Generative Diffusion Augmentation with Quantum-Enhanced Discrimination for Medical Image Diagnosis
Jingsong Xia, Siqi Wang
TL;DR
This work tackles the problem of severe class imbalance in medical image diagnosis by introducing SDA-QEC, a framework that couples a forward-diffusion-based, lightweight data augmenter with a quantum-enhanced feature mapper embedded in MobileNetV2. The approach balances the training distribution and expands discriminative capacity through a compact quantum circuit with amplitude encoding, achieving state-of-the-art results on coronary angiography classification: 0.9833 accuracy, 0.9878 AUC, and 0.9833 F1, with equal sensitivity and specificity. Key contributions include the SimpleDiffusionAugmentor, a Pennylane-based QuantumFeatureLayer, and a highly parameter-efficient quantum path that dramatically reduces model size while boosting nonlinear discrimination. The findings demonstrate the practical feasibility of combining generative diffusion augmentation and quantum-enhanced modeling for reliable, edge-deployable medical AI in small-sample, high-risk diagnostic scenarios, with potential for meaningful clinical and economic impact.
Abstract
In biomedical engineering, artificial intelligence has become a pivotal tool for enhancing medical diagnostics, particularly in medical image classification tasks such as detecting pneumonia from chest X-rays and breast cancer screening. However, real-world medical datasets frequently exhibit severe class imbalance, where positive samples substantially outnumber negative samples, leading to biased models with low recall rates for minority classes. This imbalance not only compromises diagnostic accuracy but also poses clinical misdiagnosis risks. To address this challenge, we propose SDA-QEC (Simplified Diffusion Augmentation with Quantum-Enhanced Classification), an innovative framework that integrates simplified diffusion-based data augmentation with quantum-enhanced feature discrimination. Our approach employs a lightweight diffusion augmentor to generate high-quality synthetic samples for minority classes, rebalancing the training distribution. Subsequently, a quantum feature layer embedded within MobileNetV2 architecture enhances the model's discriminative capability through high-dimensional feature mapping in Hilbert space. Comprehensive experiments on coronary angiography image classification demonstrate that SDA-QEC achieves 98.33% accuracy, 98.78% AUC, and 98.33% F1-score, significantly outperforming classical baselines including ResNet18, MobileNetV2, DenseNet121, and VGG16. Notably, our framework simultaneously attains 98.33% sensitivity and 98.33% specificity, achieving a balanced performance critical for clinical deployment. The proposed method validates the feasibility of integrating generative augmentation with quantum-enhanced modeling in real-world medical imaging tasks, offering a novel research pathway for developing highly reliable medical AI systems in small-sample, highly imbalanced, and high-risk diagnostic scenarios.