Method and system for generating three-dimensional eye model based on fundus photo and scanning data

Abstract

According to the method and the system for generating the three-dimensional eye model based on the fundus photo and the scanning data provided by the invention, the depth information of the potential eye in the target fundus description information is divided according to the updated sample statistical paradigm corresponding to each fundus abnormal description content; therefore, the updated sample fundus anomaly description contents corresponding to all the fundus anomaly description contents included in the depth information of each potential eye obtained by division are the same; when the depth information of the potential eye is executed by the corresponding updated sample fundus anomaly description content, the fusion accuracy of the updated sample fundus anomaly description content in executing each fundus anomaly description content of the depth information of the potential eye is relatively high; the error of each sample statistical example can be fully reduced, and the accuracy of three-dimensional eye model construction is improved.

Description

Technical Field

[0001] The present application relates to the technical field of three-dimensional eye model construction, and more specifically, to a method and system for generating a three-dimensional eye model based on fundus photographs and scanning data. Background Art

[0002] Ophthalmic diseases, especially cataracts, have become one of the leading causes of visual impairment worldwide. With the aging population, the prevalence of cataracts is increasing year by year, and it is particularly common among the elderly. Early diagnosis and accurate assessment of cataracts are crucial for their treatment and surgical effectiveness. Currently, ophthalmologists rely mainly on traditional two-dimensional fundus photographs and optical imaging technologies (such as OCT scans) for cataract detection and diagnosis. However, these methods often fail to fully display the three-dimensional structure of the fundus, resulting in some tiny lesions not being detected in time or being ignored, affecting the accuracy and effectiveness of treatment.

[0003] The 3D eye model generated from fundus photographs and scan data can overcome the limitations of traditional methods and help doctors comprehensively assess fundus conditions. The 3D reconstruction technology improves the inaccurate assessments of existing technologies. Summary of the Invention

[0004] In view of this, the present application provides a method and system for generating a three-dimensional eye model based on fundus photographs and scanning data.

[0005] In a first aspect, a method for generating a three-dimensional eye model based on fundus photographs and scan data is provided, the method comprising: Obtaining target fundus description information, wherein fundus abnormality description content in the target fundus description information is divided into a plurality of potential eye depth information according to updated sample statistical examples corresponding to each fundus abnormality description content, the updated sample statistical examples corresponding to the fundus abnormality description content included in the depth information of each potential eye are the same, and the updated sample statistical examples corresponding to the fundus abnormality description content are sample statistical examples whose states are updated when processing the fundus abnormality description content is executed in the plurality of sample statistical examples; For the depth information of each potential eye in the target fundus description information, the depth information of the potential eye is associated with the updated sample statistical example three-dimensional eye model construction processing corresponding to the fundus abnormality description content included in the depth information of the potential eye to obtain the three-dimensional eye model construction result of the target fundus description information.

[0006] Preferably, the fundus abnormality description content in the target fundus description information is pre-configured and divided into several potential eye depth information according to the following method: For each fundus abnormality description content in the target fundus description information, determining an updated sample statistical example corresponding to the fundus abnormality description content; determining, based on updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and correlations between each fundus abnormality description content, an identification attribute of each fundus abnormality description content in the target fundus abnormality description content, the identification attribute being used to characterize identification of the fundus abnormality description content in depth information of the potential eye to be divided; Dividing the target fundus description information into a plurality of potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information; The step of determining, for each fundus abnormality description content in the target fundus description information, an updated sample statistical example corresponding to the fundus abnormality description content, includes: Determining the worst association method for all data labels, wherein all data labels are data acquisition ends that complete the estimated loss and / or estimated usage of processing the target fundus description information, under the premise of associating fundus abnormality description content represented by the association method with sample statistical examples and associating each fundus abnormality description content in the target fundus description information with the sample statistical example corresponding to the fundus abnormality description content for constructing a three-dimensional eye model; For each fundus abnormality description content in the target fundus description information, using the sample statistical examples corresponding to the fundus abnormality description content in the association method as updated sample statistical examples corresponding to the fundus abnormality description content; The step of determining the identification attributes of each fundus abnormality description content in the target fundus abnormality description content according to the updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and the correlation relationship between each fundus abnormality description content includes: For each fundus abnormality description content in the target fundus description information, the identification attributes of the fundus abnormality description content are determined based on whether the updated sample statistical examples corresponding to each main fundus abnormality description content of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to each potential fundus abnormality description content of the fundus abnormality description content are the same, wherein the main fundus abnormality description content is the fundus abnormality description content that is output as the input of the fundus abnormality description content, and the potential fundus abnormality description content is the fundus abnormality description content that is input as the output of the fundus abnormality description content.

[0007] Preferably, before determining the identification attribute of the fundus abnormality description content based on whether the updated sample statistical examples corresponding to the respective main fundus abnormality description contents of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to the respective potential fundus abnormality description contents of the fundus abnormality description content are the same, the method further includes: For each potential fundus abnormality description content of the fundus abnormality description content, determining whether an updated sample statistical example corresponding to the potential fundus abnormality description content is the same as an updated sample statistical example corresponding to the fundus abnormality description content; If the updated sample statistical example corresponding to the potential fundus abnormality description content is the same as the updated sample statistical example corresponding to the fundus abnormality description content, determining whether a training network exists for the target fundus description information, the training network being a path with the potential fundus abnormality description content as a starting node and the fundus abnormality description content as an end point, and each fundus abnormality description content in the training network is a potential fundus abnormality description content of a next fundus abnormality description content, and the training network does not include a division area between the potential fundus abnormality description content and the fundus abnormality description content; If a training network exists in the target fundus description information, and fundus abnormality description content corresponding to different sample statistical examples from the fundus abnormality description content and the potential fundus abnormality description content exists in the training network, deleting the association relationship between the fundus abnormality description content and the potential fundus abnormality description content in the projection relationship of the fundus abnormality description content; The determining of the identification attribute of the fundus abnormality description content according to whether the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description content are the same includes: The identification attributes of the fundus abnormality description content are determined based on whether the updated sample statistical examples corresponding to all the main fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same, and whether the updated sample statistical examples corresponding to all the potential fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same.

[0008] Preferably, for each fundus abnormality description content in the target fundus description information, determining the identification attribute of the fundus abnormality description content according to whether the updated sample statistical examples corresponding to each main fundus abnormality description content of the fundus abnormality description content and whether the updated sample statistical examples corresponding to each potential fundus abnormality description content of the fundus abnormality description content are the same includes: If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different from each other, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents have the same sample statistical example, then it is determined that the fundus abnormality description contents belong to the depth information start node of the potential eye; If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different from each other, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents are different from each other, then it is determined that the fundus abnormality description contents belong to the depth information of the potential eye of the fundus abnormality description contents; If the same sample statistical examples exist in the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents, it is determined that the fundus abnormality description contents belong to the depth information attribute of the potential eye.

[0009] Preferably, the target fundus description information is divided into a plurality of potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information, including: Classify each fundus abnormality description content belonging to the depth information of the potential eye of the fundus abnormality description content into a potential eye depth information; For each fundus abnormality description content belonging to the depth information start node of the potential eye, classify all the fundus abnormality description content's depth information attributes belonging to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same fundus abnormality description content into the depth information of the same potential eye; And for each fundus abnormality description content that is divided into the depth information of the same potential eye, all the depth information attributes of the fundus abnormality description content that belong to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same potential eye are divided into the depth information of the same potential eye.

[0010] In a second aspect, a system for generating a three-dimensional eye model based on fundus photographs and scan data is provided, comprising a data acquisition terminal and a data processing terminal, wherein the data acquisition terminal and the data processing terminal are communicatively connected, and the data processing terminal is specifically configured to: Obtaining target fundus description information, wherein fundus abnormality description content in the target fundus description information is divided into a plurality of potential eye depth information according to updated sample statistical examples corresponding to each fundus abnormality description content, the updated sample statistical examples corresponding to the fundus abnormality description content included in the depth information of each potential eye are the same, and the updated sample statistical examples corresponding to the fundus abnormality description content are sample statistical examples whose states are updated when processing the fundus abnormality description content is executed in the plurality of sample statistical examples; For the depth information of each potential eye in the target fundus description information, the depth information of the potential eye is associated with the updated sample statistical example three-dimensional eye model construction processing corresponding to the fundus abnormality description content included in the depth information of the potential eye to obtain the three-dimensional eye model construction result of the target fundus description information.

[0011] Preferably, the data processing terminal is specifically used for: For each fundus abnormality description content in the target fundus description information, determining an updated sample statistical example corresponding to the fundus abnormality description content; determining, based on updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and correlations between each fundus abnormality description content, an identification attribute of each fundus abnormality description content in the target fundus abnormality description content, the identification attribute being used to characterize identification of the fundus abnormality description content in depth information of the potential eye to be divided; Dividing the target fundus description information into a plurality of potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information; The data processing terminal is further configured to: Determining the worst association method for all data labels, wherein all data labels are data acquisition ends that complete the estimated loss and / or estimated usage of processing the target fundus description information, under the premise of associating fundus abnormality description content represented by the association method with sample statistical examples and associating each fundus abnormality description content in the target fundus description information with the sample statistical example corresponding to the fundus abnormality description content for constructing a three-dimensional eye model; For each fundus abnormality description content in the target fundus description information, using the sample statistical examples corresponding to the fundus abnormality description content in the association method as updated sample statistical examples corresponding to the fundus abnormality description content; The data processing terminal is further configured to: For each fundus abnormality description content in the target fundus description information, the identification attributes of the fundus abnormality description content are determined based on whether the updated sample statistical examples corresponding to each main fundus abnormality description content of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to each potential fundus abnormality description content of the fundus abnormality description content are the same, wherein the main fundus abnormality description content is the fundus abnormality description content that is output as the input of the fundus abnormality description content, and the potential fundus abnormality description content is the fundus abnormality description content that is input as the output of the fundus abnormality description content.

[0012] Preferably, the data processing terminal is further used for: For each potential fundus abnormality description content of the fundus abnormality description content, determining whether an updated sample statistical example corresponding to the potential fundus abnormality description content is the same as an updated sample statistical example corresponding to the fundus abnormality description content; If the updated sample statistical example corresponding to the potential fundus abnormality description content is the same as the updated sample statistical example corresponding to the fundus abnormality description content, determining whether a training network exists for the target fundus description information, the training network being a path with the potential fundus abnormality description content as a starting node and the fundus abnormality description content as an end point, and each fundus abnormality description content in the training network is a potential fundus abnormality description content of a next fundus abnormality description content, and the training network does not include a division area between the potential fundus abnormality description content and the fundus abnormality description content; If a training network exists in the target fundus description information, and fundus abnormality description content corresponding to different sample statistical examples from the fundus abnormality description content and the potential fundus abnormality description content exists in the training network, deleting the association relationship between the fundus abnormality description content and the potential fundus abnormality description content in the projection relationship of the fundus abnormality description content; The determining of the identification attribute of the fundus abnormality description content according to whether the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description content are the same includes: The identification attributes of the fundus abnormality description content are determined based on whether the updated sample statistical examples corresponding to all the main fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same, and whether the updated sample statistical examples corresponding to all the potential fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same.

[0013] Preferably, the data processing terminal is specifically used for: If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different from each other, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents have the same sample statistical example, then it is determined that the fundus abnormality description contents belong to the depth information start node of the potential eye; If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different from each other, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents are different from each other, then it is determined that the fundus abnormality description contents belong to the depth information of the potential eye of the fundus abnormality description contents; If the same sample statistical examples exist in the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents, it is determined that the fundus abnormality description contents belong to the depth information attribute of the potential eye.

[0014] Preferably, the data processing terminal is specifically used for: Classify each fundus abnormality description content belonging to the depth information of the potential eye of the fundus abnormality description content into a potential eye depth information; For each fundus abnormality description content belonging to the depth information start node of the potential eye, classify all the fundus abnormality description content's depth information attributes belonging to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same fundus abnormality description content into the depth information of the same potential eye; And for each fundus abnormality description content that is divided into the depth information of the same potential eye, all the depth information attributes of the fundus abnormality description content that belong to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same potential eye are divided into the depth information of the same potential eye.

[0015] The method and system for generating a three-dimensional eye model based on fundus photographs and scanning data provided in the embodiments of the present application, since the depth information of the potential eye in the target fundus description information is divided according to the updated sample statistical examples corresponding to each fundus abnormality description content, the updated sample fundus abnormality description content corresponding to all fundus abnormality description contents included in the depth information of each potential eye obtained by division is the same. When the depth information of the potential eye is executed by the corresponding updated sample fundus abnormality description content, the updated sample fundus abnormality description content can be made to have a high fusion accuracy when executing each fundus abnormality description content in the depth information of the potential eye, which can fully reduce the error of each sample statistical example and improve the accuracy of constructing the three-dimensional eye model. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the region. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a flowchart of a method for generating a three-dimensional eye model based on fundus photographs and scan data provided in an embodiment of the present application.

[0018] Figure 2 A block diagram of a device for generating a three-dimensional eye model based on fundus photographs and scan data provided in an embodiment of the present application.

[0019] Figure 3 This is an architectural diagram of a system for generating a three-dimensional eye model based on fundus photographs and scan data, provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to better understand the above technical solution, the technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0021] See also Figure 1 , shows a method for generating a three-dimensional eye model based on fundus photographs and scanning data, which may include the technical solutions described in steps 100 and 200.

[0022] Step 100: Obtain target fundus description information, wherein the fundus abnormality description content in the target fundus description information is divided into several potential eye depth information according to the updated sample statistical examples corresponding to each fundus abnormality description content, and the updated sample statistical examples corresponding to the fundus abnormality description content included in the depth information of each potential eye are the same, and the updated sample statistical examples corresponding to the fundus abnormality description content are the sample statistical examples of the status update when the processing of the fundus abnormality description content is executed in the several sample statistical examples.

[0023] Step 200, for the depth information of each potential eye in the target fundus description information, the depth information of the potential eye is associated with the updated sample statistical example three-dimensional eye model construction processing corresponding to the fundus abnormality description content included in the depth information of the potential eye to obtain the three-dimensional eye model construction result of the target fundus description information.

[0024] It can be understood that when executing the technical solutions described in steps 100 and 200 above, since the depth information of the potential eye in the target fundus description information is divided according to the updated sample statistical examples corresponding to each fundus abnormality description content, the updated sample fundus abnormality description content corresponding to all fundus abnormality description contents included in the depth information of each potential eye obtained by division is the same. When the depth information of the potential eye is executed by the corresponding updated sample fundus abnormality description content, the updated sample fundus abnormality description content can be made to have a higher fusion accuracy when executing each fundus abnormality description content in the depth information of the potential eye, which can fully reduce the error of each sample statistical example and improve the accuracy of constructing a three-dimensional eye model.

[0025] In an alternative embodiment, the fundus abnormality description content in the target fundus description information is pre-configured and divided into several potential eye depth information according to the following method, which may include the technical solutions described in the following steps q1 to q3.

[0026] Step q1: for each fundus abnormality description content in the target fundus description information, determine an updated sample statistical example corresponding to the fundus abnormality description content.

[0027] Step q2, based on the updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and the correlation between each fundus abnormality description content, determine the identification attributes of each fundus abnormality description content in the target fundus abnormality description information, and the identification attributes are used to characterize the identification of the fundus abnormality description content in the depth information of the potential eye to be divided.

[0028] Step q3: Divide the target fundus description information into several potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information. It can be understood that when executing the technical solution described in the above steps q1 to q3, the accuracy of dividing the target fundus description information into several potential eye depth information is improved by accurately determining the updated sample statistical examples corresponding to the fundus abnormality description content.

[0029] In an alternative embodiment, the inventors discovered that, for each fundus abnormality description content in the target fundus description information, there is a problem that all data labels are inaccurately associated with the fundus abnormality description content represented by the association method and the sample statistical example, making it difficult to accurately determine the updated sample statistical example corresponding to the fundus abnormality description content. In order to improve the above technical problem, the step described in step q1 of determining the updated sample statistical example corresponding to each fundus abnormality description content in the target fundus description information can specifically include the technical solutions described in the following steps q11 and q12.

[0030] Step q11, determine the worst association method for all data labels, wherein all data labels are associated with the fundus abnormality description content represented by the association method and the sample statistical example, and each fundus abnormality description content in the target fundus description information is associated with the sample statistical example corresponding to the fundus abnormality description content to complete the estimated loss of the processing of the target fundus description information and / or the estimated use of the data acquisition end.

[0031] Step q12: for each fundus abnormality description content in the target fundus description information, using the sample statistical examples corresponding to the fundus abnormality description content in the association method as updated sample statistical examples corresponding to the fundus abnormality description content.

[0032] It can be understood that when executing the technical solutions described in the above steps q11 and q12, for each fundus abnormality description content in the target fundus description information, the problem of inaccurate association between all data labels and sample statistical examples represented by the association method is improved, so that the updated sample statistical examples corresponding to the fundus abnormality description content can be accurately determined.

[0033] In an alternative embodiment, the inventors discovered that, based on the updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and the correlation relationship between each fundus abnormality description content, there is a problem of incompleteness of each fundus abnormality description content, making it difficult to completely determine the identification attributes of each fundus abnormality description content in the target fundus abnormality description content. In order to improve the above technical problem, the step described in step q2 of determining the identification attributes of each fundus abnormality description content in the target fundus abnormality description content based on the updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and the correlation relationship between each fundus abnormality description content can specifically include the technical solution described in the following step q21.

[0034] Step q21, for each fundus abnormality description content in the target fundus description information, determine the identification attributes of the fundus abnormality description content based on whether the updated sample statistical examples corresponding to each main fundus abnormality description content of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to each potential fundus abnormality description content of the fundus abnormality description content are the same, wherein the main fundus abnormality description content is the fundus abnormality description content that is output as the input of the fundus abnormality description content, and the potential fundus abnormality description content is the fundus abnormality description content that is input as the output of the fundus abnormality description content.

[0035] It can be understood that when executing the technical solution described in the above step q21, the problem of incomplete fundus abnormality description contents is improved based on the updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and the correlation between each fundus abnormality description content, so that the identification attributes of each fundus abnormality description content in the target fundus abnormality description content can be fully determined.

[0036] Based on the above foundation, before determining the identification attributes of the fundus abnormality description content based on whether the updated sample statistical examples corresponding to the various main fundus abnormality description contents of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to the various potential fundus abnormality description contents of the fundus abnormality description content are the same, the technical solutions described in the following steps w1 to w3 may also be included.

[0037] Step w1 : for each potential fundus abnormality description content of the fundus abnormality description content, determining whether the updated sample statistical example corresponding to the potential fundus abnormality description content is the same as the updated sample statistical example corresponding to the fundus abnormality description content.

[0038] Step w2: if the updated sample statistical example corresponding to the potential fundus abnormality description content is the same as the updated sample statistical example corresponding to the fundus abnormality description content, determine whether there is a training network for the target fundus description information, the training network is a path with the potential fundus abnormality description content as the starting node and the fundus abnormality description content as the end point, and each fundus abnormality description content in the training network is the potential fundus abnormality description content of the next fundus abnormality description content, and the training network does not include the division area between the potential fundus abnormality description content and the fundus abnormality description content.

[0039] Step w3: If there is a training network in the target fundus description information, and there is fundus abnormality description content in the training network that corresponds to different sample statistical examples from the fundus abnormality description content and the potential fundus abnormality description content, delete the association relationship between the fundus abnormality description content and the potential fundus abnormality description content in the projection relationship of the fundus abnormality description content.

[0040] It can be understood that the technical solution described in executing the above steps w1 to w3 is to improve the accuracy of deleting the association relationship between the fundus abnormality description content and the potential fundus abnormality description content in the projection relationship of the fundus abnormality description content by accurately determining whether the updated sample statistical example corresponding to the potential fundus abnormality description content is the same as the updated sample statistical example corresponding to the fundus abnormality description content.

[0041] In an alternative embodiment, the inventors found that there is a problem of inaccurate projection relationship when the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are the same and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents are the same, making it difficult to accurately determine the identification attributes of the fundus abnormality description contents. In order to improve the above technical problems, the step described in step q21 of determining the identification attributes of the fundus abnormality description content according to whether the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are the same and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents are the same can specifically include the technical solution described in the following step e1.

[0042] Step e1, determining the identification attributes of the fundus abnormality description content based on whether the updated sample statistical examples corresponding to all the main fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same, and whether the updated sample statistical examples corresponding to all the potential fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same.

[0043] It can be understood that when executing the technical solution described in the above step e1, the problem of inaccurate projection relationship is improved based on whether the updated sample statistical examples corresponding to the various main fundus abnormality description contents of the fundus abnormality description contents and whether the updated sample statistical examples corresponding to the various potential fundus abnormality description contents of the fundus abnormality description contents are the same, so that the identification attributes of the fundus abnormality description contents can be accurately determined.

[0044] In an alternative embodiment, the inventors found that for each fundus abnormality description content in the target fundus description information, there are multiple analysis situations, which makes it difficult to accurately determine the identification attributes of the fundus abnormality description content. In order to improve the above technical problem, the step q21 described in determining the identification attributes of the fundus abnormality description content for each fundus abnormality description content in the target fundus description information according to whether the updated sample statistical examples corresponding to the each main fundus abnormality description content of the fundus abnormality description content and whether the updated sample statistical examples corresponding to the each potential fundus abnormality description content are the same can specifically include the technical solutions described in the following steps r1 to r3.

[0045] Step r1: If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different, and the same sample statistical examples exist in the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents, then it is determined that the fundus abnormality description contents belong to the depth information start node of the potential eye.

[0046] Step r2: If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents are different, then it is determined that the fundus abnormality description contents belong to the depth information of the potential eye of the fundus abnormality description contents.

[0047] Step r3: If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents have the same sample statistical examples, it is determined that the fundus abnormality description contents belong to the depth information attribute of the potential eye.

[0048] It can be understood that when executing the technical solution described in the above steps r1 to r3, for each fundus abnormality description content in the target fundus description information, based on whether the updated sample statistical examples corresponding to the various main fundus abnormality description contents of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to the various potential fundus abnormality description contents of the fundus abnormality description content are the same, multiple analysis situations are improved, so that the identification attributes of the fundus abnormality description content can be accurately determined.

[0049] In an alternative embodiment, the inventors discovered that, when the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information is used, there is a problem of inaccurate division of the fundus abnormality description content, making it difficult to accurately divide the target fundus description information into several potential eye depth information. In order to improve the above technical problem, the step q3 described in dividing the target fundus description information into several potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information can specifically include the technical solutions described in the following steps q31-q33.

[0050] Step q31 : each fundus abnormality description content belonging to the depth information of the potential eye of the fundus abnormality description content is divided into one potential eye depth information.

[0051] Step q32, for each fundus abnormality description content of the depth information starting node belonging to the potential eye, all the fundus abnormality description content's depth information attributes belonging to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same potential eye abnormality description content are divided into the depth information of the same potential eye.

[0052] Step q33, and for each fundus abnormality description content that is divided into the depth information of the same potential eye, all the depth information attributes of the fundus abnormality description content that belong to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the fundus abnormality description content are divided into the depth information of the same potential eye.

[0053] It can be understood that when executing the technical solution described in the above steps q31 to q33, the problem of inaccurate division of fundus abnormality description contents is improved according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information, so that the target fundus description information can be accurately divided into several potential eye depth information.

[0054] Based on the above foundation, after dividing the target fundus description information into several potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information, the technical solution described in the following step a1 may also be included.

[0055] Step a1: for each two potential eyes with the same fundus abnormality description content, merge the depth information of the two potential eyes.

[0056] It can be understood that when executing the technical solution described in step a1 above, the depth information of the two potential eyes can be completely merged through a plurality of fundus abnormality description contents.

[0057] Based on the above, please refer to Figure 2 , provides a device 200 for generating a three-dimensional eye model based on fundus photographs and scan data, which is applied to a data processing terminal, and the device includes: The data acquisition module 210 is configured to obtain target fundus description information, wherein fundus abnormality description content in the target fundus description information is divided into a plurality of potential eye depth information according to the updated sample statistical examples corresponding to each fundus abnormality description content, the updated sample statistical examples corresponding to the fundus abnormality description content included in the depth information of each potential eye are the same, and the updated sample statistical examples corresponding to the fundus abnormality description content are sample statistical examples whose status is updated when the fundus abnormality description content is processed in the plurality of sample statistical examples; The model construction module 220 is used to associate the depth information of each potential eye in the target fundus description information with the updated sample statistical example three-dimensional eye model construction processing corresponding to the fundus abnormality description content included in the depth information of the potential eye, and obtain the three-dimensional eye model construction result of the target fundus description information.

[0058] On the basis of the above, please refer to Figure 3 , shows a system 300 for generating a three-dimensional eye model based on fundus photographs and scan data, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.

[0059] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0060] In summary, based on the above scheme, since the depth information of the potential eye in the target fundus description information is divided according to the updated sample statistical examples corresponding to each fundus abnormality description content, the updated sample fundus abnormality description content corresponding to all fundus abnormality description contents included in the depth information of each potential eye obtained by division is the same. When the depth information of the potential eye is executed by the corresponding updated sample fundus abnormality description content, the updated sample fundus abnormality description content can be made to have a higher fusion accuracy when executing the various fundus abnormality description contents in the depth information of the potential eye, which can fully reduce the error of each sample statistical example and improve the accuracy of constructing the three-dimensional eye model.

[0061] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above-mentioned methods and systems can be implemented using computer-executable instructions and / or contained in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the system and its modules of the present application. Not only can hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. be implemented, they can also be implemented using software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).

[0062] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0063] The basic concepts have been described above. It will be apparent to those skilled in the art that the detailed disclosure above is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and amendments to this application. Such modifications, improvements, and amendments are suggested in this application and remain within the spirit and scope of the exemplary embodiments of this application.

[0064] At the same time, this application uses specific terms to describe the embodiments of this application. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or more in different places in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application may be appropriately combined.

[0065] In addition, it will be understood by those skilled in the art that various aspects of the present application can be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application can be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be manifested as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0066] A computer storage medium may include a propagated data signal embodying the computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, or any suitable combination thereof. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium that can be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transfer the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of these.

[0067] The computer program code required for the operation of the various parts of this application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages. The program code can be executed entirely on the user's computer, or as a stand-alone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any network, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0068] In addition, unless expressly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0069] Similarly, it should be noted that, in order to simplify the presentation of this application and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this application sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not mean that the subject matter of this application requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single embodiment disclosed above.

[0070] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their regions in some embodiments of the present application are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible region.

[0071] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this application, as well as documents (currently or subsequently attached to this application) that limit the broadest area of ​​the claims of this application. It should be noted that if the descriptions, definitions, and / or use of terms in the accompanying materials of this application are inconsistent with or conflict with the content of this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0072] Finally, it should be understood that the embodiments described in this application are intended only to illustrate the principles of the embodiments of this application. Other variations may also fall within the scope of this application. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this application may be considered to be equivalent to the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly introduced and described in this application.

[0073] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for generating a three-dimensional eye model based on fundus photographs and scan data, characterized in that: The method comprises: Obtaining target fundus description information, wherein fundus abnormality description content in the target fundus description information is divided into a plurality of potential eye depth information according to updated sample statistical examples corresponding to each fundus abnormality description content, the updated sample statistical examples corresponding to the fundus abnormality description content included in the depth information of each potential eye are the same, and the updated sample statistical examples corresponding to the fundus abnormality description content are sample statistical examples whose states are updated when processing the fundus abnormality description content is executed in the plurality of sample statistical examples; For the depth information of each potential eye in the target fundus description information, the depth information of the potential eye is associated with the updated sample statistical example three-dimensional eye model construction processing corresponding to the fundus abnormality description content included in the depth information of the potential eye to obtain the three-dimensional eye model construction result of the target fundus description information.

2. The method according to claim 1, characterized in that The fundus abnormality description content in the target fundus description information is pre-configured and divided into several potential eye depth information according to the following method: For each fundus abnormality description content in the target fundus description information, determining an updated sample statistical example corresponding to the fundus abnormality description content; determining, based on updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and correlations between each fundus abnormality description content, an identification attribute of each fundus abnormality description content in the target fundus abnormality description content, the identification attribute being used to characterize identification of the fundus abnormality description content in depth information of the potential eye to be divided; Dividing the target fundus description information into a plurality of potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information; The step of determining, for each fundus abnormality description content in the target fundus description information, an updated sample statistical example corresponding to the fundus abnormality description content, includes: Determining the worst association method for all data labels, wherein all data labels are data acquisition ends that complete the estimated loss and / or estimated usage of processing the target fundus description information, under the premise of associating fundus abnormality description content represented by the association method with sample statistical examples and associating each fundus abnormality description content in the target fundus description information with the sample statistical example corresponding to the fundus abnormality description content for constructing a three-dimensional eye model; For each fundus abnormality description content in the target fundus description information, using the sample statistical examples corresponding to the fundus abnormality description content in the association method as updated sample statistical examples corresponding to the fundus abnormality description content; The step of determining the identification attributes of each fundus abnormality description content in the target fundus abnormality description content according to the updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and the correlation relationship between each fundus abnormality description content includes: For each fundus abnormality description content in the target fundus description information, the identification attributes of the fundus abnormality description content are determined based on whether the updated sample statistical examples corresponding to each main fundus abnormality description content of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to each potential fundus abnormality description content of the fundus abnormality description content are the same, wherein the main fundus abnormality description content is the fundus abnormality description content that is output as the input of the fundus abnormality description content, and the potential fundus abnormality description content is the fundus abnormality description content that is input as the output of the fundus abnormality description content.

3. The method according to claim 2, characterized in that Before determining the identification attribute of the fundus abnormality description content based on whether the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description content are the same, the method further includes: For each potential fundus abnormality description content of the fundus abnormality description content, determining whether an updated sample statistical example corresponding to the potential fundus abnormality description content is the same as an updated sample statistical example corresponding to the fundus abnormality description content; If the updated sample statistical example corresponding to the potential fundus abnormality description content is the same as the updated sample statistical example corresponding to the fundus abnormality description content, determining whether a training network exists for the target fundus description information, the training network being a path with the potential fundus abnormality description content as a starting node and the fundus abnormality description content as an end point, and each fundus abnormality description content in the training network is a potential fundus abnormality description content of a next fundus abnormality description content, and the training network does not include a division area between the potential fundus abnormality description content and the fundus abnormality description content; If a training network exists in the target fundus description information, and fundus abnormality description content corresponding to different sample statistical examples from the fundus abnormality description content and the potential fundus abnormality description content exists in the training network, deleting the association relationship between the fundus abnormality description content and the potential fundus abnormality description content in the projection relationship of the fundus abnormality description content; The determining of the identification attribute of the fundus abnormality description content according to whether the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description content are the same includes: The identification attributes of the fundus abnormality description content are determined based on whether the updated sample statistical examples corresponding to all the main fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same, and whether the updated sample statistical examples corresponding to all the potential fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same.

4. The method according to claim 2, characterized in that The determining of the identification attributes of the fundus abnormality description content according to whether the updated sample statistical examples corresponding to the main fundus abnormality description content of the fundus abnormality description content and the updated sample statistical examples corresponding to the potential fundus abnormality description content of the fundus abnormality description content are the same for each fundus abnormality description content in the target fundus description information includes: If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different from each other, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents have the same sample statistical example, then it is determined that the fundus abnormality description contents belong to the depth information start node of the potential eye; If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different from each other, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents are different from each other, then it is determined that the fundus abnormality description contents belong to the depth information of the potential eye of the fundus abnormality description contents; If the same sample statistical examples exist in the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents, it is determined that the fundus abnormality description contents belong to the depth information attribute of the potential eye.

5. The method according to claim 4, characterized in that The target fundus description information is divided into a plurality of potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information, including: Classify each fundus abnormality description content belonging to the depth information of the potential eye of the fundus abnormality description content into a potential eye depth information; For each fundus abnormality description content belonging to the depth information start node of the potential eye, classify all the fundus abnormality description content's depth information attributes belonging to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same fundus abnormality description content into the depth information of the same potential eye; And for each fundus abnormality description content that is divided into the depth information of the same potential eye, all the depth information attributes of the fundus abnormality description content that belong to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same potential eye are divided into the depth information of the same potential eye.

6. A system for generating a three-dimensional eye model based on fundus photographs and scan data, characterized in that: It includes a data acquisition terminal and a data processing terminal, the data acquisition terminal and the data processing terminal are communicatively connected, and the data processing terminal is specifically used to: Obtaining target fundus description information, wherein fundus abnormality description content in the target fundus description information is divided into a plurality of potential eye depth information according to updated sample statistical examples corresponding to each fundus abnormality description content, the updated sample statistical examples corresponding to the fundus abnormality description content included in the depth information of each potential eye are the same, and the updated sample statistical examples corresponding to the fundus abnormality description content are sample statistical examples whose states are updated when processing the fundus abnormality description content is executed in the plurality of sample statistical examples; For the depth information of each potential eye in the target fundus description information, the depth information of the potential eye is associated with the updated sample statistical example three-dimensional eye model construction processing corresponding to the fundus abnormality description content included in the depth information of the potential eye to obtain the three-dimensional eye model construction result of the target fundus description information.

7. The system according to claim 6, characterized in that The data processing terminal is specifically used for: For each fundus abnormality description content in the target fundus description information, determining an updated sample statistical example corresponding to the fundus abnormality description content; determining, based on updated sample statistical examples corresponding to each fundus abnormality description content in the target fundus description information and correlations between each fundus abnormality description content, an identification attribute of each fundus abnormality description content in the target fundus abnormality description content, the identification attribute being used to characterize identification of the fundus abnormality description content in depth information of the potential eye to be divided; Dividing the target fundus description information into a plurality of potential eye depth information according to the identification content represented by the identification data of each fundus abnormality description content in the target fundus description information; The data processing terminal is further configured to: Determining the worst association method for all data labels, wherein all data labels are data acquisition ends that complete the estimated loss and / or estimated usage of processing the target fundus description information, under the premise of associating fundus abnormality description content represented by the association method with sample statistical examples and associating each fundus abnormality description content in the target fundus description information with the sample statistical example corresponding to the fundus abnormality description content for constructing a three-dimensional eye model; For each fundus abnormality description content in the target fundus description information, using the sample statistical examples corresponding to the fundus abnormality description content in the association method as updated sample statistical examples corresponding to the fundus abnormality description content; The data processing terminal is further configured to: For each fundus abnormality description content in the target fundus description information, the identification attributes of the fundus abnormality description content are determined based on whether the updated sample statistical examples corresponding to each main fundus abnormality description content of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to each potential fundus abnormality description content of the fundus abnormality description content are the same, wherein the main fundus abnormality description content is the fundus abnormality description content that is output as the input of the fundus abnormality description content, and the potential fundus abnormality description content is the fundus abnormality description content that is input as the output of the fundus abnormality description content.

8. The system according to claim 7, characterized in that The data processing terminal is further specifically used for: For each potential fundus abnormality description content of the fundus abnormality description content, determining whether an updated sample statistical example corresponding to the potential fundus abnormality description content is the same as an updated sample statistical example corresponding to the fundus abnormality description content; If the updated sample statistical example corresponding to the potential fundus abnormality description content is the same as the updated sample statistical example corresponding to the fundus abnormality description content, determining whether a training network exists for the target fundus description information, the training network being a path with the potential fundus abnormality description content as a starting node and the fundus abnormality description content as an end point, and each fundus abnormality description content in the training network is a potential fundus abnormality description content of a next fundus abnormality description content, and the training network does not include a division area between the potential fundus abnormality description content and the fundus abnormality description content; If a training network exists in the target fundus description information, and fundus abnormality description content corresponding to different sample statistical examples from the fundus abnormality description content and the potential fundus abnormality description content exists in the training network, deleting the association relationship between the fundus abnormality description content and the potential fundus abnormality description content in the projection relationship of the fundus abnormality description content; The determining of the identification attribute of the fundus abnormality description content according to whether the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description content are the same and whether the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description content are the same includes: The identification attributes of the fundus abnormality description content are determined based on whether the updated sample statistical examples corresponding to all the main fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same, and whether the updated sample statistical examples corresponding to all the potential fundus abnormality description contents of the fundus abnormality description content in the projection relationship of the fundus abnormality description content are the same.

9. The system according to claim 7, wherein: The data processing terminal is specifically used for: If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different from each other, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents have the same sample statistical example, then it is determined that the fundus abnormality description contents belong to the depth information start node of the potential eye; If the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents are different from each other, and the updated sample statistical examples corresponding to the potential fundus abnormality description contents of the fundus abnormality description contents are different from each other, then it is determined that the fundus abnormality description contents belong to the depth information of the potential eye of the fundus abnormality description contents; If the same sample statistical examples exist in the updated sample statistical examples corresponding to the main fundus abnormality description contents of the fundus abnormality description contents, it is determined that the fundus abnormality description contents belong to the depth information attribute of the potential eye.

10. The system according to claim 9, characterized in that The data processing terminal is specifically used for: Classify each fundus abnormality description content belonging to the depth information of the potential eye of the fundus abnormality description content into a potential eye depth information; For each fundus abnormality description content belonging to the depth information start node of the potential eye, classify all the fundus abnormality description content's depth information attributes belonging to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same fundus abnormality description content into the depth information of the same potential eye; And for each fundus abnormality description content that is divided into the depth information of the same potential eye, all the depth information attributes of the fundus abnormality description content that belong to the potential eye and the example fundus abnormality description content of the updated sample statistical example corresponding to the same potential eye are divided into the depth information of the same potential eye.

Images