Med-CAM: Minimal Evidence for Explaining Medical Decision Making

TL;DR

Med-CAM introduces a novel method for generating minimal, faithful, and interpretable evidence maps in medical imaging AI, improving transparency and clinician trust.

Contribution

Med-CAM is a new framework that produces minimal, sharp, and faithful explanations for medical decisions using Classifier Activation Matching, surpassing prior methods.

Findings

Med-CAM provides conclusive, evidence-based explanations for model predictions.

It outperforms Grad-CAM and attention maps in spatial accuracy and interpretability.

Experiments demonstrate improved trust and understanding in clinical settings.

Abstract

Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances in deep learning, most medical AI systems operate as opaque black boxes, providing little insight into why a particular diagnosis was reached. In this paper, we introduce Med-CAM, a framework for generating minimal and sharp maps as evidence-based explanations for Medical decision making via Classifier Activation Matching. Med-CAM trains a segmentation network from scratch to produce a mask that highlights the minimal evidence critical to model's decision for any seen or unseen image. This ensures that the explanation is both faithful to the network's behaviour and interpretable to clinicians. Experiments show, unlike prior spatial explanation methods, such as Grad-CAM and attention maps, which yield only fuzzy regions of relative importance, Med-CAM with its superior spatial awareness to shapes, textures, and boundaries, delivers conclusive, evidence-based explanations that faithfully replicate the model's prediction for any given image. By explicitly constraining explanations to be compact, consistent with model activations, and diagnostic alignment, Med-CAM advances transparent AI to foster clinician understanding and trust in high-stakes medical applications such as pathology and radiology.