Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Frontiers in Artificial Intelligence

Rheumatoid arthritis classification using hybrid pretrained quantum convolutional neural network

D. Jeyamani, Rukmani Panjanathan

Published Aug 19, 2026• 0 citations
Publisher

Abstract

Rheumatoid arthritis (RA) is a chronic autoimmune disease where early diagnosis is critical for preventing irreversible joint damage. Recent advances in quantum computing have established potential advantages in modelling complex, high-dimensional biomedical data. The main objective of the work is to propose a Hybrid Pretrained Quantum Convolutional Neural Network (HP-QCNN) for automated RA classification from hand X-ray images. The proposed framework integrates pretrained convolutional neural networks with a variational quantum layer to enhance feature representation and classification performance. The hybrid architecture employs a 4-qubit quantum layer based on variational quantum circuits, utilizing quantum superposition and entanglement to perform parameter-efficient feature transformations. This quantum layer is embedded between a pretrained feature extractor and a classical classification head. Multiple pretrained backbones were explored in a hybrid quantum-optimized activation function. The proposed VGG16-based HP-QCNN achieved the highest classification accuracy, outperforming DenseNet121, MobileNetV2, EfficientNetB3, and InceptionV3. The proposed model highlights quantum computing efficiency by achieving an accuracy as 92.41%, the highest ROC-AUC, and specificity over 95%, which outperforms the classical VGG16 baseline by 7.3, 3, and 10%, respectively. Stratification ensures the class distribution, while weighted classes reduce the residual class imbalance. The best Matthews correlation coefficient and Cohen's kappa score, which are above the baseline (0.7), indicate strong class separability and reliability under class imbalance. These results confirm the effectiveness of quantum-enhanced deep learning in medical image analysis.

DOI
10.3389/frai.2026.1794495

Related papers

Osteoarthritis Classification Using Hybrid Quantum Convolutional Neural Network

Devansh Tikariha, Abdul Moomin, D. Jeyamani +1 more

This work explores the integration of quantum computing within a classical Convolutional Neural Network (CNN) framework, leveraging a VGG16 model enhanced with a quantum Convolutional Neural Network (QCNN) for the classification of knee osteoarthritis (OA) severity. A custom quantum layer was incorporated to boost the model’s feature extraction capabilities, enabling effective differentiation between healthy and OA-affected knees in medical imaging data. The model utilizes the Swish activation function, which combines smoothness and nonlinearity to enhance learning efficiency and gradient flow, which are critical in complex diagnostic tasks. Using a QCNN, this model harnesses the ability of quantum computing to represent high-dimensional data transformations, a novel approach that complements classical CNN layers by exploring patterns that are not easily captured in traditional networks. The initial results showed a high classification accuracy of 97.26%, suggesting that quantum-enhanced layers can significantly bolster feature extraction and classification in medical diagnostics. Furthermore, multiple variations of pre-trained models with Quantum Convolutional Layers, such as XceptionNet, ResNet, and InceptionNet, were developed and compared in terms of the evaluation metrics that achieved 87.84,89.70,86.64, respectively. This hybrid VGG16-QCNN model showed the highest accuracy, demonstrating the potential of QCNNs in advancing the precision and scalability of AI-driven healthcare solutions.

IEEE Access•Jan 1, 2025•2 citations

Hybrid Quantum-Classical Neural Networks for Medical Image Diagnosis

Mayank Genwa

Medical image classification is a fundamental aspect of contemporary diagnosis, but the conventional Deep Learning (DL) model is increasingly encountering difficulties in terms of computational complexity, data availability, and interpretability. With the massive growth of medical data, the "black box" phenomenon of Convolutional Neural Networks (CNNs) hinders medical validation. This paper presents a novel Hybrid Quantum-Classical Neural Network (HQCNN) approach for multimodal diagnosis, specifically addressing Brain Tumors (MRI), Pneumonia (Chest X-Ray), and Retinal Diseases (OCT). The proposed model combines a pre-trained ResNet-18 backbone for high-level feature representation with a 4-qubit Variational Quantum Circuit (VQC) to harness the power of quantum entanglement for improved classification in high-dimensional Hilbert spaces. More-over, we close the interpretability gap by incorporating Gradient-weighted Class Activation Mapping (Grad-CAM). Experimental results show that the hybrid model performs exceptionally well, specifically with 98.76% accuracy on Retina OCT, 90.71% accuracy on Chest X-Rays and 95.27% on Brain MRI, with a substantial decrease in trainable parameters in the decision head compared to classical models.

International Conference on Cognitive Computing and Networking Systems (ICC-CNS)•Jun 1, 2026•0 citations

HQCNN: A Hybrid Quantum-Classical Neural Network for Medical Image Classification

Shahjalal, Jahid Karim Fahim, Pintu Chandra Paul +3 more

Classification of medical images plays a vital role in medical image analysis; however, it remains challenging due to the limited availability of labeled data, class imbalances, and the complexity of medical patterns. To overcome these challenges, we propose a novel Hybrid Quantum-Classical Neural Network (HQCNN) for both binary and multi-class classification. The architecture of HQCNN integrates a five-layer classical convolutional backbone with a 4-qubit variational quantum circuit that incorporates quantum state encoding, superpositional entanglement, and a Fourier-inspired quantum attention mechanism. We evaluate the model on six MedMNIST v2 benchmark datasets. The HQCNN consistently outperforms classical and quantum baselines, achieving up to 99.91% accuracy and 100.00% AUC on PathMNIST (binary) and 99.95% accuracy on OrganAMNIST (multi-class) with strong robustness on noisy datasets like BreastMNIST (87.18% accuracy). The model demonstrates superior generalization capability and computational efficiency, accomplished with significantly fewer trainable parameters, making it suitable for data-scarce scenarios. Our findings provide strong empirical evidence that hybrid quantum-classical models can advance medical imaging tasks.

arXiv:2509.14277•Sep 16, 2025•5 citations

HQCNN: a hybrid quantum-classical neural network with Fourier-inspired quantum attention for medical image classification

Shahjalal Khan, Jahid Karim Fahim, Pintu Chandra Paul +5 more

Medical image classification is a critical component of modern healthcare; however, accurate diagnosis remains challenging due to limited annotated datasets, class imbalance, and the high dimensionality of medical imaging data. To address these challenges, a hybrid quantum-classical neural network (HQCNN) is proposed, integrating classical deep learning with variational quantum learning for medical image classification. The proposed architecture combines a five-layer convolutional neural network (CNN) for hierarchical feature extraction with a lightweight 4-qubit variational quantum circuit (VQC) incorporating quantum state encoding, superposition and entanglement mechanisms, and a quantum attention-Fourier (QAF) module. This hybrid design aims to improve nonlinear feature representation and quantum parameter efficiency while maintaining a shallow quantum circuit suitable for noisy intermediate-scale quantum (NISQ)-era constraints. Experimental evaluation on six MedMNIST benchmark datasets demonstrated competitive performance across both binary and multi-class classification tasks. HQCNN achieved 98.88% accuracy on the binary subset of PathMNIST (classes 0 vs. 1), 97.61% accuracy on the multi-class OrganAMNIST dataset, and 86.29% accuracy on BreastMNIST. Comparative experiments and statistical analyses demonstrated consistent improvements over the controlled BHQNN baseline, while component-wise ablation studies showed that the QAF module, superposition and entanglement mechanisms, and expressive parameterized rotations contributed to classification performance in a complementary and dataset-dependent manner. Moreover, HQCNN reduced the number of trainable quantum parameters by approximately 55.6% compared with the baseline hybrid quantum neural network (BHQNN). Noise-aware simulations further showed that the model retained relatively stable predictive performance under moderate depolarizing noise, supporting further evaluation under near-term quantum computing conditions. Overall, the results demonstrate that HQCNN provides a parameter-efficient hybrid quantum-classical framework for medical image classification and offers a promising foundation for further investigation of quantum-enhanced medical image analysis.

International Journal of Advanced Technology and Engineering Exploration•Aug 31, 2026•0 citations

Quantum-Enhanced CNN for Multi-Class Retinal Disease Classification from OCT Images

Lovish Bhatia, Shreyansh Gupta, Rizil Patel +1 more

Abstract This study demonstrates that a hybrid CNN–QNN architecture outperforms classical CNNs for multi-class retinal OCT classification by leveraging variational quantum circuits to enhance feature separability. Early detection of retinal diseases through optical coherence tomography (OCT) imaging is critical for timely intervention and vision preservation. While classical convolutional neural networks (CNNs) excel at pattern recognition in retinal OCT B-scans, their ability to capture complex, non-linear feature relationships in subtle disease manifestations remains limited. Hybrid quantum-classical architectures offer a promising approach by leveraging variational quantum circuits to enhance feature separability in challenging classification regimes. This study presents a hybrid CNN–QNN architecture for multi-class classification of retinal OCT images dataset (CNV, DME, DRUSEN, NORMAL). A classical CNN backbone extracts hierarchical spatial features from B-scans, which are then processed through parallel classical and quantum classification heads. The quantum head employs a 5-qubit variational quantum circuit with angle embedding and strongly entangling layers to generate quantum-enhanced feature representations. Outputs from both heads are concatenated and passed through a final softmax layer for four-class prediction. The findings establish hybrid quantum-classical neural networks as a viable enhancement to conventional deep learning for retinal OCT analysis, offering improved discriminative performance on established medical imaging benchmarks through quantum feature transformations.

•Mar 20, 2026•0 citations

A Hybrid Quantum–Classical Convolutional Neural Network for Enhanced Image Classification

D. Deepika, K Vanishree, Munishamaiah Krishna

The objective of this research is to develop a Hybrid Quantum-Classical Convolutional Neural Network (QC-CNN) framework that integrates parameterized quantum circuits (PQCs) within classical CNN architectures to enhance image classification performance.The proposed model leverages quantum principles such as superposition and entanglement for high-dimensional feature representation, achieving superior accuracy and reduced computational complexity.Experiments on MNIST and CIFAR-10 datasets demonstrated improved classification accuracy of 98.7% and 82.5%, respectively, surpassing traditional CNNs while reducing training time by 33% and parameters by 45%.Statistical analysis confirmed the significance of these improvements.Visualizations using t-SNE revealed enhanced class separability, and noise perturbation tests validated the model's robustness.The results highlight the hybrid QC-CNN's potential for efficient and scalable quantum-enhanced deep learning applications.Extended evaluations, including quantum-layer-depth analysis, robustness testing, and t-SNE visualization, empirically support the hybrid QC-CNN's effectiveness across varied scenarios.

International Journal of Computer Applications•Dec 18, 2025•2 citations
Rheumatoid arthritis (RA) is a chronic autoimmune disease where early diagnosis is critical for preventing irreversible joint damage. Recent advances in quantum computing have established potential advantages in modelling complex, high-dimensional biomedical data. The main objective of the work is to propose a Hybrid Pretrained Quantum Convolutional Neural Network (HP-QCNN) for automated RA classification from hand X-ray images. The proposed framework integrates pretrained convolutional neural networks with a variational quantum layer to enhance feature representation and classification performance. The hybrid architecture employs a 4-qubit quantum layer based on variational quantum circuits, utilizing quantum superposition and entanglement to perform parameter-efficient feature transformations. This quantum layer is embedded between a pretrained feature extractor and a classical classification head. Multiple pretrained backbones were explored in a hybrid quantum-optimized activation function. The proposed VGG16-based HP-QCNN achieved the highest classification accuracy, outperforming DenseNet121, MobileNetV2, EfficientNetB3, and InceptionV3. The proposed model highlights quantum computing efficiency by achieving an accuracy as 92.41%, the highest ROC-AUC, and specificity over 95%, which outperforms the classical VGG16 baseline by 7.3, 3, and 10%, respectively. Stratification ensures the class distribution, while weighted classes reduce the residual class imbalance. The best Matthews correlation coefficient and Cohen's kappa score, which are above the baseline (0.7), indicate strong class separability and reliability under class imbalance. These results confirm the effectiveness of quantum-enhanced deep learning in medical image analysis.
This work explores the integration of quantum computing within a classical Convolutional Neural Network (CNN) framework, leveraging a VGG16 model enhanced with a quantum Convolutional Neural Network (QCNN) for the classification of knee osteoarthritis (OA) severity. A custom quantum layer was incorporated to boost the model’s feature extraction capabilities, enabling effective differentiation between healthy and OA-affected knees in medical imaging data. The model utilizes the Swish activation function, which combines smoothness and nonlinearity to enhance learning efficiency and gradient flow, which are critical in complex diagnostic tasks. Using a QCNN, this model harnesses the ability of quantum computing to represent high-dimensional data transformations, a novel approach that complements classical CNN layers by exploring patterns that are not easily captured in traditional networks. The initial results showed a high classification accuracy of 97.26%, suggesting that quantum-enhanced layers can significantly bolster feature extraction and classification in medical diagnostics. Furthermore, multiple variations of pre-trained models with Quantum Convolutional Layers, such as XceptionNet, ResNet, and InceptionNet, were developed and compared in terms of the evaluation metrics that achieved 87.84,89.70,86.64, respectively. This hybrid VGG16-QCNN model showed the highest accuracy, demonstrating the potential of QCNNs in advancing the precision and scalability of AI-driven healthcare solutions.
Medical image classification is a fundamental aspect of contemporary diagnosis, but the conventional Deep Learning (DL) model is increasingly encountering difficulties in terms of computational complexity, data availability, and interpretability. With the massive growth of medical data, the "black box" phenomenon of Convolutional Neural Networks (CNNs) hinders medical validation. This paper presents a novel Hybrid Quantum-Classical Neural Network (HQCNN) approach for multimodal diagnosis, specifically addressing Brain Tumors (MRI), Pneumonia (Chest X-Ray), and Retinal Diseases (OCT). The proposed model combines a pre-trained ResNet-18 backbone for high-level feature representation with a 4-qubit Variational Quantum Circuit (VQC) to harness the power of quantum entanglement for improved classification in high-dimensional Hilbert spaces. More-over, we close the interpretability gap by incorporating Gradient-weighted Class Activation Mapping (Grad-CAM). Experimental results show that the hybrid model performs exceptionally well, specifically with 98.76% accuracy on Retina OCT, 90.71% accuracy on Chest X-Rays and 95.27% on Brain MRI, with a substantial decrease in trainable parameters in the decision head compared to classical models.
Classification of medical images plays a vital role in medical image analysis; however, it remains challenging due to the limited availability of labeled data, class imbalances, and the complexity of medical patterns. To overcome these challenges, we propose a novel Hybrid Quantum-Classical Neural Network (HQCNN) for both binary and multi-class classification. The architecture of HQCNN integrates a five-layer classical convolutional backbone with a 4-qubit variational quantum circuit that incorporates quantum state encoding, superpositional entanglement, and a Fourier-inspired quantum attention mechanism. We evaluate the model on six MedMNIST v2 benchmark datasets. The HQCNN consistently outperforms classical and quantum baselines, achieving up to 99.91% accuracy and 100.00% AUC on PathMNIST (binary) and 99.95% accuracy on OrganAMNIST (multi-class) with strong robustness on noisy datasets like BreastMNIST (87.18% accuracy). The model demonstrates superior generalization capability and computational efficiency, accomplished with significantly fewer trainable parameters, making it suitable for data-scarce scenarios. Our findings provide strong empirical evidence that hybrid quantum-classical models can advance medical imaging tasks.
Medical image classification is a critical component of modern healthcare; however, accurate diagnosis remains challenging due to limited annotated datasets, class imbalance, and the high dimensionality of medical imaging data. To address these challenges, a hybrid quantum-classical neural network (HQCNN) is proposed, integrating classical deep learning with variational quantum learning for medical image classification. The proposed architecture combines a five-layer convolutional neural network (CNN) for hierarchical feature extraction with a lightweight 4-qubit variational quantum circuit (VQC) incorporating quantum state encoding, superposition and entanglement mechanisms, and a quantum attention-Fourier (QAF) module. This hybrid design aims to improve nonlinear feature representation and quantum parameter efficiency while maintaining a shallow quantum circuit suitable for noisy intermediate-scale quantum (NISQ)-era constraints. Experimental evaluation on six MedMNIST benchmark datasets demonstrated competitive performance across both binary and multi-class classification tasks. HQCNN achieved 98.88% accuracy on the binary subset of PathMNIST (classes 0 vs. 1), 97.61% accuracy on the multi-class OrganAMNIST dataset, and 86.29% accuracy on BreastMNIST. Comparative experiments and statistical analyses demonstrated consistent improvements over the controlled BHQNN baseline, while component-wise ablation studies showed that the QAF module, superposition and entanglement mechanisms, and expressive parameterized rotations contributed to classification performance in a complementary and dataset-dependent manner. Moreover, HQCNN reduced the number of trainable quantum parameters by approximately 55.6% compared with the baseline hybrid quantum neural network (BHQNN). Noise-aware simulations further showed that the model retained relatively stable predictive performance under moderate depolarizing noise, supporting further evaluation under near-term quantum computing conditions. Overall, the results demonstrate that HQCNN provides a parameter-efficient hybrid quantum-classical framework for medical image classification and offers a promising foundation for further investigation of quantum-enhanced medical image analysis.
Abstract This study demonstrates that a hybrid CNN–QNN architecture outperforms classical CNNs for multi-class retinal OCT classification by leveraging variational quantum circuits to enhance feature separability. Early detection of retinal diseases through optical coherence tomography (OCT) imaging is critical for timely intervention and vision preservation. While classical convolutional neural networks (CNNs) excel at pattern recognition in retinal OCT B-scans, their ability to capture complex, non-linear feature relationships in subtle disease manifestations remains limited. Hybrid quantum-classical architectures offer a promising approach by leveraging variational quantum circuits to enhance feature separability in challenging classification regimes. This study presents a hybrid CNN–QNN architecture for multi-class classification of retinal OCT images dataset (CNV, DME, DRUSEN, NORMAL). A classical CNN backbone extracts hierarchical spatial features from B-scans, which are then processed through parallel classical and quantum classification heads. The quantum head employs a 5-qubit variational quantum circuit with angle embedding and strongly entangling layers to generate quantum-enhanced feature representations. Outputs from both heads are concatenated and passed through a final softmax layer for four-class prediction. The findings establish hybrid quantum-classical neural networks as a viable enhancement to conventional deep learning for retinal OCT analysis, offering improved discriminative performance on established medical imaging benchmarks through quantum feature transformations.
The objective of this research is to develop a Hybrid Quantum-Classical Convolutional Neural Network (QC-CNN) framework that integrates parameterized quantum circuits (PQCs) within classical CNN architectures to enhance image classification performance.The proposed model leverages quantum principles such as superposition and entanglement for high-dimensional feature representation, achieving superior accuracy and reduced computational complexity.Experiments on MNIST and CIFAR-10 datasets demonstrated improved classification accuracy of 98.7% and 82.5%, respectively, surpassing traditional CNNs while reducing training time by 33% and parameters by 45%.Statistical analysis confirmed the significance of these improvements.Visualizations using t-SNE revealed enhanced class separability, and noise perturbation tests validated the model's robustness.The results highlight the hybrid QC-CNN's potential for efficient and scalable quantum-enhanced deep learning applications.Extended evaluations, including quantum-layer-depth analysis, robustness testing, and t-SNE visualization, empirically support the hybrid QC-CNN's effectiveness across varied scenarios.