image is a vascular optical coherence tomography image in polar coordinates carrying a marker of a plaque type; wherein the plaque type includes normal tissue, thin-film fibrous atheromatous plaque, cholesterol crystal, macrophage, plaque rupture, plaque erosion or calcified nodule; A first calculation module, used for calculating and determining a light attenuation coefficient of the target optical coherence tomography image; A first determination module, configured to determine a maximum light attenuation coefficient on each A line in the target optical coherence tomography image; An updating module, configured to update the pixel value of the corresponding pixel point in the target optical coherence tomography image with the maximum light decay coefficient to obtain a maximum light decay coefficient map; A filtering processing module, used for filtering the maximum light decay coefficient based on the maximum light decay coefficient map to obtain a target area image; A first calculation module, configured to calculate an enhanced light attenuation index based on the number of A lines in the target area image and a light attenuation coefficient in the target area image that meets a preset condition; A second calculation module is used to calculate the real value corresponding to each mark based on the enhanced light attenuation index, taking the mark of the plaque type as normal tissue as false, taking the mark of other plaque types as true, and obtaining the real value corresponding to each mark; wherein the other plaque type is the plaque type other than the normal tissue; A type determination module is used to determine the target plaque type of the target optical coherence tomography image according to the true value.

6. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images