CN-121999048-A - High-precision three-dimensional cornea vertex positioning method and system based on image analysis

CN121999048ACN 121999048 ACN121999048 ACN 121999048ACN-121999048-A

Abstract

The invention provides a high-precision three-dimensional cornea vertex positioning method and system based on image analysis, which belong to the technical field of image processing, and concretely comprise the steps of determining a three-dimensional cornea vertex positioning result by using a positioning processing method, determining multiple positioning demand characteristics in cornea image characteristics based on deviation conditions of the positioning processing result among different positioning processing methods in different users, determining available matching combinations in a user combination according to positioning processing data of the multiple positioning demand characteristics, and combining the positioning processing data of the users in different positioning verification processing methods and the multiple positioning demand characteristic data, and determining an optimization processing strategy of the three-dimensional cornea vertex of the user according to the positioning processing data of the three-dimensional cornea vertex when the optimization processing of the positioning processing strategy is required.

Inventors

CHENG DEJI
CHENG XIANGYUN
NIU HAITAO
XU BING
Lv Xingzheng
CHENG ZIHAO

Assignees

杭州目乐医疗科技股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260209

Claims (10)

1. The high-precision three-dimensional cornea vertex positioning method based on image analysis is characterized by comprising the following steps of: Carrying out positioning processing of three-dimensional cornea vertexes by using acquired data of a multi-dimensional image and an image analysis model, and carrying out determination of a positioning processing method of an auxiliary image pickup device of the three-dimensional cornea vertexes of a user by combining extraction results of cornea image features of the user on the basis of verification processing data of positioning processing results of different users; determining a positioning processing result of the three-dimensional cornea vertex by using the positioning processing method, and determining multiple positioning requirement characteristics in the cornea image characteristics based on deviation conditions of the positioning processing result among different positioning processing methods in different users; And determining available matching combinations in the user combination according to the positioning processing data of the multiple positioning demand features, and determining the optimization processing strategy of the three-dimensional cornea vertex of the user according to the positioning processing data of the three-dimensional cornea vertex when the optimization processing of the positioning processing strategy is determined according to the positioning processing data of the three-dimensional cornea vertex by combining the positioning processing data of the user in different positioning verification processing methods and the multiple positioning demand feature data.
2. The image resolution based high precision three dimensional corneal vertex positioning method of claim 1, wherein the multi dimensional image is at least two images of different origin comprising a corneal region.
3. The method for positioning a three-dimensional cornea vertex with high precision based on image analysis according to claim 1, wherein the positioning processing data under the cornea image feature is determined according to the number of users of the positioning processing under the cornea image feature.
4. The method for positioning the three-dimensional cornea vertex with high precision based on image analysis according to claim 1, wherein the method for determining the positioning processing method of the auxiliary imaging device of the three-dimensional cornea vertex of the user is as follows: Dividing the users with the similarity degree meeting the requirements of the cornea image characteristics into the same user combination based on the positioning processing data of different users; determining the number of users in the positioning process in different user combinations according to the distribution data of the user combinations; And determining the positioning processing method of the auxiliary imaging device of the three-dimensional cornea vertex of the user according to the extraction result of the cornea image characteristics of the user and the number of users in the positioning processing in different user combinations.
5. The image resolution based high precision three dimensional cornea vertex positioning method according to claim 4, wherein if the similarity coefficient of cornea image characteristics between the user and other users is greater than a preset similarity coefficient threshold, the user and other users are classified into the same user combination.
6. The method for positioning a three-dimensional cornea vertex with high precision based on image analysis according to claim 1, wherein the positioning processing method performs the division processing according to the position of the auxiliary image pickup device.
7. The method for positioning the three-dimensional cornea vertex based on image analysis according to claim 1, wherein the method for determining multiple positioning requirement features in the cornea image features is as follows: Determining a positioning processing process with inconsistent positioning processing results according to the deviation condition of the positioning processing results among the positioning processing methods in the users, and taking the positioning processing process as an inconsistent process; According to a positioning processing method corresponding to a positioning processing result consistent with a verification processing result in the inconsistent process, the positioning processing method is used as a matching verification method; Multiple positioning demand features in the corneal image features are determined based on inconsistent processes among different users and matching verification method data.
8. The image resolution based high precision three dimensional cornea vertex positioning method of claim 1, wherein the available matching combination is a user combination with an adaptation coefficient greater than a preset adaptation coefficient threshold, wherein the adaptation coefficient is a proportion of users in the user combination for which an identification matching process exists.
9. The method for positioning a three-dimensional cornea vertex with high precision based on image analysis according to claim 1, wherein determining whether the optimization of the positioning strategy is required comprises: Determining the number of available matching combinations in the user combination according to the available matching combination data in the user combination; Determining the positioning process of the auxiliary imaging device for three-dimensional cornea vertex and positioning process by adopting two set positions in different user combinations according to the positioning process data of the users in different positioning verification processing methods, and taking the two set positions as other positioning processes; And determining whether optimization processing of a positioning processing strategy is needed or not based on the number of available matching combinations, other positioning process data in different user combinations and the multiple positioning requirement characteristic data.
10. A computer system comprising a memory and a processor in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor, when running the computer program, performs a high precision three-dimensional corneal vertex positioning method based on image analysis as claimed in any one of claims 1-9.

Description

High-precision three-dimensional cornea vertex positioning method and system based on image analysis Technical Field The invention belongs to the technical field of image processing, and particularly relates to a high-precision three-dimensional cornea vertex positioning method and system based on image analysis. Background The corneal vertex is the point of greatest curvature and most prominence of the anterior surface of the cornea, usually near the visual axis, and is a key reference point for ophthalmic surgery (e.g., femtosecond laser valve making, ICL implantation) and also a core benchmark for optometry and corneal topography analysis. The positioning accuracy directly determines the safety and effectiveness of the operation. When the positioning processing of the corneal vertex is performed, the auxiliary image pickup device often adopts a fixed position, and the measurement result of the corneal vertex is possibly inaccurate along with the difference of the image characteristics of the cornea of the eye of the user, so that the determination of the identification processing method of the corneal vertex of the auxiliary image pickup device at a plurality of positions is performed under different image characteristics, the optimal setting position of the auxiliary image pickup device is selected and obtained under the image characteristics of different cornea, and the accuracy of the positioning result is ensured to be the technical problem to be solved urgently. Therefore, a high-precision three-dimensional cornea vertex positioning method and system based on image analysis are needed. Disclosure of Invention In order to achieve the purpose of the invention, the invention adopts the following technical scheme: Specifically, the application provides a high-precision three-dimensional cornea vertex positioning method based on image analysis, which specifically comprises the following steps: S1, carrying out positioning processing of three-dimensional cornea vertexes by using acquired data of a multi-dimensional image and an image analysis model, and carrying out determination of a positioning processing method of an auxiliary image pickup device of the three-dimensional cornea vertexes of a user by combining extraction results of cornea image features of the user on the basis of verification processing data of positioning processing results of different users; S2, determining a positioning processing result of the three-dimensional cornea vertex by using the positioning processing method, and determining multiple positioning requirement characteristics in the cornea image characteristics based on deviation conditions of the positioning processing results among different positioning processing methods in different users; S3, determining available matching combinations in the user combination according to positioning processing data of multiple positioning demand features, and determining an optimization processing strategy of the three-dimensional cornea vertex of the user according to the positioning processing data of the three-dimensional cornea vertex when the optimization processing of the positioning processing strategy is determined according to the positioning processing data of the three-dimensional cornea vertex by combining the positioning processing data of the user in different positioning verification processing methods and the multiple positioning demand feature data. The invention has the beneficial effects that: The method comprises the steps of determining a positioning processing method of an auxiliary camera device of a three-dimensional cornea vertex of a user, intelligently selecting a most reliable and most efficient positioning strategy of the auxiliary camera device for each new user, improving positioning accuracy, shortening calibration time and guaranteeing clinical reliability of results, classifying users with highly similar cornea morphological characteristics into the same user combination by analyzing cornea image characteristics and successful positioning data of the historical users, judging stability and reliability of the positioning results of the characteristic group according to the number of accumulated reliable positioning samples in different combinations, and finally dynamically determining whether the positioning method of the auxiliary camera device adopted for the new user adopts a mature, preset standard position scheme or enables a more complex and more flexible multi-position verification scheme according to the experience richness of the characteristic group of the new user, thereby realizing personalized and accurate positioning support of different characteristic user groups. In the application, according to the positioning processing data of the three-dimensional cornea vertex, an optimization processing strategy of the three-dimensional cornea vertex of a user is determined, first, preliminary screening is carried out according to the new position