Domain Generalization with Quantum Enhancement for Medical Image Classification: A Lightweight Approach for Cross-Center Deployment

TL;DR

This work tackles cross-center generalization in medical imaging by proposing a lightweight quantum-enhanced domain-generalization framework. It combines multi-domain imaging shift simulation, a MobileNetV2-based domain-invariant encoder, a parameterized quantum feature layer, and domain-adversarial training with test-time adaptation to achieve robust generalization to unseen centers. Empirical results on simulated multi-center data show DG-Quantum delivering higher accuracy and AUC with tighter confidence intervals than classical baselines, demonstrating improved resilience to domain shift while remaining computationally feasible on laptop-level hardware. The findings support the feasibility and potential clinical impact of quantum–classical hybrids for robust, privacy-conscious cross-center medical imaging deployment.

Abstract

Medical image artificial intelligence models often achieve strong performance in single-center or single-device settings, yet their effectiveness frequently deteriorates in real-world cross-center deployment due to domain shift, limiting clinical generalizability. To address this challenge, we propose a lightweight domain generalization framework with quantum-enhanced collaborative learning, enabling robust generalization to unseen target domains without relying on real multi-center labeled data. Specifically, a MobileNetV2-based domain-invariant encoder is constructed and optimized through three key components: (1) multi-domain imaging shift simulation using brightness, contrast, sharpening, and noise perturbations to emulate heterogeneous acquisition conditions; (2) domain-adversarial training with gradient reversal to suppress domain-discriminative features; and (3) a lightweight quantum feature enhancement layer that applies parameterized quantum circuits for nonlinear feature mapping and entanglement modeling. In addition, a test-time adaptation strategy is employed during inference to further alleviate distribution shifts. Experiments on simulated multi-center medical imaging datasets demonstrate that the proposed method significantly outperforms baseline models without domain generalization or quantum enhancement on unseen domains, achieving reduced domain-specific performance variance and improved AUC and sensitivity. These results highlight the clinical potential of quantum-enhanced domain generalization under constrained computational resources and provide a feasible paradigm for hybrid quantum--classical medical imaging systems.

Figures (5)

• Figure 1: Confusion matrices of classification results across different models.
• Figure 2: Model performance metrics with 95% confidence intervals.
• Figure 3: Multimetric performance comparison across different models.
• Figure 4: Bootstrap performance distributions across different classification models.
• Figure 5: Receiver operating characteristic curves with confidence analysis.