Deep-Learning Retinal Blood-Vessel Analysis for Alzheimer’s Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current diagnosis methods for Alzheimer's disease are costly and complex, making it difficult for patients to access timely and affordable diagnostic tools beyond histological examinations.
Innovation Solution
A computing device utilizing deep learning technology to analyze retinal images, extracting blood vessel images through preprocessing and machine learning modules to provide diagnostic information for Alzheimer's disease, reducing the need for expensive imaging techniques like CT or MRI.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional diagnostic methods (CT, MRI, PET) are used for Alzheimer's disease diagnosis, then diagnostic accuracy is improved, but examination cost increases and accessibility decreases
Solution Approach 1:
The patent extracts and analyzes only the retinal region from the photographed image to generate a focused retinal image, then further extracts blood vessel images from this processed image. This extraction approach allows diagnosis using a specific, easily obtainable body part (retina) rather than requiring complex whole-body imaging, thereby reducing examination complexity while maintaining diagnostic value
Solution Approach 2:
The patent uses deep learning models to generate synthetic blood vessel images from retinal images. These generated images serve as diagnostic proxies that capture the essential pathological information needed for Alzheimer's diagnosis without requiring expensive and complex original imaging procedures, thus reducing both cost and complexity while preserving diagnostic accuracy
2Device complexity
If deep learning-based retinal image analysis is used, then examination cost decreases and accessibility improves, but diagnostic precision may be compromised
Solution Approach 1:
The patent replaces complex mechanical imaging systems (CT, MRI, PET scanners) with a computational approach using deep learning models. The system uses standard photographed images of the retina and processes them through trained neural networks to generate diagnostic information, substituting expensive hardware-based diagnostics with software-based analysis that maintains accuracy while reducing cost and complexity
Solution Approach 2:
The patent transforms the diagnostic approach by changing from direct imaging parameters (CT scans, MRI signals) to analyzing blood vessel morphology parameters extracted from retinal images. The deep learning models learn to detect subtle changes in blood vessel characteristics that correlate with Alzheimer's pathology, enabling accurate diagnosis through different measurable parameters that are easier and cheaper to obtain
Data Source
AI summary
Disclosed are a method for providing the necessary information for a diagnosis of Alzheimer's disease and an apparatus for executing the method. The apparatus for executing the method for providing the necessary information for a diagnosis of Alzheimer's disease includes one or more processors, a memory, and one or more programs, in which the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs includes an instruction for acquiring a photographed image of a patient's eyeball, an instruction for preprocessing the photographed image, generating a blood vessel image from the pre-processed photographed image using machine learning-based technology, and providing the necessary information for a diagnosis of Alzheimer's disease based on the generated blood vessel image, and an instruction for generating diagnostic prediction information based on the necessary information for a diagnosis of Alzheimer's disease.