Navigating limitations with precision: A fine-grained ensemble approach to wrist pathology recognition on a limited x-ray dataset

TL;DR

This paper presents a fine-grained ensemble method utilizing explainable AI to improve wrist pathology recognition on limited X-ray datasets, addressing subtle differences in medical images.

Contribution

It introduces a novel ensemble approach combined with Grad-CAM for fine-grained recognition of wrist pathologies using limited data, advancing medical image analysis.

Findings

Outperforms several state-of-the-art techniques

Effective in identifying subtle wrist pathologies

Utilizes only image-level annotations

Abstract

The exploration of automated wrist fracture recognition has gained considerable research attention in recent years. In practical medical scenarios, physicians and surgeons may lack the specialized expertise required for accurate X-ray interpretation, highlighting the need for machine vision to enhance diagnostic accuracy. However, conventional recognition techniques face challenges in discerning subtle differences in X-rays when classifying wrist pathologies, as many of these pathologies, such as fractures, can be small and hard to distinguish. This study tackles wrist pathology recognition as a fine-grained visual recognition (FGVR) problem, utilizing a limited, custom-curated dataset that mirrors real-world medical constraints, relying solely on image-level annotations. We introduce a specialized FGVR-based ensemble approach to identify discriminative regions within X-rays. We employ an Explainable AI (XAI) technique called Grad-CAM to pinpoint these regions. Our ensemble approach outperformed many conventional SOTA and FGVR techniques, underscoring the effectiveness of our strategy in enhancing accuracy in wrist pathology recognition.