Explainable Transformer Prototypes for Medical Diagnoses

TL;DR

This paper introduces a novel prototype-based attention mechanism for Transformer models in medical diagnosis, enhancing explainability by highlighting regions of interest, thereby increasing trust and facilitating clinical adoption.

Contribution

It proposes a new attention block that emphasizes region-to-region correlations using prototype learning, improving interpretability over traditional pixel-based explanations.

Findings

Demonstrated effectiveness on NIH chest X-ray dataset

Provided both quantitative and qualitative validation

Enhanced interpretability of Transformer-based diagnostics

Abstract

Deployments of artificial intelligence in medical diagnostics mandate not just accuracy and efficacy but also trust, emphasizing the need for explainability in machine decisions. The recent trend in automated medical image diagnostics leans towards the deployment of Transformer-based architectures, credited to their impressive capabilities. Since the self-attention feature of transformers contributes towards identifying crucial regions during the classification process, they enhance the trustability of the methods. However, the complex intricacies of these attention mechanisms may fall short of effectively pinpointing the regions of interest directly influencing AI decisions. Our research endeavors to innovate a unique attention block that underscores the correlation between 'regions' rather than 'pixels'. To address this challenge, we introduce an innovative system grounded in prototype learning, featuring an advanced self-attention mechanism that goes beyond conventional ad-hoc visual explanation techniques by offering comprehensible visual insights. A combined quantitative and qualitative methodological approach was used to demonstrate the effectiveness of the proposed method on the large-scale NIH chest X-ray dataset. Experimental results showed that our proposed method offers a promising direction for explainability, which can lead to the development of more trustable systems, which can facilitate easier and rapid adoption of such technology into routine clinics. The code is available at www.github.com/NUBagcilab/r2r_proto.