Method and device for identifying identical capillaries without bifurcation

Abstract

The present invention provides a method and device for identifying the same capillary without bifurcation, belonging to the technical field of optical coherence tomography. The method of the present invention comprises: obtaining an OCTA image with capillaries; scanning at multiple positions on the OCTA image respectively, each position corresponding to multiple initial cross-sectional images at different times, fusing the cross-sectional images at each position, each position corresponding to a fused cross-sectional image; selecting any capillary signal on a fused cross-sectional image, and performing cross-correlation calculation with all capillary signals on another fused cross-sectional image, and when the cross-correlation coefficient is greater than or equal to the coefficient threshold, judging that the corresponding two capillaries are the same capillary without bifurcation; the present invention avoids the tedious training process of the image recognition algorithm, and improves the convenience of recognition while ensuring the recognition accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of optical coherence tomography, in particular to the technical field of capillary identification, and more particularly to a method for identifying identical capillaries without bifurcations, a device for identifying identical capillaries without bifurcations, a computer device, a computer-readable storage medium and a computer program product. 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] Capillaries are extremely tiny blood vessels that connect arteries and veins and are interconnected to form a network. Capillaries have thin walls and small diameters, and the blood flow in them is very slow. They are used for the exchange of substances between blood and tissues. For example, the capillaries in the eyes are generally distributed between the optic nerve layer and the inner nuclear layer of the retina. They are usually not visible to the naked eye and play an important role in eye function and health. There are also many capillaries in the dermis of the skin. If the capillaries inside the skin are ruptured or blocked for various reasons, the skin surface is prone to black purple or bruises. Therefore, detecting the blood flow velocity of human capillaries can effectively prevent or treat lesions.

[0004] The commonly used method for measuring capillary flow velocity is microscope imaging technology, which measures the flow velocity by observing the movement trajectory of red blood cells in the blood vessels through a microscope. When performing blood flow detection, it is necessary to generate a three-dimensional image of the capillaries, and then find the same capillary through algorithm recognition based on the obtained three-dimensional image and then perform blood flow detection. The inventors found that the above method has the following problems:

[0005] (1) The field of view is small, and it is not possible to quickly build a 3D map. In addition, a large amount of preprocessing of the acquired microscopic images is required to remove noise interference during the 3D mapping process, which is a lot of work.

[0006] (2) It is necessary to train a more accurate image recognition algorithm to identify the same capillary without bifurcations. During the training process, training data of capillaries with and without bifurcations are required. However, it is difficult to obtain training data, and the accuracy of the image recognition algorithm cannot be guaranteed. Summary of the invention

[0007] In order to address the deficiencies in the prior art, the present invention provides a method and device for identifying the same capillary without bifurcation, which uses a non-invasive approach to determine whether the capillary is the same and has no bifurcations by comparing the correlation between the capillary cross-sectional image signal changes at any two scanning positions, thereby avoiding the tedious training process of the image recognition algorithm and improving the convenience of recognition while ensuring recognition accuracy.

[0008] In order to achieve the above object, the present invention adopts the following technical solution:

[0009] In a first aspect, the present invention provides a method for identifying identical capillaries without bifurcations.

[0010] A method for identifying identical capillaries without bifurcations, comprising the following steps:

[0011] Acquire OCTA images with capillaries present;

[0012] Scanning is performed at multiple locations on the OCTA image, each location corresponds to multiple initial cross-sectional images at different times, and the cross-sectional images at each location are fused, and each location corresponds to a fused cross-sectional image;

[0013] Any capillary signal on one fused cross-sectional image is selected to perform cross-correlation calculation with all capillary signals on another fused cross-sectional image. When the cross-correlation coefficient is greater than or equal to the coefficient threshold, the corresponding two capillaries are judged to be the same capillary without bifurcation.

[0014] As a further limitation of the first aspect of the present invention, acquiring an OCTA image with capillaries present includes:

[0015] The part without capillaries on the near-infrared OCTA image is removed by edge recognition and segmentation, and the OCTA image with capillaries is extracted.

[0016] As a further limitation of the first aspect of the present invention, before the step of selecting any capillary signal on a fused cross-sectional image, the process of identifying the capillary signal is also included:

[0017] The brightness on the fused cross-sectional image is contrasted. When the brightness is greater than the set threshold, it is a blood vessel, and when the diameter is less than the diameter threshold, it is a capillary. Alternatively, for each point in the fused cross-sectional image, time is used as the horizontal axis and the brightness signal of multiple repeated scans is used as the vertical axis. The brightness signals at different times are compared. The area with a wavy brightness signal and a suitable size greater than the threshold is a capillary signal.

[0018] In a second aspect, the present invention provides a device for identifying identical capillaries without bifurcations.

[0019] A device for identifying identical capillaries without bifurcation, comprising:

[0020] An image acquisition unit is configured to: acquire an OCTA image with capillaries;

[0021] The cross-sectional image generating unit is configured to: scan multiple positions on the OCTA image respectively, each position corresponds to multiple initial cross-sectional images at different times, fuse the cross-sectional images at each position, and each position corresponds to a fused cross-sectional image;

[0022] The capillary recognition unit is configured to: select any capillary signal on a fused cross-sectional image, and perform cross-correlation calculation with all capillary signals on another fused cross-sectional image. When the cross-correlation coefficient is greater than or equal to a coefficient threshold, it is determined that the corresponding two capillaries are the same capillary without bifurcation.

[0023] As a further limitation of the second aspect of the present invention, in the image acquisition unit, acquiring an OCTA image with capillaries, includes:

[0024] The part without capillaries on the near-infrared OCTA image is removed by edge recognition and segmentation, and the OCTA image with capillaries is extracted.

[0025] As a further limitation of the second aspect of the present invention, in the capillary recognition unit, before the step of selecting any capillary signal on a fused cross-sectional image, the process of recognizing the capillary signal is also included:

[0026] The brightness on the fused cross-sectional image is contrasted. When the brightness is greater than the set threshold, it is a blood vessel, and when the diameter is less than the diameter threshold, it is a capillary. Alternatively, for each point in the fused cross-sectional image, time is used as the horizontal axis and the brightness signal of multiple repeated scans is used as the vertical axis. The brightness signals at different times are compared. The area with a wavy brightness signal and a suitable size greater than the threshold is a capillary signal.

[0027] In a third aspect, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium;

[0028] a processor adapted to execute a computer program;

[0029] A computer-readable storage medium having a computer program stored therein, wherein when the computer program is executed by the processor, the method for identifying identical capillaries without bifurcations as described in the first aspect of the present invention is implemented.

[0030] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executing the method for identifying identical capillaries without bifurcations as described in the first aspect of the present invention.

[0031] In a fifth aspect, the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method for identifying identical capillaries without bifurcations as described in the first aspect of the present invention.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. The present invention innovatively proposes a strategy for identifying the same capillary without bifurcation, which uses a non-invasive method to determine whether it is the same blood vessel by the correlation of the capillary cross-sectional image signal changes at any two scanning positions, thus avoiding the tedious training process of the image recognition algorithm and improving the convenience of recognition while ensuring the recognition accuracy.

[0034] 2. The present invention removes the portion without capillaries on the near-infrared OCTA image through edge recognition and segmentation, extracts the OCTA image with capillaries, and can quickly perform the next step of non-branched capillary recognition, avoiding interference of other tissues on recognition and improving the overall recognition efficiency.

[0035] 3. The present invention performs light-dark contrast on the brightness on the fused cross-sectional image. When the brightness is greater than the brightness threshold, it is a blood vessel, and when the diameter is less than the diameter threshold, it is a capillary. The brightness signal corresponding to the capillary can be quickly identified; or, for each point in the fused cross-sectional image, time is used as the horizontal axis and the brightness signal of multiple repeated scans is used as the vertical axis, and the brightness signals at different times are compared. The wavy brightness signal is a capillary signal, which can quickly identify the capillaries and improve the recognition efficiency of the same non-branched capillary.

[0036] 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

[0037] 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.

[0038] Figure 1 A schematic diagram of the process of the method for identifying the same capillary without bifurcation provided in Example 1 of the present invention;

[0039] Figure 2 A schematic diagram of a scanned image provided in Embodiment 1 of the present invention;

[0040] Figure 3 This is a schematic diagram of an initial cross section provided in Example 1 of the present invention;

[0041] Figure 4A schematic diagram of the process of the device for identifying the same capillary without bifurcation provided in Example 2 of the present invention;

[0042] Figure 5 This is a schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0043] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0044] 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.

[0045] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0046] Embodiment 1:

[0047] In the implementation, a method for identifying identical capillaries without bifurcation is proposed. The following is a brief introduction to the technical terms and related concepts involved in this identification scheme, including:

[0048] OCTA (Optical Coherence Tomography Angiography) is a new non-invasive inspection technology. For example, in ophthalmology applications, it can identify retinal choroidal blood flow movement information with high resolution, image the retinal choroidal microvascular circulation in living tissue, and has unique advantages in the management and follow-up of normal retinal choroidal vascular changes and disease, and the detection of treatment effects. The technical principle of OCTA in ophthalmology is mainly based on a concept, that is, in a stationary eyeball, the only moving structure of the fundus is the blood cells flowing in the blood vessels. Repeated scanning of the same cross-section generates a contrast between static and active structures through special calculation methods (such as decorrelation of signal amplitude, etc.), thereby obtaining blood flow signals, and based on this, three-dimensional reconstruction of vascular structures is performed.

[0049] The correlation coefficient is a statistical indicator first designed by statistician Karl Pearson. It is a measure of the linear correlation between variables. It is usually represented by the letter R. Due to the different research objects, there are many ways to define the correlation coefficient. The most commonly used one is the Pearson correlation coefficient. The absolute value of the R value is between 0 and 1. Generally speaking, the closer the absolute value of the R value is to 1, the stronger the correlation between the two quantities X and Y. Conversely, the closer the absolute value of the R value is to 0, the weaker the correlation between the two quantities X and Y.

[0050] Specifically, this implementation method takes the recognition of the same capillary without bifurcation in the eyeball as an example, and of course it can be extended to the recognition of capillaries in other locations (such as capillaries in the skin), including the following processes:

[0051] S1: Obtain OCTA images with capillaries, such as Figure 2 As shown;

[0052] S2: Scan multiple locations on the OCTA image, each location corresponds to multiple initial cross-sectional images at different times, such as Figure 3 As shown, the cross-sectional images at each position are fused, and each position corresponds to a fused cross-sectional image;

[0053] S3: Select any capillary signal on one fused cross-sectional image, and perform cross-correlation calculation with all capillary signals on another fused cross-sectional image. When the cross-correlation coefficient is greater than or equal to the coefficient threshold, it is determined that the corresponding two capillaries are the same capillary without bifurcation.

[0054] In the present implementation, in step S1, an OCTA image with capillaries is obtained (taking the OCTA image of the eyeball as an example), specifically, it includes: obtaining a near-infrared OCTA image of the eyeball, removing the portion of the retina without capillaries by edge recognition and segmentation, and extracting the image from the optic nerve layer to the inner nuclear layer of the retina with capillaries. It can be understood that in the present implementation, as long as one of the layers of images containing capillaries is obtained, it can be used for identification. Of course, in other implementations, if it is desired to realize capillary identification of images at each layer, then the images at each layer are identified in turn to realize capillary analysis of the entire eye.

[0055] It is understandable that the existing image recognition method can also be used to directly determine whether there are capillaries in the collected OCTA image. As long as capillaries exist, it can be directly used as an OCTA image with capillaries (without edge recognition and segmentation); or, when the existing image recognition method is used to determine that capillaries exist in the collected OCTA image, edge recognition and segmentation can be performed to use it as an OCTA image with capillaries. Several methods are possible, and the main thing is to obtain an OCTA image with capillaries, which will not be illustrated in detail here.

[0056] In this implementation, in step S2, the cross-sectional view at each position is fused, including:

[0057] For any position, 10 consecutive OCTA images (or other numbers that meet the requirements) at different times at this position are automatically selected for pixel averaging processing to reduce random noise and improve image quality. The pixel averaging processing here refers to adding the ten pixel values ​​of the same pixel point and taking the average to obtain a fused image. It can be understood that there can be more OCTA images here, and the main purpose is to obtain more accurate capillary signals on the cross-section.

[0058] The capillary recognition principle of this implementation method is that red blood cells in capillaries have the characteristic of circulating in a single queue, and will appear bright or dark when other tissues and red blood cells are scanned. The single flow of red blood cells in capillaries will show a phenomenon of light and dark changes. By fusing multiple OCTA images at different times, it is inevitable that the brightness signals corresponding to all capillaries can be found. If only one image is used, the brightness signal may be missed, which will lead to the inability to identify the corresponding capillaries.

[0059] It can be understood that in some other implementations, the fusion processing here can also be carried out by directly adding the pixel values ​​of the same pixel point, so that the area with brightness signals can always be found, and all blood vessel signals can be found in this way; or, further, the pixel values ​​of the same pixel point can be directly added to obtain all brightness signals, and then the brightness of all darker signals (i.e., tissue signals below a certain brightness threshold) is averaged, and the brightness signal greater than a certain brightness threshold is subtracted from the brightness average signal, and then the result is multiplied by a certain multiple to enhance the difference signal to obtain the final blood vessel signal. The above method is only for illustration, and other fusion methods can also be used to obtain the brightness signals corresponding to all blood vessels, which will not be repeated here.

[0060] In this implementation, in step S3, before the step of selecting any capillary signal on a fused cross-sectional image, a capillary signal recognition process is also included, specifically including:

[0061] The brightness on the fused cross-sectional image is contrasted. When the brightness is greater than the brightness threshold, it is a blood vessel, and when the diameter is less than the diameter threshold, it is a capillary. In this implementation, the brightness threshold can be determined in the following ways:

[0062] (1) According to the empirical value setting, the general brightness value corresponding to the blood vessel can be obtained based on a large number of measurement results, and this general brightness value is used as the brightness threshold; (2) The maximum brightness and the minimum brightness on this fused cross-sectional image are obtained, and the average of the two is taken, and the average is taken as the brightness threshold; (3) All brightness signal values ​​on this fused cross-sectional image are obtained, all brightness signal values ​​are sorted, the lowest 10% brightness values ​​are removed, and the average of the remaining brightness values ​​is taken as the brightness threshold.

[0063] It is understandable that the brightness threshold may also be set in other ways, as long as it can effectively distinguish the brightness signal corresponding to the tissue (generally darker) from the brightness signal corresponding to the blood vessel (generally brighter), which will not be specifically illustrated here.

[0064] In this implementation, the diameter threshold may be determined in the following ways:

[0065] (1) According to the empirical value setting, the first diameter range corresponding to the large blood vessels and the second diameter range corresponding to the capillaries can be obtained based on a large number of measurement results. According to the minimum value of the first diameter range and the maximum value of the second diameter range, a value between the minimum value and the maximum value is determined as the diameter threshold; (2) The maximum blood vessel diameter value and the minimum blood vessel diameter value on this fused cross-sectional image are obtained, and the average of the two is taken as the blood vessel diameter threshold; (3) All blood vessel diameter values ​​on this fused cross-sectional image are obtained, all blood vessel diameter values ​​are sorted, the lowest 10% blood vessel diameter values ​​are removed, and the average of the remaining blood vessel diameter values ​​is taken as the diameter threshold.

[0066] It is understandable that the diameter threshold may also be set in other ways as long as it can effectively distinguish large blood vessels from capillaries, which will not be specifically illustrated here.

[0067] Optionally, in some other implementations, the capillary signal recognition process can also be carried out in the following manner: for each point in the fused cross-sectional image, time is used as the horizontal axis, and the brightness signal of multiple repeated scans (for example, 10) is used as the vertical axis, and the brightness signals at different times are compared. The capillary signal is a wavy brightness signal, while the brightness of other tissues is in a relatively low and stable state, and the brightness of large blood vessels is in a relatively high and stable state.

[0068] In this implementation, in S3, any capillary signal on one fused cross-sectional image is selected to perform cross-correlation calculation with all capillary signals on another fused cross-sectional image. When the cross-correlation coefficient is greater than or equal to the coefficient threshold, it is determined that the corresponding two capillaries are the same capillary without bifurcation. More specifically, it includes:

[0069] The comparison here refers to sequential comparison, that is, all the capillaries on one fused cross-sectional image are sequentially cross-correlated with all the capillaries on another fused cross-sectional image (that is, brightness signals are cross-correlated), and then capillaries without bifurcations are identified.

[0070] Optionally, the coefficient threshold here is generally set according to an empirical value. For example, the coefficient threshold can be set to 0.2, that is, the mutual correlation coefficient greater than 0.2 is regarded as a capillary without bifurcation. Alternatively, the coefficient threshold can be set to 0.5 or other values, which will not be further described here.

[0071] In this implementation, the corresponding two capillaries are the same capillary without bifurcation, specifically, the capillary corresponding to the signal on one fused cross-sectional image and the capillary corresponding to the signal on the other fused cross-sectional image are the same capillary without bifurcation.

[0072] Embodiment 2:

[0073] like Figure 4 As shown, the present invention provides a device for identifying the same capillary without bifurcation, comprising:

[0074] The image acquisition unit is configured to: acquire an OCTA image with capillaries; the specific process is the same as the process of step S1 in embodiment 1, which will not be repeated here;

[0075] The cross-sectional image generating unit is configured to: scan multiple positions on the OCTA image respectively, each position corresponds to multiple initial cross-sectional images at different times, and fuse the cross-sectional images at each position, each position corresponds to a fused cross-sectional image; the specific process is the same as the process of step S2 in embodiment 1, and will not be repeated here;

[0076] The capillary identification unit is configured to: select any capillary signal on a fused cross-sectional image, and perform cross-correlation calculation with all capillary signals on another fused cross-sectional image; when the cross-correlation coefficient is greater than or equal to a coefficient threshold, determine that the corresponding two capillaries are the same capillary without bifurcation; the specific process is the same as the process of step S3 in Example 1, and will not be repeated here.

[0077] It is understandable that the above-mentioned units can be separately or all combined into one or several other units to constitute, or 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 function 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 image processing device 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.

[0078] According to another embodiment of the present application, the system described in this embodiment can be constructed and the identification method of the embodiment 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 computing device such as a computer including 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.

[0079] Embodiment 3:

[0080] like Figure 5 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.

[0081] 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.

[0082] 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 is specifically suitable for loading and executing one or more instructions to implement the following process:

[0083] Acquire an OCTA image with capillaries; the specific process is the same as the process of step S1 in Example 1, and will not be repeated here;

[0084] Scanning is performed at multiple positions on the OCTA image, each position corresponds to multiple initial cross-sectional images at different times, and the cross-sectional images at each position are fused, and each position corresponds to a fused cross-sectional image; the specific process is the same as the process of step S2 in embodiment 1, and will not be repeated here;

[0085] Any capillary signal on a fused cross-sectional image is selected, and cross-correlation calculation is performed with all capillary signals on another fused cross-sectional image. When the cross-correlation coefficient is greater than or equal to the coefficient threshold, the corresponding two capillaries are judged to be the same capillary without bifurcation; the specific process is the same as the process of step S3 in Example 1, and will not be repeated here.

[0086] Embodiment 4:

[0087] 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.

[0088] 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 (non-volatile memory), such as at least one disk storage; optionally, it may also be at least one computer-readable storage medium located away from the aforementioned processor.

[0089] 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 steps:

[0090] Acquire an OCTA image with capillaries; the specific process is the same as the process of step S1 in Example 1, and will not be repeated here;

[0091] Scanning is performed at multiple positions on the OCTA image, each position corresponds to multiple initial cross-sectional images at different times, and the cross-sectional images at each position are fused, and each position corresponds to a fused cross-sectional image; the specific process is the same as the process of step S2 in embodiment 1, and will not be repeated here;

[0092] Any capillary signal on a fused cross-sectional image is selected, and cross-correlation calculation is performed with all capillary signals on another fused cross-sectional image. When the cross-correlation coefficient is greater than or equal to the coefficient threshold, the corresponding two capillaries are judged to be the same capillary without bifurcation; the specific process is the same as the process of step S3 in Example 1, and will not be repeated here.

[0093] Embodiment 5:

[0094] This embodiment 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 steps:

[0095] Acquire an OCTA image with capillaries; the specific process is the same as the process of step S1 in Example 1, and will not be repeated here;

[0096] Scanning is performed at multiple positions on the OCTA image, each position corresponds to multiple initial cross-sectional images at different times, and the cross-sectional images at each position are fused, and each position corresponds to a fused cross-sectional image; the specific process is the same as the process of step S2 in embodiment 1, and will not be repeated here;

[0097] Any capillary signal on a fused cross-sectional image is selected, and cross-correlation calculation is performed with all capillary signals on another fused cross-sectional image. When the cross-correlation coefficient is greater than or equal to the coefficient threshold, the corresponding two capillaries are judged to be the same capillary without bifurcation; the specific process is the same as the process of step S3 in Example 1, and will not be repeated here.

[0098] 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.

[0099] 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 loading and executing computer program instructions on a 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 device. The computer instruction can be stored in a computer-readable storage medium or transmitted by a computer-readable storage medium. The computer instruction 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 (for example, coaxial cable, optical fiber, digital line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server, a data center, etc. that contains one or more available media integration. Available media can be magnetic media (for example, floppy disk, hard disk, tape), optical media (for example, DVD), or semiconductor media (for example, solid-state drive (Solid State Disk, SSD)) and the like.

[0100] 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 method for identifying identical capillaries without bifurcations, characterized in that: The process includes: Acquire OCTA images with capillaries present; Scanning is performed at multiple locations on the OCTA image, each location corresponds to multiple initial cross-sectional images at different times, and the cross-sectional images at each location are fused, and each location corresponds to a fused cross-sectional image; Select any capillary signal on one fused cross-sectional image and perform cross-correlation calculation with all capillary signals on another fused cross-sectional image. When the cross-correlation coefficient is greater than or equal to the coefficient threshold, the corresponding two capillaries are judged to be the same capillary without bifurcation. Before selecting any capillary signal on a fused cross-section image, the capillary signal recognition process is also included: For each point in the fused cross-sectional image, time is used as the horizontal axis and the brightness signal of multiple repeated scans is used as the vertical axis. The brightness signals at different times are compared. The area with a suitable size and a wavy brightness signal greater than a threshold is a capillary signal.

2. The method for identifying the same capillary without bifurcation as claimed in claim 1, characterized in that: The part without capillaries on the near-infrared OCTA image is removed by edge recognition and segmentation, and the OCTA image with capillaries is extracted.

3. The method for identifying identical capillaries without bifurcations according to claim 1 or 2, characterized in that: Before selecting any capillary signal on a fused cross-section image, the capillary signal recognition process is also included: The brightness on the fused cross-section image is contrasted. Blood vessels with brightness greater than the set threshold are blood vessels, and blood vessels with diameters less than the diameter threshold are capillaries.

4. A device for identifying capillaries without bifurcations, characterized in that: include: An image acquisition unit is configured to: acquire an OCTA image with capillaries; The cross-sectional image generating unit is configured to: scan multiple positions on the OCTA image respectively, each position corresponds to multiple initial cross-sectional images at different times, fuse the cross-sectional images at each position, and each position corresponds to a fused cross-sectional image; The capillary recognition unit is configured to: select any capillary signal on one fused cross-sectional image, and perform cross-correlation calculation with all capillary signals on another fused cross-sectional image, and when the cross-correlation coefficient is greater than or equal to a coefficient threshold, determine that the corresponding two capillaries are the same capillary without bifurcation; Before selecting any capillary signal on a fused cross-section image, the capillary signal recognition process is also included: For each point in the fused cross-sectional image, time is used as the horizontal axis and the brightness signal of multiple repeated scans is used as the vertical axis. The brightness signals at different times are compared. The area with a suitable size and a wavy brightness signal greater than a threshold is a capillary signal.

5. The device for identifying the same capillary without bifurcation as claimed in claim 4, characterized in that: In the image acquisition unit, OCTA images with capillaries are acquired, including: The part without capillaries on the near-infrared OCTA image is removed by edge recognition and segmentation, and the OCTA image with capillaries is extracted.

6. The device for identifying capillaries without bifurcations according to claim 4 or 5, characterized in that: Before selecting any capillary signal on a fused cross-section image, the capillary signal recognition process is also included: The brightness on the fused cross-section image is contrasted. Blood vessels with brightness greater than the set threshold are blood vessels, and blood vessels with diameters less than the diameter threshold are capillaries.

7. 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, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the method for identifying the same capillary without bifurcation as described in any one of claims 1 to 3 is implemented.

8. 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 method for identifying identical capillaries without bifurcations as described in any one of claims 1 to 3.

9. 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 method for identifying identical capillaries without bifurcations as claimed in any one of claims 1 to 3 is implemented.

Images