膜层厚度计算方法、装置、电子设备及存储介质

By determining the position of the fovea of ​​the macula in fundus OCT images and performing tilt correction, the problem of membrane thickness calculation error caused by the tilt of fundus OCT images is solved, improving the accuracy and precision of membrane thickness calculation and providing a reliable basis for the diagnosis and treatment of macular degeneration.

CN121564064BActive Publication Date: 2026-07-17EVISION TECH (BEIJING) CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
EVISION TECH (BEIJING) CO LTD
Filing Date
2025-09-30
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Due to factors such as inaccurate equipment calibration, patient cooperation, and differences in ocular structure, fundus OCT images may appear tilted, leading to errors in membrane thickness calculation and increasing the possibility of clinical misjudgment.

Method used

By determining the position coordinates of the fovea in the fundus OCT image, the retinal and choroidal layers are accurately segmented using multilayer annotation and segmentation network technology. The position of the fovea is determined by combining target detection and semantic segmentation methods. The image is corrected using a tilt correction method. A local membrane segment located on the basal side of the fovea and within the target distance threshold is selected as the reference for membrane thickness calculation.

Benefits of technology

It effectively reduces the error in film thickness calculation caused by image tilt, improves the accuracy and precision of film thickness calculation, provides more reliable clinical diagnostic basis, helps to more accurately assess macular degeneration and other related diseases, and supports more reasonable treatment plans.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121564064B_ABST
    Figure CN121564064B_ABST
Patent Text Reader

Abstract

本申请提供了一种膜层厚度计算方法、装置、电子设备及存储介质,涉及图像处理技术领域。该膜层厚度计算方法包括:确定黄斑中心凹在第一眼底OCT图像中的位置坐标,第一眼底OCT图像中包括黄斑中心凹以及位于黄斑中心凹基底侧的待测组织层;根据待测组织层的膜层结构对第一眼底OCT图像进行倾斜校正,得到第二眼底OCT图像;基于第二眼底OCT图像,根据黄斑中心凹的位置坐标计算待测组织层的膜层厚度,从而有效减少因倾斜导致的膜层厚度计算误差,提高了膜层厚度的计算准确率。
Need to check novelty before this filing date? Find Prior Art