Retinal Image AI Analysis for Non-Invasive Heart Disease Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current diagnostic methods fail to effectively utilize fundus images for non-invasive assessment of systemic diseases such as heart disease, despite their potential for observing blood vessel damage.
Innovation Solution
A method and device utilizing an artificial neural network model to analyze fundus images for heart disease diagnosis, providing assistance information such as risk grades, scores, and risk group indicators based on trained models with highlighted blood vessel elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fundus images are used for non-invasive observation of blood vessels, then the ability to detect systemic diseases is improved, but the current diagnostic methods fail to effectively utilize this potential
Solution Approach 1:
An artificial neural network model serves as an intermediary between fundus images and heart disease diagnosis. The model processes fundus images to extract blood vessel characteristics and generates diagnostic assistance information, effectively bridging the gap between non-invasive imaging and accurate disease detection.
Solution Approach 2:
Traditional manual examination methods are replaced with an automated artificial neural network system. The neural network automatically analyzes fundus images, extracts relevant features, and generates diagnostic information, substituting manual mechanical processes with intelligent automated analysis.
2Measurement precision
If deep learning technology is applied to medical diagnosis, then diagnostic accuracy is improved, but the complexity of the diagnostic system increases
Solution Approach 1:
The artificial neural network model is designed to perform multiple functions: it processes fundus images, extracts blood vessel features, generates diagnostic assistance information, and provides risk assessment. This multi-functional approach consolidates complex operations into a single versatile system.
Solution Approach 2:
The neural network model performs self-training and self-optimization through deep learning algorithms. The system automatically learns from training data and improves its diagnostic capabilities without requiring manual intervention for each diagnostic task, reducing operational complexity.
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.