Quantum Machine Learning Based Detection of Respiratory Disease using Digital Chest X-Ray Images

Abstract

The rapid growth of respiratory diseases such as pneumonia, tuberculosis, and COVID-19 has increased the demand for accurate, efficient, and automated diagnostic solutions. Conventional deep learning models have shown promising results in classifying chest X-ray images; however, they often require large datasets, high computational resources, and are limited in handling high-dimensional complex data. Quantum Machine Learning (QML) offers a novel paradigm that integrates quantum computing principles with machine learning techniques to overcome these limitations by exploiting quantum parallelism and entanglement for faster and more efficient computation. This research proposes a QML-based framework for the detection and classification of respiratory diseases using digital chest X-ray images. The methodology incorporates quantum-enhanced feature extraction and hybrid quantum-classical models to improve diagnostic accuracy while reducing computational complexity. Comparative evaluations with classical deep learning models demonstrate the potential of QML to achieve higher accuracy, robustness, and scalability in medical image classification tasks. The proposed approach highlights the future role of quantum-assisted medical imaging solutions in building faster, cost-effective, and clinically reliable diagnostic systems for global healthcare applications