Neural Network Fundus Image Analysis for Heart Disease Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for heart disease diagnosis lack effective non-invasive tools for assessing systemic diseases through fundus images, which are primarily used for eye diseases, limiting their application in diagnosing heart conditions.
Innovation Solution
A method and device utilizing a neural network model trained on fundus images to provide diagnosis assistance information, including risk grades, scores, and risk group classification for heart diseases, by highlighting blood vessel elements and using reconstructed images for improved diagnostic accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If fundus images are used for heart disease diagnosis, then diagnostic capability for systemic diseases is improved, but the application scope expansion creates challenges in measurement precision and reliability
Solution Approach 1:
The fundus image analysis system is designed to perform multiple diagnostic functions - originally for eye diseases and now extended to heart disease diagnosis. The neural network model is trained to extract cardiovascular risk information from fundus images, enabling the same imaging modality to serve both ophthalmological and cardiological purposes, thus resolving the contradiction between application scope expansion and maintaining diagnostic precision
Solution Approach 2:
A neural network model serves as an intermediary between the fundus images and heart disease diagnosis. The model learns to identify cardiovascular risk patterns in retinal blood vessels, acting as a mediator that translates visual information from fundus images into clinically meaningful heart disease risk assessments, thereby ensuring measurement precision while expanding application scope
2Productivity
If deep learning technology is applied to fundus image analysis, then diagnostic efficiency is improved, but device complexity and data processing requirements increase
Solution Approach 1:
The neural network model performs automated analysis of fundus images for heart disease risk assessment without requiring manual intervention. The system self-learns from training data and automatically identifies cardiovascular risk patterns, reducing the need for complex manual processing protocols and specialized expert intervention, thus improving diagnostic efficiency while managing system complexity
Solution Approach 2:
The neural network model is pre-trained on large datasets of fundus images with corresponding heart disease outcomes before deployment. This preliminary training action enables the model to perform accurate risk assessment during actual diagnosis, eliminating the need for complex real-time processing and reducing system complexity during operational use while maintaining high diagnostic efficiency
Data Source
AI summary
The present invention relates to a method of assisting in diagnosis of a target heart disease using a retinal image, the method including: obtaining a target retinal image which is obtained by imaging a retina of a testee; on the basis of the target retinal image, obtaining heart disease diagnosis assistance information of the testee according to the target retinal image, via a heart disease diagnosis assistance neural network model which obtains diagnosis assistance information that is used for diagnosis of the target heart disease according to the retinal image; and outputting the heart disease diagnosis assistance information of the testee.