Approach to Designing CV Systems for Medical Applications: Data, Architecture and AI

TL;DR

This paper presents a novel AI-based system for fundus image analysis that mimics clinical diagnosis by analyzing features without predicting specific diseases, aiming to improve objectivity and workflow in ophthalmology.

Contribution

It introduces a new modular AI-driven architecture for fundus analysis that emphasizes feature examination over disease prediction, aligning with clinical practices.

Findings

Effective analysis of fundus features demonstrated

System enhances clinical workflow and objectivity

Potential for application in various medical domains

Abstract

This paper introduces an innovative software system for fundus image analysis that deliberately diverges from the conventional screening approach, opting not to predict specific diagnoses. Instead, our methodology mimics the diagnostic process by thoroughly analyzing both normal and pathological features of fundus structures, leaving the ultimate decision-making authority in the hands of healthcare professionals. Our initiative addresses the need for objective clinical analysis and seeks to automate and enhance the clinical workflow of fundus image examination. The system, from its overarching architecture to the modular analysis design powered by artificial intelligence (AI) models, aligns seamlessly with ophthalmological practices. Our unique approach utilizes a combination of state-of-the-art deep learning methods and traditional computer vision algorithms to provide a comprehensive and nuanced analysis of fundus structures. We present a distinctive methodology for designing medical applications, using our system as an illustrative example. Comprehensive verification and validation results demonstrate the efficacy of our approach in revolutionizing fundus image analysis, with potential applications across various medical domains.