Rheumatoid arthritis classification using hybrid pretrained quantum convolutional neural network

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.