Explainable CNN With Fuzzy Tree Regularization for Respiratory Sound Analysis

Jianqiang Li,Asoke K Nandi,Cheng Wang,Heng Zhang,Yuyan Dai,Jie Chen,Lingwei Wang,Li Wang

doi:10.1109/tfuzz.2022.3144448

Abstract

Auscultation is an important tool for diagnosing respiratory-related diseases. Unfortunately, the quality of auscultation is limited by the professional level of the doctor and the environment of the auscultation. Some studies have focused on automated auscultation techniques. However, existing approaches suffer from two challenges: 1) the models cannot learn from data distributed among multiple hospitals and 2) the predictions of the models are difficult to interpret for physicians. To address this issue, this article proposes a novel explainable respiratory sound analysis framework with fuzzy decision tree regularization. This framework develops an ensemble knowledge distillation technique to learn distributed data and achieves good performance in terms of model efficiency and accuracy. Fuzzy decision trees are used to explain the predictions of the model and produce decision rules that can be well accepted by physicians. The effectiveness of this framework is thoroughly validated on the Respiratory Sound database and compared with other existing approaches.

Highlights

C HRONIC Respiratory Diseases, such as Chronic Obstructive Pulmonary Disease (COPD) and Asthma, are responsible for a large number of deaths in the world, affecting more than 15% of the world population [1]
This work proposes a novel explainable Convolutional Neural Networks (CNN) framework based on fuzzy decision tree regularization for respiratory sounds analysis, which can learn distributed data from multiple hospitals and provide decision rules that can be simulated by
Fuzzy decision trees are used to deal with the uncertainty in the decision process, improving the interpretability of the model

Summary

Introduction

C HRONIC Respiratory Diseases, such as Chronic Obstructive Pulmonary Disease (COPD) and Asthma, are responsible for a large number of deaths in the world, affecting more than 15% of the world population [1]. According to the prediction of the World Health Organization, COPD will become the third leading cause of death in the world [2]. Respiratory sounds are commonly used to diagnose obstructive or restrictive lung diseases [4]. Fuzzy ID3 is a top-down algorithm applied to construct fuzzy decision trees. The fuzzy decision tree will be constructed by fuzzy ID3 algorithm [25]. The fuzzy ID3 algorithm splits the attributes based on fuzzy information gain by Eq 2 and the pseudocode is shown in Algorithm 1

Objectives

Methods

Findings

Conclusion