Eye fundus atrophy focus evaluation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of eye fundus image processing, in particular to an eye fundus atrophy focus evaluation method and device, electronic equipment and a computer readable storage medium, and aims to solve the problem of low efficiency and accuracy of manually recognizing eye fundus atrophy focus in an eye fundus image. According to the method, after a target fundus image is acquired, a leopard spot distribution area and a fundus atrophy focus candidate area of the target fundus image can be determined based on the target fundus image, and then a first evaluation result is determined based on the leopard spot distribution area and the fundus atrophy focus candidate area. The first evaluation result can evaluate the classification result of the fundus atrophy focus in the target fundus image, so that the interference of subjective factors or personal experience can be avoided, and the classification result of the fundus atrophy focus can be efficiently and accurately evaluated, thereby better assisting medical workers to quickly find and diagnose eye diseases according to the first evaluation result, and improving the detection accuracy. A treatment scheme can be accurately formulated, and the fundus atrophy focus can be conveniently identified, so that medical workers can be assisted to intuitively evaluate the illness state.

Description

Technical Field

[0001] This application relates to the field of fundus image processing technology, and in particular to a method, apparatus, electronic device and computer-readable storage medium for evaluating fundus atrophic lesions. Background Technology

[0002] Pathological myopia is a serious visual impairment characterized by excessive elongation of the eyeball, leading to a series of pathological changes in the retina and choroid. The most fundamental changes in choroidal damage in pathological myopia are degeneration and atrophy. As the degree of myopia continues to increase, diffuse retinal and choroidal atrophy, patchy retinal and choroidal atrophy, macular atrophy, and other pathological changes in myopia may appear in the fundus.

[0003] Doctors often use fundus images to observe and analyze the presence of atrophic lesions in the fundus, a crucial indicator. By observing these lesions, they assess the progression of the disease and develop targeted treatment plans to slow its deterioration. However, doctors typically observe and analyze fundus images manually. Due to the complexity of fundus images and the large number of images doctors need to examine daily, manual interpretation is not only inefficient but also susceptible to the influence of factors such as staff fatigue, distraction, personal experience, and subjective judgment. These factors can affect the accuracy of the diagnosis, potentially leading to misdiagnosis or missed diagnosis. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, electronic device, and computer-readable storage medium for assessing fundus atrophy lesions, in order to solve the problem of low efficiency and accuracy in manually identifying fundus atrophy lesions in fundus images.

[0005] In a first aspect, one embodiment of this application provides a method for evaluating fundus atrophy lesions, comprising: acquiring a target fundus image; determining, based on the target fundus image, a leopard spot distribution area and a candidate area for fundus atrophy lesions in the target fundus image; and determining a first evaluation result based on the leopard spot distribution area and the candidate area for fundus atrophy lesions, wherein the first evaluation result is used to evaluate the classification result of fundus atrophy lesions in the target fundus image.

[0006] In conjunction with the first aspect, in certain implementations of the first aspect, a first evaluation result is determined based on the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions, including: determining the surrounding area of ​​the candidate area of ​​fundus atrophy lesions based on the candidate area of ​​fundus atrophy lesions; determining the intersection of the surrounding areas of the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions; determining the distribution of leopard spots in the periphery of the candidate area of ​​fundus atrophy lesions based on the intersection of the surrounding areas of the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions; and determining the first evaluation result based on the distribution of leopard spots in the periphery of the candidate area of ​​fundus atrophy lesions.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, a first evaluation result is determined based on the distribution of leopard spots around the candidate area of ​​fundus atrophy lesions, including: obtaining the intersection of the distribution area of ​​leopard spots and the surrounding area of ​​the candidate area of ​​fundus atrophy lesions, and the enclosing angle relative to the candidate area of ​​fundus atrophy lesions; and determining the first evaluation result based on the enclosing angle.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, determining the surrounding area of ​​the candidate area of ​​fundus atrophy lesions based on the candidate area of ​​fundus atrophy lesions includes: performing dilation processing on the boundary area of ​​the candidate area of ​​fundus atrophy lesions to obtain the dilated candidate area of ​​fundus atrophy lesions; and determining the surrounding area of ​​the candidate area of ​​fundus atrophy lesions based on the dilated candidate area of ​​fundus atrophy lesions and the candidate area of ​​fundus atrophy lesions.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, determining the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions in the target fundus image based on the target fundus image includes: determining the leopard spot distribution area based on the leopard spot; determining the grayscale threshold of the leopard spot based on the leopard spot; and performing threshold segmentation on the target fundus image based on the grayscale threshold of the leopard spot to determine the candidate area of ​​fundus atrophy lesions.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the target fundus image includes multiple image channels; determining the grayscale threshold of the leopard spot based on the leopard spot includes: acquiring grayscale images corresponding to at least two image channels of the target fundus image; and determining the grayscale threshold of the leopard spot in the grayscale images corresponding to at least two image channels based on the leopard spot and the grayscale images corresponding to at least two image channels.

[0011] In conjunction with the first aspect, in certain implementations of the first aspect, threshold segmentation is performed on the target fundus image based on the grayscale threshold of the leopard spots to determine candidate regions for fundus atrophy lesions. This includes: threshold segmentation is performed on the grayscale images corresponding to at least two image channels based on the grayscale threshold of the leopard spots in the grayscale images corresponding to each of the at least two image channels, to obtain the threshold-segmented grayscale images; the intersection of the threshold-segmented grayscale images is determined; and candidate regions for fundus atrophy lesions are determined based on the intersection of the threshold-segmented grayscale images.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, after acquiring the target fundus image, the method further includes: determining the density of leopard spots in the target fundus image; and determining a second evaluation result based on the density of leopard spots in the target fundus image, wherein the second evaluation result is used in combination with the first evaluation result to evaluate the classification result of fundus atrophic lesions in the target fundus image.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, the target fundus image includes an upper region, an lower region, and a nasal region. After acquiring the target fundus image, the method further includes: determining a third evaluation result based on the distribution of leopard spots in the upper region, lower region, and nasal region. The third evaluation result is used in conjunction with the first evaluation result to evaluate the classification result of fundus atrophic lesions in the target fundus image.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the target fundus image includes a retinal choroidal atrophy arc. After determining candidate areas of fundus atrophy lesions based on the target fundus image, the method further includes: determining a fourth evaluation result based on the retinal choroidal atrophy arc and the candidate areas of fundus atrophy lesions. The fourth evaluation result is used to evaluate the classification result of fundus atrophy lesions in the target fundus image in combination with the first evaluation result.

[0015] Secondly, one embodiment of this application provides a device for evaluating fundus atrophy lesions, comprising: an acquisition module for acquiring a target fundus image; a determination module for determining, based on the target fundus image, a leopard spot distribution area and a candidate area for fundus atrophy lesions in the target fundus image; and a first evaluation module for determining a first evaluation result based on the leopard spot distribution area and the candidate area for fundus atrophy lesions, wherein the first evaluation result is used to evaluate the classification result of fundus atrophy lesions in the target fundus image.

[0016] Thirdly, one embodiment of this application provides an electronic device, including: a processor; a memory for storing processor-executable instructions; and a processor for executing the fundus atrophy assessment method according to any one of the first aspects.

[0017] Fourthly, one embodiment of this application provides a computer-readable storage medium storing a computer program for performing the fundus atrophy assessment method described in any one of the first aspects.

[0018] The fundus atrophy assessment method provided in this embodiment, after acquiring a target fundus image, can determine the leopard spot distribution area and candidate fundus atrophy areas based on the target fundus image, and then determine the first assessment result based on the leopard spot distribution area and the candidate fundus atrophy areas. Since the first assessment result can evaluate the classification of fundus atrophy lesions in the target fundus image, it can avoid interference from subjective factors or personal experience, and can efficiently and accurately assess the classification of fundus atrophy lesions in the fundus image. This better assists medical professionals in quickly discovering and diagnosing eye diseases based on the first assessment result, accurately formulating treatment plans, and facilitating the identification of fundus atrophy lesions for intuitive assessment of the condition, guidance of treatment, and monitoring of disease changes. Attached Figure Description

[0019] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0020] Figure 1 The diagram shows a scenario applicable to an embodiment of this application.

[0021] Figure 2 The diagram shows another scenario applicable to an embodiment of this application.

[0022] Figure 3 The diagram shown is a flowchart illustrating an exemplary embodiment of the present application for evaluating fundus atrophy lesions.

[0023] Figure 4 The diagram shown is a schematic flowchart of an exemplary embodiment of this application, which describes the process of determining the first evaluation result based on the distribution area of ​​leopard spots and the candidate area of ​​fundus atrophy lesions.

[0024] Figure 5 The diagram shows a flowchart of an exemplary embodiment of this application, which describes the process of determining the first evaluation result based on the distribution of leopard spots around candidate areas of fundus atrophy lesions.

[0025] Figure 6 The diagram shown is a schematic flowchart of determining the surrounding area of ​​a candidate area of ​​fundus atrophy based on a candidate area of ​​fundus atrophy, according to an exemplary embodiment of this application.

[0026] Figure 7 The diagram shown is a schematic flowchart of a process for determining the leopard spot distribution area and candidate areas of fundus atrophy based on a target fundus image, according to an exemplary embodiment of this application.

[0027] Figure 8 The diagram shown is a schematic flowchart of determining the grayscale threshold of leopard spots based on leopard spots, according to an exemplary embodiment of this application.

[0028] Figure 9 The diagram shows a flowchart of a process for determining candidate regions of fundus atrophy lesions by thresholding a target fundus image based on a grayscale threshold of leopard spots, according to an exemplary embodiment of this application.

[0029] Figure 10 The diagram shown is a flowchart illustrating a method for assessing fundus atrophy lesions provided in another exemplary embodiment of this application.

[0030] Figure 11The diagram shown is a flowchart illustrating a method for assessing fundus atrophy lesions provided in another exemplary embodiment of this application.

[0031] Figure 12 The diagram shown is a flowchart illustrating a method for assessing fundus atrophy lesions provided in another exemplary embodiment of this application.

[0032] Figure 13 The diagram shown is a structural schematic of a fundus atrophy assessment device provided in an embodiment of this application.

[0033] Figure 14 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. Detailed Implementation

[0034] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0035] Pathological myopia is a serious visual impairment characterized by excessive elongation of the eyeball, leading to a series of pathological changes in the retina and choroid. The most fundamental changes in choroidal damage in pathological myopia are degeneration and atrophy. As the degree of myopia continues to increase, diffuse retinal and choroidal atrophy, patchy retinal and choroidal atrophy, macular atrophy, and other pathological changes in myopia may appear in the fundus.

[0036] Doctors often use fundus images to observe and analyze the presence of atrophic lesions in the fundus, a crucial indicator. By observing these lesions, they assess the progression of the disease and develop targeted treatment plans to slow its deterioration. However, doctors typically observe and analyze fundus images manually. Due to the complexity of fundus images and the large number of images doctors need to examine daily, manual interpretation is not only inefficient but also susceptible to the influence of factors such as staff fatigue, distraction, personal experience, and subjective judgment. These factors can affect the accuracy of the diagnosis, potentially leading to misdiagnosis or missed diagnosis.

[0037] Therefore, there is an urgent need for a method to assess fundus atrophy lesions that can avoid the interference of subjective factors and efficiently and accurately evaluate the classification results of fundus atrophy lesions in fundus images, so as to help doctors quickly discover and diagnose eye diseases and accurately formulate treatment plans.

[0038] Exemplary System The following is combined Figure 1A brief introduction to the application scenario of one embodiment of this application will be given.

[0039] Figure 1 The diagram shows a scenario applicable to an embodiment of this application. Figure 1 As shown, this scenario involves image processing. Specifically, the image processing scenario includes a server 110 and a user terminal 120 communicatively connected to the server 110. The server 110 is used to execute the methods mentioned in the embodiments of this application.

[0040] For example, in practical applications, a user issues a command to process an image through a user terminal 120. Upon receiving the command, the server 110 processes the target fundus image and determines a first evaluation result. Specifically, the process of processing the target fundus image is as follows: based on the target fundus image, the distribution area of ​​leopard spots and candidate areas of fundus atrophy lesions are determined; based on the distribution area of ​​leopard spots and candidate areas of fundus atrophy lesions, the first evaluation result is determined. The first evaluation result is used to evaluate the classification result of fundus atrophy lesions in the target fundus image.

[0041] Specifically, the target fundus images include, but are not limited to: all image data stored by the medical institution for the same or different target users during treatment, relevant fundus image data of one or more target users input by the user, and fundus image data of one or more target users taken as needed during their medical visits. Target users may include patients (e.g., people known to have eye diseases) or those seeking diagnosis.

[0042] For example, the target fundus image can be a fundus image with a 45° field of view, a 60° field of view, a wide-angle fundus image, or a fundus image with other field of view, or even a fundus image of other modalities. The target fundus image can be taken with the optic disc as the center, or with the macula as the center, or images from other eye positions. The method of this application embodiment can be used for follow-up analysis and processing with different field of view and different eye position imaging centers.

[0043] For example, server 110 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, and big data and artificial intelligence platforms. For example, server 110 can directly receive target fundus images or obtain them from data storage devices. For example, user terminal 120 includes, but is not limited to, computer terminals such as desktop computers and laptops, and mobile terminals such as tablet computers and mobile phones.

[0044] Figure 2 The diagram illustrates another scenario applicable to an embodiment of this application. This scenario includes an image processing device 200. The image processing device 200 includes an image acquisition module 210 and a calculation module 220. The image acquisition module 210 and the calculation module 220 are communicatively connected. In other words, the image processing device 200 simultaneously possesses image acquisition and calculation functions.

[0045] Specifically, the image acquisition module 210 can be used to acquire a target fundus image. The target fundus image can be a fundus image of a human or animal. After acquiring the target fundus image, the image acquisition module 210 can send the target fundus image to the calculation module 220. After receiving the target fundus image, the calculation module 220 can first determine the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions in the target fundus image, and then determine a first evaluation result based on the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions. The first evaluation result is used to evaluate the classification result of fundus atrophy lesions in the target fundus image.

[0046] For example, the image acquisition module 210 may be a module in the image processing device 200 that has image acquisition or image capture functions, such as a fundus camera. The computing module 220 may be a module in the image processing device 200 that has image processing functions, such as a processor.

[0047] Exemplary methods Figure 3 The diagram shown is a flowchart illustrating an exemplary embodiment of the method for assessing fundus atrophy lesions provided in this application. Figure 3 As shown in the embodiments of this application, the method for assessing fundus atrophy lesions includes the following steps.

[0048] Step S310: Obtain the target fundus image.

[0049] The target fundus image can be a fundus image of a human or animal. Specifically, the target fundus image can be a fundus image of a patient or a person to be diagnosed. The target fundus image can include one or more of the following: color fundus photography, optical coherence tomography (OCT) images, and fluorescein fundus angiography (FFA) images. For example, the fundus image can be acquired by taking a picture of the target user's fundus using a fundus camera. For example, the fundus image can also be acquired from a data storage device.

[0050] Step S320: Based on the target fundus image, determine the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions in the target fundus image.

[0051] For example, fundus atrophy foci may include diffuse atrophy foci in the fundus. For example, fundus atrophy foci may include atrophy foci caused by diffuse retinal and choroidal atrophy. Specifically, the leopard spot distribution area may be the region where leopard spots are located in the target fundus image. The fundus atrophy foci candidate area may be the region in the target fundus image suspected of having atrophy foci. For example, the leopard spot distribution area can be determined using a leopard spot feature extraction model. The fundus atrophy foci candidate area can be determined using an atrophy foci feature extraction model. For example, the leopard spot feature extraction model and the fundus atrophy foci feature extraction model can be obtained by training with machine learning (ML). For example, the leopard spot distribution area and the fundus atrophy foci candidate area in the target fundus image can be determined based on threshold segmentation, edge detection, and machine learning classification.

[0052] Step S330: Based on the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions, determine the first assessment result.

[0053] Specifically, since leopard-like spots are usually distributed to a certain extent near or around fundus atrophy lesions, a first evaluation result can be determined based on this distribution characteristic. The first evaluation result is used to assess the classification result of fundus atrophy lesions in the target fundus image. For example, the first evaluation result may include whether fundus atrophy lesions exist in the target fundus image, and may also include whether at least some fundus atrophy lesions exist in the candidate area of ​​fundus atrophy lesions, the classification of fundus atrophy lesions, the location, outline, area, and number of fundus atrophy lesions, etc. In a preferred embodiment, the first evaluation result of this application classifies the fundus atrophy lesions in the target fundus image as diffuse atrophy lesions.

[0054] For example, the target fundus image may not contain leopard spots, and the first evaluation result may be that no fundus atrophy lesions are distributed in the target fundus image. For example, step S330 may include: determining the first evaluation result based on the distribution relationship between the leopard spot distribution area and the candidate fundus atrophy lesion area. For example, step S330 may include: determining the first evaluation result based on the degree to which the leopard spot distribution area surrounds the candidate fundus atrophy lesion area.

[0055] In some embodiments, where the first evaluation result includes the presence of at least some fundus atrophy lesions in the candidate area of ​​fundus atrophy lesions, the method further includes identifying the candidate area of ​​fundus atrophy lesions to visually present the fundus atrophy lesions.

[0056] The fundus atrophy assessment method provided in this embodiment, after acquiring a target fundus image, can determine the leopard spot distribution area and candidate fundus atrophy areas based on the target fundus image, and then determine the first assessment result based on the leopard spot distribution area and the candidate fundus atrophy areas. Since the first assessment result can evaluate the classification of fundus atrophy lesions in the target fundus image, it can avoid interference from subjective factors or personal experience, and can efficiently and accurately assess the classification of fundus atrophy lesions in the fundus image. This better assists medical professionals in quickly discovering and diagnosing eye diseases based on the first assessment result, accurately formulating treatment plans, and facilitating the identification of fundus atrophy lesions for intuitive assessment of the condition, guidance of treatment, and monitoring of disease changes.

[0057] In some application scenarios, medical workers may face the need to review a large number of images in a short period of time. Examples include situations with a large number of fundus images of patients to be diagnosed, a large number of patients to be diagnosed, and a limited number of medical workers. The fundus atrophy assessment method provided in this embodiment can quickly analyze a large number of fundus images, which is more efficient than manual image review and reduces the impact of fatigue or lack of concentration on medical workers. In some areas with underdeveloped medical systems, where there are few medical workers, or even where medical workers lack the ability to diagnose fundus atrophy, the fundus atrophy assessment method provided in this embodiment can assist doctors in diagnosis, enabling patients to receive timely intervention and treatment.

[0058] Figure 4 The diagram shown is a schematic representation of an exemplary embodiment of this application, illustrating the process of determining a first evaluation result based on leopard spot distribution areas and candidate areas of fundus atrophy lesions. Figure 4 As shown, the first assessment result is determined based on the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions, including the following steps.

[0059] Step S410: Based on the candidate area of ​​fundus atrophy lesions, determine the surrounding area of ​​the candidate area of ​​fundus atrophy lesions.

[0060] For example, the peripheral region of the candidate area for fundus atrophy lesions can be an extended region adjacent to the candidate area. For example, the peripheral region of the candidate area for fundus atrophy lesions can include a ring-shaped region surrounding the candidate area. For example, boundaries can be set according to the shape and size of each candidate area for fundus atrophy lesions. The peripheral region of the candidate area for fundus atrophy lesions can be the area between this boundary and the edge of the corresponding candidate area. The distance between this boundary and the edge of the candidate area can be set according to actual needs.

[0061] Step S420: Determine the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate fundus atrophy lesion area.

[0062] For example, the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate fundus atrophy lesion area can be determined by methods such as image overlay and region matching.

[0063] Step S430: Based on the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate area of ​​fundus atrophy lesions, determine the distribution of leopard spots around the candidate area of ​​fundus atrophy lesions.

[0064] Specifically, by examining the intersection of the leopard-spot distribution area and the surrounding area of ​​the candidate area for fundus atrophy, a detailed understanding of the specific distribution of leopard-spot spots around the candidate area for fundus atrophy can be obtained. For example, the distribution of leopard-spot spots around the candidate area for fundus atrophy can include the area, area proportion, density, and morphology of the intersection within the surrounding area of ​​the candidate area.

[0065] Step S440: Based on the distribution of leopard spots around the candidate area of ​​fundus atrophy lesions, determine the first assessment result.

[0066] Leopard spots, as a manifestation of fundus lesions, are often closely related to the presence and extent of fundus atrophy lesions in terms of their distribution and morphology. The presence of leopard spots in the periphery of candidate atrophy lesion areas may indicate the presence of atrophy lesions in those areas. The method provided in this embodiment determines the distribution of leopard spots around candidate fundus atrophy lesion areas by identifying the intersection of the leopard spot distribution area and the periphery of the candidate atrophy lesion area, thereby clearly determining the first assessment result. The method is simple and highly operable.

[0067] Figure 5 The diagram illustrates a flowchart of an exemplary embodiment of this application, illustrating the process of determining a first evaluation result based on the distribution of leopard-spot patterns around candidate areas of fundus atrophy lesions. Figure 5 As shown, the first assessment result is determined based on the distribution of leopard spots around the candidate area of ​​fundus atrophy lesions, including the following steps.

[0068] Step S510: Obtain the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate area of ​​fundus atrophy lesions, and the relative enclosing angle of the candidate area of ​​fundus atrophy lesions.

[0069] For example, the enclosing angle of the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate fundus atrophy lesion area relative to the candidate fundus atrophy lesion area can be the angle between the intersection and the center or edge line of the candidate fundus atrophy lesion area. For example, the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate fundus atrophy lesion area can include multiple discontinuous sub-regions, and the enclosing angle of this intersection relative to the candidate fundus atrophy lesion area can be the sum of the enclosing angles of each sub-region relative to the candidate fundus atrophy lesion area. The enclosing angle of a sub-region relative to the candidate fundus atrophy lesion area can be the angle between the sub-region and the center or edge line of the candidate fundus atrophy lesion area. By obtaining the size of the enclosing angle of the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate fundus atrophy lesion area relative to the candidate fundus atrophy lesion area, the distribution of leopard spots around the candidate fundus atrophy lesion area can be quantified.

[0070] Step S520: Determine the first evaluation result based on the wrap angle.

[0071] For example, step S520 may include: when the candidate area of ​​fundus atrophy lesion does not overlap with the optic disc in the fundus, if the enclosure angle is greater than a first preset value, the first evaluation result may include the presence of fundus atrophy lesions in the target fundus image. Further, the first evaluation result may also include the presence of at least a portion of fundus atrophy lesions in the candidate area of ​​fundus atrophy lesion corresponding to the enclosure angle. Further, when the candidate area of ​​fundus atrophy lesion does not overlap with the optic disc in the fundus, if the enclosure angle is less than or equal to the first preset value, the first evaluation result may include the absence of fundus atrophy lesions in the target fundus image. For example, the range of the first preset value may be greater than or equal to 170° and less than or equal to 190°. For example, the first preset value may be 180°.

[0072] For example, step S520 may include: when the candidate area of ​​fundus atrophy lesion overlaps with the optic disc in the fundus, if the enclosure angle is greater than a second preset value, the first evaluation result may include the presence of fundus atrophy lesions in the target fundus image. Further, the first evaluation result may also include the presence of at least a portion of fundus atrophy lesions in the candidate area of ​​fundus atrophy lesion corresponding to the enclosure angle. Further, when the candidate area of ​​fundus atrophy lesion overlaps with the optic disc in the fundus, if the enclosure angle is less than or equal to the second preset value, the first evaluation result may include the absence of fundus atrophy lesions in the target fundus image. For example, the range of the second preset value may be greater than or equal to 80° and less than or equal to 100°. For example, the first preset value may be 90°.

[0073] The method provided in this embodiment quantifies the distribution of leopard spots around the candidate area of ​​fundus atrophy by obtaining the size of the angle of the intersection between the distribution area of ​​leopard spots and the surrounding area of ​​the candidate area of ​​fundus atrophy. This makes the first assessment result more objective and quantifiable, reduces the influence of subjective judgment, makes the first assessment result more reliable, and helps to improve the efficiency of assessment, providing strong support for assisting medical workers in the diagnosis and treatment of fundus atrophy.

[0074] Figure 6 The diagram shown is a schematic representation of an exemplary embodiment of this application, illustrating the process of determining the surrounding region of a candidate region for fundus atrophy. Figure 6 As shown, the surrounding area of ​​the candidate area of ​​fundus atrophy lesions is determined based on the candidate area of ​​fundus atrophy lesions, including the following steps.

[0075] Step S610: Dilate the boundary region of the candidate area of ​​fundus atrophy lesion to obtain the dilated candidate area of ​​fundus atrophy lesion.

[0076] For example, the boundary region of the candidate area for fundus atrophy can be the boundary between the candidate area and its surrounding background or adjacent areas. For example, the boundary region of the candidate area can be the edge of the candidate area and a portion of the candidate area near its edge. The boundary of the candidate area can be enlarged by dilating the boundary region of the candidate area.

[0077] Step S620: Based on the expanded candidate area of ​​fundus atrophy lesions and the candidate area of ​​fundus atrophy lesions, determine the surrounding area of ​​the candidate area of ​​fundus atrophy lesions.

[0078] For example, step S620 may include: subtracting the candidate area of ​​fundus atrophy from the expanded candidate area of ​​fundus atrophy to obtain the peripheral area of ​​the candidate area of ​​fundus atrophy.

[0079] The method provided in this embodiment can expand the boundary region of the candidate area of ​​fundus atrophy lesion, and determine the surrounding area of ​​the candidate area of ​​fundus atrophy lesion based on the expanded candidate area of ​​fundus atrophy lesion and the candidate area of ​​fundus atrophy lesion, so as to obtain the intersection of the distribution area of ​​leopard spots and the surrounding area of ​​the candidate area of ​​fundus atrophy lesion. The method is simple and easy to implement.

[0080] Figure 7 The diagram illustrates a flowchart of an exemplary embodiment of this application, illustrating the process of determining the leopard-spot distribution area and candidate areas of fundus atrophy lesions in a target fundus image. Figure 7 As shown, based on the target fundus image, the distribution area of ​​leopard spots and the candidate area of ​​fundus atrophy lesions in the target fundus image are determined, including the following steps.

[0081] Step S710: Determine the leopard spot distribution area based on the leopard spots.

[0082] For example, image recognition technology can be used to identify leopard spots in a target fundus image to determine the distribution area of ​​the leopard spots.

[0083] Step S720: Determine the grayscale threshold of the leopard spots based on the leopard spots.

[0084] Step S730: Based on the grayscale threshold of the leopard spots, threshold segmentation is performed on the target fundus image to determine the candidate area of ​​fundus atrophy lesions.

[0085] For example, the grayscale threshold for the leopard spots can be the average grayscale value of the leopard spots in the target fundus image. Based on the average grayscale value of the leopard spots, average thresholding is performed on the target fundus image to determine candidate regions for fundus atrophy lesions. For example, the grayscale threshold for the leopard spots can also be an adaptive grayscale threshold for the leopard spots in the target fundus image. Based on the adaptive grayscale threshold for the leopard spots, the threshold is dynamically adjusted according to the grayscale distribution of different regions in the fundus image. Thresholding segmentation is performed on the target fundus image using a local thresholding method to determine candidate regions for fundus atrophy lesions. The grayscale threshold for the leopard spots and the thresholding method can be set according to actual needs.

[0086] Figure 8 The diagram illustrates a flowchart of an exemplary embodiment of this application, illustrating the process of determining the grayscale threshold of leopard spots based on leopard spots. In this embodiment, the target fundus image includes multiple image channels. Figure 8 As shown, the grayscale threshold of leopard spots is determined based on the leopard spots, including the following steps.

[0087] Step S810: Obtain the grayscale images corresponding to at least two image channels of the target fundus image.

[0088] Step S820: Based on the leopard spots and the corresponding grayscale images of at least two image channels, determine the grayscale threshold of the leopard spots in the grayscale images corresponding to each of the at least two image channels. Further, based on the leopard spots in the grayscale images corresponding to each of the at least two image channels, determine the grayscale threshold of the leopard spots in the grayscale images corresponding to each of the at least two image channels.

[0089] For example, the target fundus image can be an RGB (red, green, blue) format image. An RGB format image includes three channels: the R channel (i.e., the red channel), the G channel (i.e., the green channel), and the B channel (i.e., the blue channel). For example, step S810 can include: acquiring the grayscale images corresponding to the R channel and the G channel of the target fundus image. Step S820 can include: determining the grayscale thresholds of the leopard spots in the grayscale images corresponding to the R channel and the G channel of the target fundus image based on the leopard spots and the grayscale images corresponding to the R channel and the G channel of the target fundus image. For example, the grayscale images corresponding to the R, G, and B channels of the target fundus image can also be acquired, and the grayscale thresholds of the leopard spots in the respective grayscale images of the R, G, and B channels can be determined based on the leopard spots and the grayscale images corresponding to the R, G, and B channels of the target fundus image.

[0090] For example, the target fundus image can be at least one of the following: HSV (hue, saturation, value) format image, CMY / CMYK (cyan, magenta, yellow, key) color space image, HLS (hue, lightness, saturation) format image, Lab color space image, and LUV color space image. For example, the target fundus image is an HSV format image. The grayscale images corresponding to the H, S, and V channels of the target fundus image can be obtained, and based on the leopard spots and the grayscale images corresponding to the H, S, and V channels of the target fundus image, the grayscale thresholds of the leopard spots in each of the H, S, and V channels can be determined. The format of the target fundus image and the at least two image channels of the selected target fundus image can be set according to actual needs; this embodiment does not impose specific limitations.

[0091] The method provided in this embodiment determines the grayscale threshold of the leopard spot in the grayscale image corresponding to at least two image channels of the target fundus image by using the grayscale image corresponding to each of the at least two image channels. This can increase the accuracy of threshold segmentation of the target fundus image to determine the candidate area of ​​fundus atrophy lesions, making the first evaluation result more accurate and reliable.

[0092] Figure 9 The diagram illustrates a flowchart of a process for thresholding a target fundus image and determining candidate regions for fundus atrophy lesions based on a grayscale threshold of leopard spots, as provided in an exemplary embodiment of this application. Figure 9 As shown, threshold segmentation is performed on the target fundus image based on the grayscale threshold of leopard spots to determine candidate regions for fundus atrophy lesions, including the following steps.

[0093] Step S910: Based on the grayscale threshold of the leopard spots in the grayscale images corresponding to at least two image channels, threshold segmentation is performed on the grayscale images corresponding to at least two image channels respectively to obtain the threshold-segmented grayscale images.

[0094] Step S920: Determine the intersection of the grayscale images after threshold segmentation.

[0095] Step S930: Based on the intersection of the grayscale images after threshold segmentation, determine the candidate regions for fundus atrophy lesions.

[0096] Specifically, thresholding is performed on the grayscale images corresponding to at least two image channels to obtain the segmented grayscale images corresponding to at least two image channels. Based on the intersection of the segmented grayscale images corresponding to at least two image channels, candidate regions for fundus atrophy lesions are determined.

[0097] For example, the target fundus image can be an RGB format image. Step S910 may include: performing threshold segmentation on the grayscale image corresponding to the R channel of the target fundus image based on the grayscale threshold 'a' of the leopard spots in the grayscale image corresponding to the R channel, obtaining the threshold-segmented grayscale image corresponding to the R channel; and performing threshold segmentation on the grayscale image corresponding to the G channel based on the grayscale threshold 'b' of the leopard spots in the grayscale image corresponding to the G channel, obtaining the threshold-segmented grayscale image corresponding to the G channel. Step S920 may include: determining the intersection of the threshold-segmented grayscale image corresponding to the R channel and the threshold-segmented grayscale image corresponding to the G channel. Step S930 may include: determining candidate regions for fundus atrophy lesions based on the intersection of the threshold-segmented grayscale image corresponding to the R channel and the threshold-segmented grayscale image corresponding to the G channel. For example, the intersection of the threshold-segmented grayscale image corresponding to the R channel and the threshold-segmented grayscale image corresponding to the G channel can be determined as candidate regions for fundus atrophy lesions.

[0098] For example, grayscale thresholds a and b are the average grayscale thresholds of the leopard spots in their respective grayscale images. For example, when performing thresholding on the grayscale image corresponding to the R channel, the grayscale threshold set is less than the grayscale threshold a of the leopard spots in the grayscale image corresponding to the R channel of the target fundus image. When performing thresholding on the grayscale image corresponding to the G channel, the grayscale threshold set is less than the grayscale threshold b of the leopard spots in the grayscale image corresponding to the G channel of the target fundus image. For example, when performing thresholding on the grayscale image corresponding to the R channel, the grayscale threshold set is equal to a minus 20. When performing thresholding on the grayscale image corresponding to the G channel, the grayscale threshold set is equal to b minus 20.

[0099] The method provided in this embodiment obtains the grayscale images corresponding to at least two image channels by thresholding the grayscale images, and then uses the intersection of the grayscale images corresponding to the at least two image channels to determine the candidate area of ​​fundus atrophy lesions, rather than determining the candidate area of ​​fundus atrophy lesions by the grayscale image corresponding to a single image channel. This makes the range of the candidate area of ​​fundus atrophy lesions more accurate and improves the accuracy of the first evaluation result.

[0100] In some embodiments, after step S310, the method for evaluating fundus atrophy lesions further includes: preprocessing the target fundus image. Preprocessing the target fundus image includes, but is not limited to: extracting a region of interest (ROI) from the target fundus image, or performing image enhancement processing on the target fundus image, such as histogram equalization, sharpening, filtering, smoothing, etc., to make the fundus atrophy lesions more prominent. Alternatively, after extracting the ROI from the target fundus image, image enhancement processing can be performed on the extracted ROI regions.

[0101] In some embodiments, determining a first evaluation result based on the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions includes: optimizing the candidate area of ​​fundus atrophy lesions; and determining the first evaluation result based on the leopard spot distribution area and the optimized candidate area of ​​fundus atrophy lesions.

[0102] The optimization process can include: based on the target fundus image, identifying the leopard-spot region, and removing the leopard-spot region from the candidate area of ​​fundus atrophy lesions, resulting in the candidate area of ​​fundus atrophy lesions after removing the leopard-spot region. Specifically, the candidate area of ​​fundus atrophy lesions after removing the leopard-spot region is the optimized candidate area of ​​fundus atrophy lesions. Since the color of some leopard-spots is similar to the color of fundus atrophy lesions, this setting can reduce the interference of leopard-spots on the candidate area of ​​fundus atrophy lesions, making the selected candidate area of ​​fundus atrophy lesions more accurate.

[0103] Optimization can also include removing the portion of the candidate fundus atrophy lesion that is not located in the temporal region of the target fundus image, resulting in a candidate fundus atrophy lesion area after removing the portion outside the temporal region. Specifically, the candidate fundus atrophy lesion area after removing the portion outside the temporal region is the optimized candidate fundus atrophy lesion area. Since fundus atrophy lesions are mainly distributed in the temporal region, this setting can remove non-fundus atrophy lesions in other locations, making the selected candidate fundus atrophy lesion area more precise.

[0104] Figure 10 The diagram shown is a flowchart illustrating a method for assessing fundus atrophy lesions provided in another exemplary embodiment of this application. Specifically, in Figure 3 Extending from the illustrated embodiment Figure 10 The illustrated embodiment will be described in detail below. Figure 10 The illustrated embodiments and Figure 3 The differences between the illustrated embodiments are not repeated here, and the similarities are not. Figure 10 As shown, after step S310, the method for assessing fundus atrophy lesions further includes the following steps.

[0105] Step S1010: Determine the density of leopard spots in the target fundus image.

[0106] For example, image recognition technology can be used to identify leopard spots in a target fundus image and obtain the area of ​​the leopard spots in the target fundus image. The leopard spot density can be the ratio of the area of ​​the leopard spots in the target fundus image to the area of ​​the target fundus image.

[0107] Step S1020: Determine the second evaluation result based on the density of leopard spots in the target fundus image.

[0108] For example, step S1020 may include: if the density of leopard spots in the target fundus image is greater than a third preset value, then the second evaluation result is yes; if the density of leopard spots in the target fundus image is less than or equal to the third preset value, then the second evaluation result is no. For example, the third preset value may be greater than or equal to 0.08 and less than or equal to 0.18. Preferably, the third preset value is 0.18.

[0109] Specifically, the second evaluation result is used in conjunction with the first evaluation result to assess the classification result of fundus atrophy lesions in the target fundus image. For example, if the first evaluation result includes the presence of fundus atrophy lesions in the target fundus image and the second evaluation result is yes, the final evaluation result may include the presence of fundus atrophy lesions in the target fundus image. Further, the final evaluation result may also include the presence of at least a portion of fundus atrophy lesions in the candidate area of ​​fundus atrophy lesions. If the first evaluation result includes the absence of fundus atrophy lesions in the target fundus image and / or the second evaluation result is no, the final evaluation result may include the absence of fundus atrophy lesions in the target fundus image. Further, the final evaluation result may also include the absence of fundus atrophy lesions in the candidate area of ​​fundus atrophy lesions.

[0110] The fundus atrophy assessment method provided in this embodiment increases the accuracy of the assessment results because the density of leopard spots is relatively high when fundus atrophy lesions are present. Based on the density of leopard spots in the target fundus image, a second assessment result is determined, and the classification result of fundus atrophy lesions in the target fundus image is finally assessed by combining the second assessment result and the first assessment result.

[0111] Figure 11 The diagram shown is a flowchart illustrating a method for assessing fundus atrophy lesions according to another exemplary embodiment of this application. Specifically, in Figure 3 Extending from the illustrated embodiment Figure 11The illustrated embodiment will be described in detail below. Figure 11 The illustrated embodiments and Figure 3 The differences between the illustrated embodiments are as follows, while the similarities will not be repeated. In this embodiment, the target fundus image includes the upper region, the lower region, and the nasal region. For example... Figure 11 As shown, after step S310, the method for assessing fundus atrophy lesions further includes the following steps.

[0112] Step S1110: Based on the distribution of leopard spots in the upper, lower, and nasal regions, determine the third assessment result.

[0113] For example, the upper region, lower region, and nasal side region are distributed around the optic disc with the optic disc as the center. For example, step S1110 may include: if the leopard spots are distributed in most areas of the upper region, lower region, and nasal side region, the second evaluation result is yes; if the leopard spots are not distributed in most areas of the upper region, lower region, and nasal side region, the second evaluation result is no. For example, if the leopard spots are distributed in most areas of the upper region, most areas of the lower region, and most areas of the nasal side region, the second evaluation result is yes.

[0114] Specifically, the third assessment result is used in conjunction with the first assessment result to evaluate the classification result of fundus atrophy lesions in the target fundus image. For example, if the first assessment result includes the presence of fundus atrophy lesions in the target fundus image and the third assessment result is yes, the final assessment result may include the presence of fundus atrophy lesions in the target fundus image. Further, the final assessment result may also include the presence of at least some fundus atrophy lesions in the candidate area of ​​fundus atrophy lesions. If the first assessment result includes the absence of fundus atrophy lesions in the target fundus image and / or the third assessment result is no, the final assessment result may include the absence of diffuse atrophy lesions in the target fundus image. Further, the final assessment result may also include the absence of diffuse atrophy lesions in the candidate area of ​​fundus atrophy lesions.

[0115] The fundus atrophy assessment method provided in this embodiment is based on the strong correlation between the presence or absence of fundus atrophy and the distribution of leopard spots in the upper, lower, and nasal regions. A third assessment result is determined based on the distribution of leopard spots in the upper, lower, and nasal regions. The third assessment result is combined with the first assessment result to finally assess the classification result of fundus atrophy in the target fundus image, thereby increasing the accuracy of the assessment result.

[0116] Figure 12 The diagram shown is a flowchart illustrating a method for assessing fundus atrophy lesions provided in another exemplary embodiment of this application. Specifically, in Figure 3 Extending from the illustrated embodiment Figure 12 The illustrated embodiment will be described in detail below. Figure 12The illustrated embodiments and Figure 3 The differences between the illustrated embodiments are not repeated here, and the similarities are not repeated. In this embodiment, the target fundus image includes the retinal choroidal atrophy arc, and as shown... Figure 12 As shown, after determining the candidate areas of fundus atrophy based on the target fundus image, the fundus atrophy assessment method also includes the following steps.

[0117] Step S1210: Based on the retinal choroidal atrophy arc and the candidate areas of fundus atrophy lesions, determine the fourth assessment result.

[0118] For example, step S1210 may include: if the retinal choroidal atrophy arc is in the periphery of the candidate area of ​​fundus atrophy lesion, the fourth evaluation result is yes; if the retinal choroidal atrophy arc is not in the periphery of the candidate area of ​​fundus atrophy lesion, the fourth evaluation result is no.

[0119] For example, step S1210 can be performed after determining the intersection of the leopard spot distribution area and the peripheral area of ​​the candidate fundus atrophy lesion area (step S420), and may include: if the intersection of the retinal choroidal atrophy arc and the peripheral area of ​​the leopard spot distribution area and the candidate fundus atrophy lesion area has an intersection, the fourth evaluation result is yes; if the intersection of the retinal choroidal atrophy arc and the peripheral area of ​​the leopard spot distribution area and the candidate fundus atrophy lesion area does not have an intersection, the fourth evaluation result is no.

[0120] Specifically, the fourth evaluation result is used in conjunction with the first evaluation result to assess the classification result of fundus atrophy lesions in the target fundus image. For example, if the first evaluation result includes the presence of fundus atrophy lesions in the target fundus image and the fourth evaluation result is yes, the final evaluation result may include the presence of fundus atrophy lesions in the target fundus image. Further, the final evaluation result may also include the presence of at least a portion of fundus atrophy lesions in the candidate area of ​​fundus atrophy lesions. If the first evaluation result includes the absence of fundus atrophy lesions in the target fundus image and / or the fourth evaluation result is no, the final evaluation result may include the absence of fundus atrophy lesions in the target fundus image. Further, the final evaluation result may also include the absence of fundus atrophy lesions in the candidate area of ​​fundus atrophy lesions.

[0121] The fundus atrophy assessment method provided in this embodiment increases the accuracy of the assessment results because the retinal choroidal atrophy arc is usually located around the fundus atrophy lesion. Based on the retinal choroidal atrophy arc and the candidate area of ​​fundus atrophy lesion, a fourth assessment result is determined. The fourth assessment result is combined with the first assessment result to finally assess the classification result of fundus atrophy lesions in the target fundus image.

[0122] In some embodiments, the target fundus image includes the optic disc. Prior to step S1210, the fundus atrophy assessment method further includes: identifying the optic disc in the target fundus image. Step S1210 may include determining a fourth assessment result based on the retinal-choroidal atrophy arc surrounding the optic disc and candidate areas of fundus atrophy lesions.

[0123] In some embodiments, the method for assessing fundus atrophy lesions further includes determining a final assessment result based on any one or more of a first assessment result, a second assessment result, a third assessment result, and a fourth assessment result. The final assessment result is used to characterize the classification results of fundus atrophy lesions in the target fundus image.

[0124] Exemplary device The above text combined Figures 1 to 12 The method embodiments of this application are described in detail below, in conjunction with... Figure 13 and Figure 14 The present application provides a detailed description of the apparatus embodiments. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be found in the foregoing method embodiments.

[0125] Figure 13 The diagram shown is a structural schematic of a fundus atrophy assessment device provided in an embodiment of this application. Figure 13 As shown, the fundus atrophy assessment device 1300 includes an acquisition module 1310, a determination module 1320, and an assessment module 1330.

[0126] The acquisition module 1310 is used to acquire the target fundus image.

[0127] The determination module 1320 is used to determine the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions in the target fundus image based on the target fundus image.

[0128] The evaluation module 1330 is used to determine a first evaluation result based on the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions. The first evaluation result is used to evaluate the classification result of fundus atrophy lesions in the target fundus image.

[0129] In some embodiments, the determining module 1320 is further configured to: determine the peripheral region of the candidate region for fundus atrophy based on the candidate region for fundus atrophy; determine the intersection of the leopard spot distribution area and the peripheral region of the candidate region for fundus atrophy; and determine the distribution of leopard spots in the periphery of the candidate region for fundus atrophy based on the intersection of the leopard spot distribution area and the peripheral region of the candidate region for fundus atrophy. The evaluation module 1330 is further configured to determine a first evaluation result based on the distribution of leopard spots in the periphery of the candidate region for fundus atrophy.

[0130] In some embodiments, the acquisition module 1310 is further configured to acquire the intersection of the peripheral regions of the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions, relative to the containment angle of the candidate area of ​​fundus atrophy lesions. The evaluation module 1330 is further configured to determine a first evaluation result based on the containment angle.

[0131] In some embodiments, the acquisition module 1310 is further configured to perform dilation processing on the boundary region of the candidate area of ​​fundus atrophy lesions to acquire the dilated candidate area of ​​fundus atrophy lesions. The determination module 1320 is further configured to determine the surrounding region of the candidate area of ​​fundus atrophy lesions based on the dilated candidate area of ​​fundus atrophy lesions and the candidate area of ​​fundus atrophy lesions.

[0132] In some embodiments, the determining module 1320 is further configured to determine the distribution area of ​​leopard spots based on leopard spots; determine the grayscale threshold of leopard spots based on leopard spots; and perform threshold segmentation on the target fundus image based on the grayscale threshold of leopard spots to determine candidate areas of fundus atrophy lesions.

[0133] In some embodiments, the target fundus image includes multiple image channels. The acquisition module 1310 is further configured to acquire grayscale images corresponding to at least two image channels of the target fundus image. The determination module 1320 is further configured to determine a grayscale threshold of the leopard spots in the grayscale images corresponding to the at least two image channels based on the leopard spots and the grayscale images corresponding to the at least two image channels.

[0134] In some embodiments, the acquisition module 1310 is further configured to perform threshold segmentation on the grayscale images corresponding to at least two image channels based on the grayscale thresholds of the leopard spots in the grayscale images corresponding to each of the at least two image channels, and acquire the threshold-segmented grayscale images. The determination module 1320 is further configured to determine the intersection of the threshold-segmented grayscale images; and determine the candidate region of fundus atrophy lesions based on the intersection of the threshold-segmented grayscale images.

[0135] In some embodiments, the fundus atrophy assessment device 1300 further includes an optimization module. The optimization module is used to optimize the candidate areas of fundus atrophy lesions. The assessment module 1330 is also used to determine a first assessment result based on the leopard spot distribution area and the optimized candidate areas of fundus atrophy lesions. Further, the optimization module is also used to perform at least one of the following optimization processes: based on the target fundus image, determine the leopard spot region and remove the leopard spot region from the candidate areas of fundus atrophy lesions to obtain a candidate area of ​​fundus atrophy lesions after removing the leopard spot region; remove the portion of the candidate area of ​​fundus atrophy lesions that is not in the temporal region of the target fundus image to obtain a candidate area of ​​fundus atrophy lesions after removing the portion not in the temporal region.

[0136] In some embodiments, the determining module 1320 is further configured to determine the density of leopard spots in the target fundus image. The evaluating module 1330 is further configured to determine a second evaluation result based on the density of leopard spots in the target fundus image. The second evaluation result is used in conjunction with the first evaluation result to evaluate the classification result of fundus atrophic lesions in the target fundus image.

[0137] In some embodiments, the target fundus image includes a superior region, a inferior region, and a nasal region. The evaluation module 1330 is further configured to determine a third evaluation result based on the distribution of leopard-spot patches in the superior, inferior, and nasal regions. The third evaluation result is used in conjunction with the first evaluation result to assess the classification of fundus atrophic lesions in the target fundus image.

[0138] In some embodiments, the target fundus image includes a retinal-choroidal atrophy arc. The evaluation module 1330 is further configured to determine a fourth evaluation result based on the retinal-choroidal atrophy arc and candidate fundus atrophy lesions. The fourth evaluation result is used in conjunction with the first evaluation result to evaluate the classification result of fundus atrophy lesions in the target fundus image.

[0139] In some embodiments, the evaluation module 1330 is further configured to determine a final evaluation result based on any one or more of the first evaluation result, the second evaluation result, the third evaluation result, and the fourth evaluation result. The final evaluation result is used to characterize the classification results of fundus atrophy lesions in the target fundus image.

[0140] Exemplary electronic devices Below, for reference Figure 14 This describes an electronic device according to embodiments of the present application. Figure 14 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application.

[0141] like Figure 14 As shown, the electronic device 1400 includes one or more processors 1410 and memory 1420.

[0142] The processor 1410 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 1400 to perform desired functions.

[0143] The memory 1420 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 1410 may execute the program instructions to implement the fundus atrophy lesion assessment methods of the various embodiments of this application mentioned above and / or other desired functions. Various contents, such as target fundus images, may also be stored in the computer-readable storage medium.

[0144] In one example, the electronic device 1400 may also include an input device 1430 and an output device 1440, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0145] The input device 1430 may include, for example, a keyboard, a mouse, etc.

[0146] The output device 1440 can output various information to the outside, including first evaluation results, final evaluation results, etc. The output device 1440 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0147] Of course, for the sake of simplicity, Figure 14 Only some of the components of the electronic device 1400 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 1400 may include any other suitable components depending on the specific application.

[0148] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the fundus atrophy assessment methods according to various embodiments of this application as described above.

[0149] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0150] Exemplary computer-readable storage media Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the fundus atrophy assessment methods according to various embodiments of this application described above.

[0151] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0152] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0153] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0154] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0155] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0156] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for assessing fundus atrophy lesions, characterized in that, include: Acquire target fundus image; Based on the target fundus image, determine the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions in the target fundus image; Based on the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions, a first evaluation result is determined, which is used to evaluate the classification result of fundus atrophy lesions in the target fundus image.

2. The method for assessing fundus atrophy lesions according to claim 1, characterized in that, The determination of the first evaluation result based on the leopard spot distribution area and the candidate area of ​​fundus atrophy includes: Based on the candidate areas of fundus atrophy, the surrounding area of ​​the candidate areas of fundus atrophy is determined; Determine the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate fundus atrophy lesion area; Based on the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate area of ​​fundus atrophy, the distribution of leopard spots around the candidate area of ​​fundus atrophy is determined. The first evaluation result is determined based on the distribution of the leopard spots around the candidate area of ​​fundus atrophy.

3. The method for assessing fundus atrophy lesions according to claim 2, characterized in that, The determination of the first evaluation result based on the distribution of the leopard-spot pattern around the candidate area of ​​fundus atrophy includes: Obtain the intersection of the leopard spot distribution area and the surrounding area of ​​the candidate area of ​​fundus atrophy, and the enclosing angle relative to the candidate area of ​​fundus atrophy. Based on the stated wrap angle, the first evaluation result is determined.

4. The method for assessing fundus atrophy lesions according to claim 2, characterized in that, The step of determining the surrounding area of ​​the candidate fundus atrophy lesion based on the candidate fundus atrophy lesion includes: The boundary region of the candidate area of ​​fundus atrophy is expanded to obtain the expanded candidate area of ​​fundus atrophy. Based on the expanded candidate area of ​​fundus atrophy and the candidate area of ​​fundus atrophy, the surrounding area of ​​the candidate area of ​​fundus atrophy is determined.

5. The method for assessing fundus atrophy lesions according to claim 1, characterized in that, The step of determining the leopard spot distribution area and candidate area of ​​fundus atrophy lesions in the target fundus image includes: The distribution area of ​​the leopard spots was determined based on the leopard spots; Based on the leopard spots, determine the grayscale threshold of the leopard spots; Based on the grayscale threshold of the leopard spots, threshold segmentation is performed on the target fundus image to determine the candidate region of fundus atrophy lesions.

6. The method for assessing fundus atrophy lesions according to claim 5, characterized in that, The target fundus image includes multiple image channels; Determining the grayscale threshold of the leopard spots based on the leopard spots includes: Obtain grayscale images corresponding to at least two image channels of the target fundus image; Based on the leopard spots and the grayscale images corresponding to the at least two image channels, determine the grayscale threshold of the leopard spots in the grayscale images corresponding to the at least two image channels.

7. The method for assessing fundus atrophy lesions according to claim 6, characterized in that, The step of thresholding the target fundus image based on the grayscale threshold of the leopard spots to determine the candidate region of fundus atrophy lesions includes: Based on the grayscale threshold of the leopard spots in the grayscale images corresponding to the at least two image channels, threshold segmentation is performed on the grayscale images corresponding to the at least two image channels respectively to obtain the grayscale images after threshold segmentation. Determine the intersection of the grayscale images after threshold segmentation; The candidate regions for fundus atrophy lesions are determined based on the intersection of the grayscale images after threshold segmentation.

8. The method for assessing fundus atrophy lesions according to any one of claims 1 to 7, characterized in that, After acquiring the target fundus image, the method further includes: Determine the density of leopard spots in the target fundus image; Based on the density of leopard spots in the target fundus image, a second evaluation result is determined. The second evaluation result is used in conjunction with the first evaluation result to evaluate the classification result of fundus atrophic lesions in the target fundus image.

9. The method for assessing fundus atrophy lesions according to any one of claims 1 to 7, characterized in that, The target fundus image includes a superior region, a inferior region, and a nasal region. After acquiring the target fundus image, the method further includes: Based on the distribution of leopard spots in the upper region, the lower region, and the nasal region, a third evaluation result is determined. This third evaluation result is used in conjunction with the first evaluation result to evaluate the classification result of fundus atrophy lesions in the target fundus image.

10. The method for assessing fundus atrophy lesions according to any one of claims 1 to 7, characterized in that, The target fundus image includes an arc of retinal choroidal atrophy. After determining candidate areas of fundus atrophy lesions based on the target fundus image, the method further includes: Based on the retinal choroidal atrophy arc and the candidate area of ​​fundus atrophy lesions, a fourth evaluation result is determined. The fourth evaluation result is used in combination with the first evaluation result to evaluate the classification result of fundus atrophy lesions in the target fundus image.

11. A device for assessing fundus atrophy lesions, characterized in that, include: The acquisition module is used to acquire target fundus images; The determination module is used to determine the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions in the target fundus image based on the target fundus image; An evaluation module is used to determine a first evaluation result based on the leopard spot distribution area and the candidate area of ​​fundus atrophy lesions. The first evaluation result is used to evaluate the classification result of fundus atrophy lesions in the target fundus image.

12. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is used to perform the fundus atrophy assessment method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the fundus atrophy assessment method according to any one of claims 1 to 10.

Images