Quanvolutional Neural Networks for Pneumonia Detection: An Efficient Quantum-Assisted Feature Extraction Paradigm

TL;DR

This work tackles pneumonia detection from chest X-ray images under data-scarce conditions by introducing a hybrid quantum-classical Quanvolutional Neural Network (QNN) that uses a parameterized quantum circuit to extract features from small image patches, which are then classified by a classical network. Key contributions include the design of a quanvolutional layer with Ry-based data encoding and entangling layers, and an empirical demonstration on the PneumoniaMNIST benchmark showing higher validation accuracy and better sample efficiency than a comparable classical CNN. The findings suggest that quantum-enhanced feature extraction can improve diagnostic performance while reducing data and computational demands, offering a foundation for future deployment on real quantum hardware and broader medical imaging tasks. Overall, the study provides evidence that QNNs can deliver practical benefits in medical AI, particularly in settings with limited labeled data and constrained computational resources.

Abstract

Pneumonia poses a significant global health challenge, demanding accurate and timely diagnosis. While deep learning, particularly Convolutional Neural Networks (CNNs), has shown promise in medical image analysis for pneumonia detection, CNNs often suffer from high computational costs, limitations in feature representation, and challenges in generalizing from smaller datasets. To address these limitations, we explore the application of Quanvolutional Neural Networks (QNNs), leveraging quantum computing for enhanced feature extraction. This paper introduces a novel hybrid quantum-classical model for pneumonia detection using the PneumoniaMNIST dataset. Our approach utilizes a quanvolutional layer with a parameterized quantum circuit (PQC) to process 2x2 image patches, employing rotational Y-gates for data encoding and entangling layers to generate non-classical feature representations. These quantum-extracted features are then fed into a classical neural network for classification. Experimental results demonstrate that the proposed QNN achieves a higher validation accuracy of 83.33 percent compared to a comparable classical CNN which achieves 73.33 percent. This enhanced convergence and sample efficiency highlight the potential of QNNs for medical image analysis, particularly in scenarios with limited labeled data. This research lays the foundation for integrating quantum computing into deep-learning-driven medical diagnostic systems, offering a computationally efficient alternative to traditional approaches.

Figures (4)

• Figure 1: Example of the dataset
• Figure 2: This figure illustrates Quantum Feature extraction
• Figure 3: Feature map generated using QNN
• Figure 4: Training and Validation Accuracy (top row) and Loss (bottom row) curves for the Hybrid QNN model (left column) and Classical CNN model (right column) over 10 epochs.