Capillary grading method and system based on retinal blood oxygen saturation

Abstract

The present invention belongs to the field of medical image processing technology. A capillary grading method and system based on retinal blood oxygen saturation is provided. A retinal structure image is obtained according to the OCT measurement result, and the retinal structure image is preprocessed; capillary segmentation is performed on the preprocessed result to identify all capillary structures; capillaries to be graded are selected from all capillary structures, and capillary segmentation is performed on the capillaries to be graded; the blood oxygen saturation of each segment is calculated, and the blood oxygen saturation of each segment is graded to obtain the final capillary grading result; the present invention can more comprehensively and accurately evaluate the health status of the retina, especially in the early detection and monitoring of retinal lesions, and has significant advantages.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a capillary grading method and system based on retinal blood oxygen saturation. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] Retinal capillaries are tiny blood vessels located in the retina, responsible for providing oxygen and nutrients to the cells of the retina, while taking away metabolic waste. Retinal capillary grading is of great significance. It helps to gain a deeper understanding of the vascular structure and function of the retina, as well as to assess the health of the eye and diagnose related diseases. Retinal capillary grading can clearly show the distribution and direction of retinal blood vessels. After the retinal blood vessels are emitted from the optic disc, they gradually branch and become thinner until a capillary network is formed. Through grading, we can better understand the connection and distribution between blood vessels at all levels, which is of great significance for studying the blood circulation and metabolism of the retina. By observing the morphology, number and distribution of capillaries, it is possible to assess whether there are lesions or abnormalities in the eye. For example, in diabetic retinopathy, capillaries will have microaneurysms, hemorrhages, hard exudates, soft exudates and other lesions. The severity and extent of these lesions can be assessed by observing the grading of capillaries.

[0004] However, the inventors found in their research that existing grading of retinal lesions is usually based on the diameter of retinal arteries and veins (arteriovenous ratio) or individual lesion characteristics (such as microaneurysms, retinal hemorrhage, etc.). These methods can effectively assess retinal health in some cases, but often lack comprehensive consideration of the balance of blood oxygen supply and demand, limiting the comprehensiveness and accuracy of their diagnosis. Summary of the invention

[0005] In order to address the deficiencies of the prior art, the present invention provides a capillary grading method and system based on retinal blood oxygen saturation, which can more comprehensively and accurately evaluate the health of the retina, especially in the early detection and monitoring of retinal diseases.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a capillary grading method based on retinal blood oxygen saturation.

[0008] A capillary grading method based on retinal blood oxygen saturation includes the following steps:

[0009] Obtaining a retinal structure image according to the OCT measurement result, and preprocessing the retinal structure image;

[0010] Perform capillary segmentation on the preprocessed results and identify all capillary structures;

[0011] Selecting capillaries to be classified from all capillary structures, and performing capillary segmentation on the capillaries to be classified;

[0012] The blood oxygen saturation of each segment is calculated, and the blood oxygen saturation of each segment is graded to obtain the final capillary grading result.

[0013] As a further limitation of the first aspect of the present invention, the preprocessing includes: performing noise removal on the retinal structure image to enhance contrast.

[0014] As a further limitation of the first aspect of the present invention, the capillaries to be classified are selected from all capillary structures by manual selection or automatic selection;

[0015] The manual selection includes: supporting the operator to manually mark the required capillaries in the image;

[0016] The automatic selection includes: automatically selecting the required capillaries based on the blood vessel diameter or blood vessel curvature using a pre-trained image recognition algorithm.

[0017] As a further limitation of the first aspect of the present invention, segmenting the capillaries to be graded comprises:

[0018] Skeletonize the capillaries to be graded;

[0019] The point set of each capillary is set to , where each point By coordinates express;

[0020] For adjacent points , ,and , calculate the direction vector of the adjacent points: , ,in,( , ) is a point The coordinates of , ) is a point The coordinates of

[0021] Compute vectors by vector dot product and vector The angle between θ ;

[0022] Set a threshold ,if Less than threshold , then the decision point is a branch point:

[0023] Traverse the skeletonized capillary point set P to identify all branch points and obtain a branch point set;

[0024] Use branch point sets to segment capillaries: points on the same segment are located between two adjacent branch points in the branch point set.

[0025] As a further limitation of the first aspect of the present invention, calculating the blood oxygen saturation of each segment includes:

[0026] Calculate the optical density of oxygenated hemoglobin and deoxygenated hemoglobin in each capillary segment;

[0027] The blood oxygen saturation of each segment is the ratio of the optical density of oxyhemoglobin to the sum of the optical density of oxyhemoglobin and the optical density of deoxyhemoglobin in the segment.

[0028] As a further limitation of the first aspect of the present invention, the classification interval is Δ , capillaries are graded, including:

[0029] The blood oxygen saturation range of level N is: , where N is a positive integer greater than or equal to 1.

[0030] In a second aspect, the present invention provides a capillary grading system based on retinal blood oxygen saturation.

[0031] A capillary grading system based on retinal blood oxygen saturation, including:

[0032] An image preprocessing unit is configured to: obtain a retinal structure image according to the OCT measurement result, and preprocess the retinal structure image;

[0033] The capillary segmentation unit is configured to: perform capillary segmentation on the preprocessed result and identify all capillary structures;

[0034] The capillary segmentation unit is configured to: select capillaries to be classified from all capillary structures, and perform capillary segmentation on the capillaries to be classified;

[0035] The capillary grading unit is configured to: calculate the blood oxygen saturation of each segment, grade the blood oxygen saturation of each segment, and obtain a final capillary grading result.

[0036] In a third aspect, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium;

[0037] a processor adapted to execute a computer program;

[0038] A computer-readable storage medium having a computer program stored therein, wherein the computer program, when executed by the processor, implements the capillary grading method based on retinal blood oxygen saturation as described in the first aspect of the present invention.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the capillary grading method based on retinal blood oxygen saturation as described in the first aspect of the present invention.

[0040] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the capillary grading method based on retinal blood oxygen saturation as described in the first aspect of the present invention.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. The present invention innovatively proposes a capillary grading method based on retinal blood oxygen saturation, performs capillary segmentation on the preprocessed results, identifies all capillary structures, selects capillaries to be graded from all capillary structures, performs capillary segmentation on the capillaries to be graded, calculates the blood oxygen saturation of each segment, grades the blood oxygen saturation of each segment, and obtains the final capillary grading result, which can more comprehensively and accurately evaluate the health status of the retina, especially in the early detection and monitoring of retinal diseases.

[0043] 2. The present invention innovatively designs a segmentation strategy for the capillaries to be classified, skeletonizes the capillaries to be classified, calculates the direction vectors of adjacent points on the capillaries to be classified, and calculates the angle between two adjacent direction vectors by vector dot product. ， If the angle is less than the set threshold, the middle point of the two adjacent direction vectors is determined to be a branch point. The skeletonized capillary point set P is traversed to identify all branch points, and a branch point set is obtained. The capillaries are segmented using the branch point set, ensuring that there are no branches in each segment, thereby improving the accuracy of capillary grading.

[0044] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0046] Figure 1 A schematic diagram of a flow chart of a capillary classification method based on retinal blood oxygen saturation provided in Example 1 of the present invention;

[0047] Figure 2 A schematic diagram of a capillary grading system based on retinal blood oxygen saturation provided in Example 2 of the present invention;

[0048] Figure 3 A schematic diagram of a computer device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0049] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0050] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0051] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0052] Embodiment 1:

[0053] This implementation proposes a capillary classification method based on retinal blood oxygen saturation, including the following process:

[0054] S1: Obtain retinal structural images, incident light intensity, and reflected light intensity based on OCT measurement results.

[0055] In this implementation, the incident light intensity, reflected light intensity and light intensity information transmitted through the tissue can be obtained through visible light OCT or multispectral OCT or a multispectral camera; the light intensity information transmitted through the tissue can be obtained through special transmitted light measurement, or indirectly inferred through the correlation between reflected light and incident light, which will not be repeated here.

[0056] S2: Preprocessing and capillary segmentation are performed on the retinal structure image to identify all capillary structures.

[0057] In this implementation, the preprocessing includes: performing noise removal on the image and enhancing the contrast so as to better identify the capillaries.

[0058] In this implementation, capillary segmentation includes: using an image segmentation algorithm to identify all capillary structures. The image segmentation algorithm here can use threshold segmentation, edge detection or a deep learning model. Existing algorithms or existing models can be used here for implementation and will not be described in detail.

[0059] S3: Select capillaries to be graded manually or automatically.

[0060] Capillaries to be graded can be screened according to the location (such as in a certain lesion area), diameter or other characteristics of the capillaries to be selected;

[0061] Manual selection: The operator can manually mark the capillaries to be graded in the retinal structure image;

[0062] Automatic selection: using an additional image processing algorithm, some capillaries are selected based on the vessel diameter or vessel curvature (such as vessel diameter, curvature, etc.), and one of the capillaries is automatically selected as the capillary to be classified; for example, an upper and lower value range of the vessel diameter is set, and any capillary within the upper and lower value range is selected as the capillary to be classified.

[0063] S4: Determine the branch point.

[0064] This implementation method determines the branch point by calculating the angle change of adjacent blood vessel segments, specifically, including the following process:

[0065] S4.1: Skeletonize the retinal vessels.

[0066] S4.2: Define the nodes of capillaries.

[0067] The point set of each capillary is set to , where each point By its coordinates ( , )express;

[0068] S4.3: Direction vectors of adjacent points.

[0069] For adjacent points , ,and , the direction vector of the adjacent points can be calculated:

[0070] (1);

[0071] (2);

[0072] in,( , ) is a point The coordinates of , ) is a point The coordinates of .

[0073] S4.4: Calculate the angle.

[0074] Calculate the angle between two vectors by using the vector dot product θ :

[0075] (3);

[0076] (4);

[0077] S4.5: Determine the branch point.

[0078] Set a threshold (usually a value between 30° and 45°, including the endpoint values ​​of 30° and 45°, which can be set according to specific working conditions, which will not be described here. The preferred embodiment of this implementation adopts 40°);

[0079] if is less than the threshold, then the point p is considered i+1 is a branch point, that is, if ,but:

[0080] (5);

[0081] According to the above formula and algorithm, traverse the skeletonized capillary point set To identify all branch points B, that is:

[0082] B={bj|b j is through Determine the branch point} (6);

[0083] S4.5: Segmentation.

[0084] Use the branch point set formed by branch point B to segment the capillaries:

[0085] S j ={p i |p i ∈P,b j-1 <p i j}(7);

[0086] Among them, S j For the j segment, i.e. j The point on the segment is j- 1 branch point and j point between branch points.​

[0087] S5: Calculate the blood oxygen saturation (SO2) of each segment.

[0088] According to the skeletonized segmentation results, the optical density of each capillary segment is calculated:

[0089] (8);

[0090] (9);

[0091] in, and The segmentation is performed at the corresponding wavelength S j The measured deoxygenated hemoglobin transmission light intensity and oxygenated hemoglobin transmission light intensity are is the optical density of deoxyhemoglobin, is the optical density of oxygenated hemoglobin.

[0092] According to the calculated optical density, the blood oxygen saturation of each segment :

[0093] (10);

[0094] Therefore, the whole process can be summarized as the following formula:

[0095] (11);

[0096] S6: Classify the blood oxygen saturation for each segment.

[0097] Set grading interval , capillaries are classified as follows:

[0098] The blood oxygen saturation range of level N is: , where N is a positive integer greater than or equal to 1.

[0099] For distance, if a grading interval is set every 10% (i.e. 10%), it can be divided into ten levels, the specific classification standards are as follows:

[0100] Level 1: SO2 value is above 90%; Level 2: SO2 value is between 80% and 90%; Level 3: SO2 value is between 70% and 80%; Level 4: SO2 value is between 60% and 70%; Level 5: SO2 value is between 50% and 60%; Level 6: SO2 value is between 40% and 50%; Level 7: SO2 value is between 30% and 40%; Level 8: SO2 value is between 20% and 30%; Level 9: SO2 value is between 10% and 20%; Level 10: SO2 value is between 0% and 10%.

[0101] It is understandable that if a grading interval is set every 5% (i.e. 5%), it can be divided into twenty levels, namely:

[0102] Level 1: SO2 value is above 95%; Level 2: SO2 value is between 90% and 95%; Level 3: SO2 value is between 85% and 90%; Level 4: SO2 value is between 80% and 85%; Level 5: SO2 value is between 75% and 80%; Level 6: SO2 value is between 70% and 75%; Level 7: SO2 value is between 65% and 70%; Level 8: SO2 value is between 60% and 65%; Level 9: SO2 value is between 55% and 60%; Level 10: SO2 value is between 50% and 55%; Level 11: SO2 value is between 50% and 55%. O2 value is between 45%~50%; Level 12: SO2 value is between 40%~45%; Level 13: SO2 value is between 35%~40%; Level 14: SO2 value is between 30%~35%; Level 15: SO2 value is between 25%~30%; Level 16: SO2 value is between 20%~25%; Level 17: SO2 value is between 15%~20%; Level 18: SO2 value is between 10%~15%; Level 19: SO2 value is between 5%~10%; Level 20: SO2 value is between 0%~5%.

[0103] Other grading intervals The classification settings are not described here.

[0104] Embodiment 2:

[0105] like Figure 2 As shown, this implementation provides a capillary grading system based on retinal blood oxygen saturation, including:

[0106] An image preprocessing unit is configured to: obtain a retinal structure image according to the OCT measurement result, and preprocess the retinal structure image;

[0107] The capillary segmentation unit is configured to: perform capillary segmentation on the preprocessed result and identify all capillary structures;

[0108] The capillary segmentation unit is configured to: select capillaries to be classified from all capillary structures, and perform capillary segmentation on the capillaries to be classified;

[0109] The capillary grading unit is configured to: calculate the blood oxygen saturation of each segment, grade the blood oxygen saturation of each segment, and obtain a final capillary grading result.

[0110] The specific working process of each of the above units is described in Example 1 and will not be repeated here.

[0111] It is understandable that the above-mentioned units can be separately or completely combined into one or several other units to constitute, or one (some) of the units can be further divided into multiple smaller units in function to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the functions of one unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the system may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0112] According to another embodiment of the present application, the system described in this embodiment can be constructed, and the method of Example 1 of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 1 on a general-purpose computing device such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0113] Embodiment 3:

[0114] like Figure 3 As shown, this implementation provides an electronic device, which includes a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer-readable storage medium 1003 may be connected via a bus or other means.

[0115] Among them, the communication interface 1002 is used to receive and send data, the computer-readable storage medium 1003 can be stored in the memory of the electronic device, the computer-readable storage medium 1003 is used to store a computer program, the computer program includes program instructions, and the processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0116] The processor 1001 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, and specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions.

[0117] The processor 1001 is configured to execute the following process:

[0118] Obtaining a retinal structure image according to the OCT measurement result, and preprocessing the retinal structure image;

[0119] Perform capillary segmentation on the preprocessed results and identify all capillary structures;

[0120] Selecting capillaries to be classified from all capillary structures, and performing capillary segmentation on the capillaries to be classified;

[0121] The blood oxygen saturation of each segment is calculated, and the blood oxygen saturation of each segment is graded to obtain the final capillary grading result.

[0122] The specific working process is described in Example 1 and will not be repeated here.

[0123] Embodiment 4:

[0124] This implementation provides a computer-readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the electronic device and, of course, extended storage media supported by the electronic device. The computer-readable storage medium provides a storage space that stores the processing system of the electronic device.

[0125] In addition, the storage space also stores one or more instructions suitable for being loaded and executed by the processor, and these instructions may be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here may be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory; optionally, it may also be at least one computer-readable storage medium located away from the aforementioned processor.

[0126] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the following process:

[0127] Obtaining a retinal structure image according to the OCT measurement result, and preprocessing the retinal structure image;

[0128] Perform capillary segmentation on the preprocessed results and identify all capillary structures;

[0129] Selecting capillaries to be classified from all capillary structures, and performing capillary segmentation on the capillaries to be classified;

[0130] The blood oxygen saturation of each segment is calculated, and the blood oxygen saturation of each segment is graded to obtain the final capillary grading result.

[0131] The specific working process is described in Example 1 and will not be repeated here.

[0132] Embodiment 5:

[0133] The present implementation provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the following process:

[0134] Obtaining a retinal structure image according to the OCT measurement result, and preprocessing the retinal structure image;

[0135] Perform capillary segmentation on the preprocessed results and identify all capillary structures;

[0136] Selecting capillaries to be classified from all capillary structures, and performing capillary segmentation on the capillaries to be classified;

[0137] The blood oxygen saturation of each segment is calculated, and the blood oxygen saturation of each segment is graded to obtain the final capillary grading result.

[0138] The specific working process is described in Example 1 and will not be repeated here.

[0139] A person skilled in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application 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. A person skilled in the art 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.

[0140] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by the computer or a data processing device such as a server, a data center, etc. that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0141] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A capillary grading method based on retinal blood oxygen saturation, characterized in that: The process includes: Obtaining a retinal structure image according to the OCT measurement result, and preprocessing the retinal structure image; Perform capillary segmentation on the preprocessed results and identify all capillary structures; Selecting capillaries to be classified from all capillary structures, and performing capillary segmentation on the capillaries to be classified; Segmenting the capillaries to be classified into capillaries, comprising: Skeletonize the capillaries to be graded; The point set of each capillary is set to , where each point By coordinates express; For adjacent points , ,and , calculate the direction vector of the adjacent points: , ,in,( , ) is a point The coordinates of , ) is a point The coordinates of Compute vectors by vector dot product and vector The angle between θ ; Set a threshold ,if Less than threshold , then the decision point is a branch point, that is, if ,but: Traverse the skeletonized capillary point set P to identify all branch points B, namely: B={bj|b j is through Determine the branch point} Use branch point set B to segment capillaries: points on the same segment are between two adjacent branch points in the branch point set: S j ={p i |p i ∈P,b j-1 <p i <b j }; Among them, S j For the j segment, i.e. j The point on the segment is j- 1 branch point and j points between branch points; Calculate the blood oxygen saturation of each segment, grade the blood oxygen saturation of each segment, and obtain the final capillary grading result; Calculate the blood oxygen saturation for each segment, including: Calculate the optical density of oxygenated hemoglobin and deoxygenated hemoglobin in each capillary segment; According to the skeletonized segmentation results, the optical density of each capillary segment is calculated: in, and The segmentation is performed at the corresponding wavelength S j The measured deoxygenated hemoglobin transmission light intensity and oxygenated hemoglobin transmission light intensity are is the optical density of deoxyhemoglobin, is the optical density of oxygenated hemoglobin; The blood oxygen saturation of each segment is equal to the ratio of the optical density of oxygenated hemoglobin in the segment to the sum of the optical density of oxygenated hemoglobin and the optical density of deoxygenated hemoglobin; Set grading interval Δ , capillaries are graded, including: The blood oxygen saturation range of level N is: , where N is a positive integer greater than or equal to 1.

2. The capillary classification method based on retinal blood oxygen saturation according to claim 1, characterized in that: The preprocessing includes: performing noise removal on the retinal structure image to enhance contrast.

3. The capillary classification method based on retinal blood oxygen saturation according to claim 1, characterized in that: Selecting capillaries to be classified from all capillary structures by manual selection or automatic selection; The manual selection includes: supporting the operator to manually mark the required capillaries in the image; The automatic selection includes: automatically selecting the required capillaries based on the blood vessel diameter or blood vessel curvature using a pre-trained image recognition algorithm.

4. A capillary grading system based on retinal blood oxygen saturation, characterized in that: include: An image preprocessing unit is configured to: obtain a retinal structure image according to the OCT measurement result, and preprocess the retinal structure image; The capillary segmentation unit is configured to: perform capillary segmentation on the preprocessed result and identify all capillary structures; The capillary segmentation unit is configured to: select capillaries to be classified from all capillary structures, and perform capillary segmentation on the capillaries to be classified; Segmenting the capillaries to be classified into capillaries, comprising: Skeletonize the capillaries to be graded; The point set of each capillary is set to , where each point By coordinates express; For adjacent points , ,and , calculate the direction vector of the adjacent points: , ,in,( , ) is a point The coordinates of , ) is a point The coordinates of Compute vectors by vector dot product and vector The angle between θ ; Set a threshold ,if Less than threshold , then the decision point is a branch point, that is, if ,but: Traverse the skeletonized capillary point set P to identify all branch points B, namely: B={bj|b j is through Determine the branch point} Use branch point set B to segment capillaries: points on the same segment are between two adjacent branch points in the branch point set: S j ={p i |p i ∈P,b j-1 <p i <b j } Among them, S j For the j segment, i.e. j The point on the segment is j- 1 branch point and j points between branch points; The capillary grading unit is configured to: calculate the blood oxygen saturation of each segment, grade the blood oxygen saturation of each segment, and obtain a final capillary grading result; Calculate the blood oxygen saturation for each segment, including: Calculate the optical density of oxygenated hemoglobin and deoxygenated hemoglobin in each capillary segment; According to the skeletonized segmentation results, the optical density of each capillary segment is calculated: in, and The segmentation is performed at the corresponding wavelength S j The measured deoxygenated hemoglobin transmission light intensity and oxygenated hemoglobin transmission light intensity are is the optical density of deoxyhemoglobin, is the optical density of oxygenated hemoglobin; The blood oxygen saturation of each segment is equal to the ratio of the optical density of oxygenated hemoglobin in the segment to the sum of the optical density of oxygenated hemoglobin and the optical density of deoxygenated hemoglobin; Set grading interval Δ , capillaries are graded, including: The blood oxygen saturation range of level N is: , where N is a positive integer greater than or equal to 1.

5. A computer device, characterized in that: include: a processor and a computer readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium having a computer program stored therein, wherein the computer program, when executed by the processor, implements the capillary grading method based on retinal blood oxygen saturation as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the capillary grading method based on retinal blood oxygen saturation as described in any one of claims 1 to 3.

7. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the capillary grading method based on retinal blood oxygen saturation is implemented as described in any one of claims 1 to 3.

Images