Prototype Learning for Interpretable Respiratory Sound Analysis

TL;DR

This paper introduces a prototype learning framework for respiratory sound classification that enhances interpretability while maintaining high accuracy, outperforming existing methods on a large public dataset.

Contribution

The study presents a novel prototype learning approach that generates exemplar samples for explanation and integrates them into DNNs for interpretable respiratory sound analysis.

Findings

Outperforms state-of-the-art methods on a large respiratory sound dataset

Provides interpretable explanations through exemplar samples

Achieves high classification accuracy in respiratory disease screening

Abstract

Remote screening of respiratory diseases has been widely studied as a non-invasive and early instrument for diagnosis purposes, especially in the pandemic. The respiratory sound classification task has been realized with numerous deep neural network (DNN) models due to their superior performance. However, in the high-stake medical domain where decisions can have significant consequences, it is desirable to develop interpretable models; thus, providing understandable reasons for physicians and patients. To address the issue, we propose a prototype learning framework, that jointly generates exemplar samples for explanation and integrates these samples into a layer of DNNs. The experimental results indicate that our method outperforms the state-of-the-art approaches on the largest public respiratory sound database.