Fundus Image-based Lesion Analysis Method and Device

Through the stitching priority processing, intersection analysis and seven-zone cropping of the fundus image set, the problem of inconsistent identification results in fundus image lesions analysis is solved, and lesion analysis with high accuracy and reliability is achieved.

CN120107707BActive Publication Date: 2025-07-22SICHUAN HEALTHSUN VISION PHARMA TECH DEV CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202510593471.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-05-09
Publication Date
2025-07-22
Estimated Expiration
2045-05-09

AI Technical Summary

Technical Problem

In the prior art, fundus image lesion analysis based on intelligent models has problems such as large differences between the training images and the actual input images, and fundus images taken at different periods are inconsistent due to jitter, resulting in poor recognition effects and reduced credibility.

Method used

By acquiring the fundus image sets for the first and subsequent periods, the stitching priority is determined, image stitching and intersection analysis is performed, image registration is carried out in combination with the optic disc features and macular areas, cropping it into a seven-zone image set, and lesion analysis is performed to generate analysis data.

Benefits of technology

It improves the accuracy and reliability of lesion analysis, ensures the consistency of lesion analysis results in different periods, and meets actual needs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention relates to the technical field of image processing, and specifically discloses a lesion analysis method and device based on fundus images, including: obtaining a first fundus image set and a second fundus image set; performing image stitching on the first fundus image set and the second fundus image set to obtain a first stitched fundus image and a second stitched fundus image; performing intersection analysis on the second stitched fundus image based on the first stitched fundus image, and processing the first stitched fundus image and the second stitched fundus image based on the intersection analysis result to obtain a first intersection image and a second intersection image; cropping the first intersection image and the second intersection image to obtain a first cropped image set and a second cropped image set; performing lesion analysis on the first cropped image set and the second cropped image set to generate first analysis data and second analysis data; generating a lesion analysis result based on the first analysis data and the second analysis data. The present invention improves the accuracy and reliability of lesion recognition.
Need to check novelty before this filing date? Find Prior Art