No Masks Needed: Explainable AI for Deriving Segmentation from Classification
This addresses segmentation challenges in medical imaging for healthcare applications, though it appears incremental as it adapts existing methods to a specific domain.
The paper tackles the problem of medical image segmentation by fine-tuning pre-trained models with Explainable AI to generate relevance scores, achieving improved results on datasets like CBIS-DDSM, NuInsSeg, and Kvasir-SEG.
Medical image segmentation is vital for modern healthcare and is a key element of computer-aided diagnosis. While recent advancements in computer vision have explored unsupervised segmentation using pre-trained models, these methods have not been translated well to the medical imaging domain. In this work, we introduce a novel approach that fine-tunes pre-trained models specifically for medical images, achieving accurate segmentation with extensive processing. Our method integrates Explainable AI to generate relevance scores, enhancing the segmentation process. Unlike traditional methods that excel in standard benchmarks but falter in medical applications, our approach achieves improved results on datasets like CBIS-DDSM, NuInsSeg and Kvasir-SEG.