Glaucoma Diagnosis via Automated Cup-Disc Ratio Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ophthalmologists' subjective estimation of the cup-disc ratio from fundus images for glaucoma diagnosis is inaccurate and time-consuming due to lack of objectivity.
Innovation Solution
A method involving machine learning models to acquire and process fundus images, extracting optic disc, optic cup, and disc rim images, and using these to determine glaucoma classification based on objective algorithms, reducing human error and effort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ophthalmologists use naked eye or shooting device to estimate cup-disc ratio, then diagnostic capability is maintained, but measurement precision and objectivity deteriorate due to subjective estimation
Solution Approach 1:
The patent replaces the mechanical/visual estimation system (naked eye or shooting device observation) with an automated image processing and machine learning system. The system captures fundus images, automatically segments the optic disc and optic cup regions, calculates the cup-disc ratio through computational algorithms, and provides objective diagnostic assistance, thereby eliminating subjective estimation errors while maintaining diagnostic capability.
2Productivity
If ophthalmologists manually estimate cup-disc ratio, then diagnostic judgment is made, but productivity deteriorates due to time and effort consumption
Solution Approach 1:
The patent implements a self-service diagnostic system where the computer automatically performs image acquisition, processing, segmentation, and cup-disc ratio calculation without requiring manual intervention from the ophthalmologist. The system serves itself by autonomously completing all measurement tasks, freeing the doctor from time-consuming manual estimation while providing rapid diagnostic results.
3Reliability
If subjective estimation method is used, then diagnostic process is simple, but reliability deteriorates due to lack of objectivity and accuracy
Solution Approach 1:
The patent replaces the simple but unreliable subjective estimation method with a complex yet reliable automated system that uses image processing algorithms and machine learning models to objectively measure the cup-disc ratio. This substitution ensures consistent, reproducible, and accurate measurements across different cases and operators, significantly improving diagnostic reliability despite the increased system complexity.
Data Source
AI summary
The present disclosure provides a glaucoma image recognition method, device and diagnosis system. The method includes acquiring a fundus image; obtaining an optic disc image and an optic cup image according to the fundus image; obtaining a disc rim image according to the optic disc image and the optic cup image; and determining whether the fundus image is classified as glaucoma according to the disc rim image.