A Lightweight Medical Image Classification Framework via Self-Supervised Contrastive Learning and Quantum-Enhanced Feature Modeling

TL;DR

This paper introduces a lightweight, hybrid classical-quantum framework for medical image classification that leverages self-supervised learning and quantum feature modeling, achieving high accuracy with low computational cost.

Contribution

It presents a novel integration of quantum-enhanced feature modeling with self-supervised contrastive learning in a lightweight architecture for medical imaging.

Findings

Outperforms classical baselines in accuracy, AUC, and F1-score.

Uses only 2-3 million parameters, demonstrating efficiency.

Improves feature discriminability and stability.

Abstract

Intelligent medical image analysis is essential for clinical decision support but is often limited by scarce annotations, constrained computational resources, and suboptimal model generalization. To address these challenges, we propose a lightweight medical image classification framework that integrates self-supervised contrastive learning with quantum-enhanced feature modeling. MobileNetV2 is employed as a compact backbone and pretrained using a SimCLR-style self-supervised paradigm on unlabeled images. A lightweight parameterized quantum circuit (PQC) is embedded as a quantum feature enhancement module, forming a hybrid classical-quantum architecture, which is subsequently fine-tuned on limited labeled data. Experimental results demonstrate that, with only approximately 2-3 million parameters and low computational cost, the proposed method consistently outperforms classical baselines without self-supervised learning or quantum enhancement in terms of Accuracy, AUC, and F1-score. Feature visualization further indicates improved discriminability and representation stability. Overall, this work provides a practical and forward-looking solution for high-performance medical artificial intelligence under resource-constrained settings.