Automatic Infectious Disease Classification Analysis with Concept Discovery

TL;DR

This paper explores automatic infectious disease classification from images, emphasizing the importance of concept discovery for interpretability, and introduces a unified NMF-based method applicable across various supervision levels.

Contribution

It introduces NMFx, a novel NMF-based approach for concept discovery that enhances interpretability in medical image classification across different supervision scenarios.

Findings

Evaluated concept discovery methods on tuberculosis and monkeypox prediction tasks.

Demonstrated NMFx’s effectiveness in unsupervised, weakly supervised, and supervised settings.

Improved understanding of neural network representations in medical diagnosis.

Abstract

Automatic infectious disease classification from images can facilitate needed medical diagnoses. Such an approach can identify diseases, like tuberculosis, which remain under-diagnosed due to resource constraints and also novel and emerging diseases, like monkeypox, which clinicians have little experience or acumen in diagnosing. Avoiding missed or delayed diagnoses would prevent further transmission and improve clinical outcomes. In order to understand and trust neural network predictions, analysis of learned representations is necessary. In this work, we argue that automatic discovery of concepts, i.e., human interpretable attributes, allows for a deep understanding of learned information in medical image analysis tasks, generalizing beyond the training labels or protocols. We provide an overview of existing concept discovery approaches in medical image and computer vision communities, and evaluate representative methods on tuberculosis (TB) prediction and monkeypox prediction tasks. Finally, we propose NMFx, a general NMF formulation of interpretability by concept discovery that works in a unified way in unsupervised, weakly supervised, and supervised scenarios.