On the Complementarity of Quantum and Classical Features: Adaptive Hybrid Quantum-Classical Feature Fusion for Breast Cancer Classification

2026-04-24

AI Summary

This work addresses the optimization asymmetry arising from the fusion of quantum and classical features in breast cancer image classification by proposing a dual-branch hybrid architecture that integrates a ResNet backbone with a trainable quantum circuit to extract complementary representations. To effectively combine these features, the study introduces three progressive fusion strategies: static, dynamic, and a novel temperature-scaled hybrid fusion (TSHF). The TSHF mechanism incorporates a learnable scalar to dynamically balance gradients, thereby alleviating optimization bottlenecks commonly encountered in hybrid model training. Experimental results on BreastMNIST demonstrate that the proposed approach achieves 87.82% accuracy, 91.77% F1 score, and 89.08% AUC-ROC, significantly outperforming purely classical baselines.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

The integration of quantum machine learning with classical deep learning offers promising avenues for medical image analysis by mapping data into high-dimensional Hilbert spaces. However, effectively unifying these distinct paradigms remains challenging due to common optimization asymmetries. In this paper, a novel hybrid quantum-classical architecture for breast cancer diagnosis based on a dual-branch feature-extraction pipeline is proposed. Our framework extracts and unifies complementary representations from classical models and quantum circuits, exploring both trainable and deterministic (non-trainable) quantum paradigms. To integrate these embeddings, three progressive feature fusion strategies are introduced: Static Hybrid Fusion (SHF) for offline extraction, Dynamic Hybrid Fusion (DHF) for end-to-end co-adaptation, and a novel Temperature-Scaled Hybrid Fusion (TSHF). The TSHF strategy incorporates a learnable scalar, inspired by multimodal learning, that dynamically balances hybrid gradient dynamics and resolves optimization bottlenecks. Empirical validation on the BreastMNIST dataset confirms our hypothesis that unifying diverse feature representations creates a richer data context. The TSHF strategy, specifically when pairing a ResNet backbone with a trainable quantum circuit, achieved a peak accuracy of 87.82%, F1-score of 91.77%, and an AUC-ROC of 89.08%, outperforming purely classical baselines. These results demonstrate that the proposed hybrid framework improves classification accuracy and threshold reliability, providing a stable, high-performance architecture for the clinical deployment of quantum-enhanced diagnostic tools.

Problem

• quantum-classical fusion
• breast cancer classification
• feature integration
• optimization asymmetry
• hybrid architectures

Innovation

• Quantum-Classical Fusion
• Temperature-Scaled Hybrid Fusion
• Breast Cancer Classification
• Quantum Machine Learning
• Feature Representation