AI-Based Approaches for Respiratory Disease Detection Using Audio Signals and Imaging Data

Abstract

Respiratory diseases (RDs) remain major global health concerns, typically diagnosed through imaging and auscultation, with cough sounds also offering diagnostic cues. These methods, however, are often subjective and depend on expert interpretation. Advances in machine learning (ML) enable automated RD diagnosis, yet challenges such as limited data, high computational costs, and accessibility gaps persist, underscoring the need for innovative approaches. This thesis proposes a series of novel approaches for automated RD detection, utilizing either cough audio or CXR as input modalities, selected for their availability and affordability. These approaches integrate advanced techniques for segmentation, feature extraction, and subsequent classification, offering practical and cost-effective diagnostic solutions. Extensive evaluation on multiple open-source datasets demonstrates the effectiveness of the proposed approaches across diverse diagnostic contexts.