A Hybrid Classical-Quantum Machine Learning Framework for Tumor Mutation Classification: A Comprehensive Study of Quantum Optimizers in Medical Image Analysis
Md Jobair Hossain Faruk, Md Kamrul Siam, Jerry Q. Cheng +3 more
Classical machine learning methods face scalability and optimization challenges when applied to large-scale histopathological datasets. Quantum machine learning (QML) offers a promising direction by enabling compact high-dimensional feature encoding and alternative optimization strategies. In neuroblastoma (NB) histopathology, where accurate tumor mutation classification is critical for clinical decision-making, such capabilities are essential to capture subtle molecular variations often overlooked by conventional models. This study presents a hybrid classical-quantum machine learning framework for tumor mutation classification, combining ViT embeddings with a 4-qubit variational quantum circuit. We conducted experiments using 594,271 tumor relevant patches of size 512 × 512 pixels, collected from 97 manually annotated Whole Slide Images (WSIs) (≤ 150,000 × 100,000 pixels) provided by domain experts which also represents 85 NB cases across three U.S. medical institutions. The classical Adam baseline achieved 91.8% accuracy with tumor sensitivity of 97.3%. The hybrid model with Simultaneous Perturbation Stochastic Approximation (SPSA) reached 91.0% accuracy, while Quantum Natural Gradient (QNG) and Rotoselect underperformed (89.8% and 81.3%, respectively). Ablation experiments showed that both Quantum Multi-Head Attention (QMHA) and Quantum MLP (QMLP) blocks provide complementary gains, with circuit depth L=2 and vector readout offering the best trade-off between expressivity and stability. We further evaluated computational performance across dataset scales. Classical ViT exhibited a linear growth of approximately 21.33 minutes per WSI, while the hybrid QML model scaled more gradually at 19.36 minutes per WSI. Although QML incurred higher overhead at smaller dataset sizes, its slower growth rate allowed it to require less processing time than ViT starting at ≈ 133 WSIs, underscoring its potential for improved scalability on large datasets. Overall, this work establishes a systematic benchmark of hybrid QML for digital pathology, demonstrating competitive classification performance and the potential for improved efficiency as quantum hardware matures.
IEEE International Conference on Healthcare Informatics (ICHI)•Jun 1, 2026•0 citations