Is Grad-CAM Explainable in Medical Images?

TL;DR

This paper investigates the effectiveness of Grad-CAM as an explainability technique in medical imaging, emphasizing its potential to improve interpretability and trust in deep learning models used for diagnosis.

Contribution

It provides an analysis of Grad-CAM's principles, discusses its limitations, and evaluates its application in medical imaging contexts.

Findings

Grad-CAM enhances interpretability in medical image classification

Explainable Deep Learning can improve diagnostic accuracy

Grad-CAM has limitations that need addressing

Abstract

Explainable Deep Learning has gained significant attention in the field of artificial intelligence (AI), particularly in domains such as medical imaging, where accurate and interpretable machine learning models are crucial for effective diagnosis and treatment planning. Grad-CAM is a baseline that highlights the most critical regions of an image used in a deep learning model's decision-making process, increasing interpretability and trust in the results. It is applied in many computer vision (CV) tasks such as classification and explanation. This study explores the principles of Explainable Deep Learning and its relevance to medical imaging, discusses various explainability techniques and their limitations, and examines medical imaging applications of Grad-CAM. The findings highlight the potential of Explainable Deep Learning and Grad-CAM in improving the accuracy and interpretability of deep learning models in medical imaging. The code is available in (will be available).