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.
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.
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.
Quantum machine learning takes advantage of features such as quantum computing superposition and entanglement to enable better performance of machine learning models. In this paper, we first propose an improved hybrid quantum convolutional neural network (HQCNN) model. The HQCNN model was used to pre-train brain tumor dataset (MRI) images. Next, the quantum classical transfer learning (QCTL) approach is used to fine-tune and extract features based on pre-trained weights. A hybrid quantum convolutional network structure was used to test the osteoarthritis of the knee dataset (OAI) and to quantitatively evaluate standard metrics to verify the robustness of the classifier. The final experimental results show that the QCTL method can effectively classify knee osteoarthritis with a classification accuracy of 98.36%. The quantum-to-classical transfer learning method improves classification accuracy by 1.08%. How to use different coding techniques in HQCNN models applied to medical image analysis is also a future research direction.
Accurate and efficient classification of bone fractures from X-ray images is crucial for timely diagnosis, effective treatment planning, and improved patient outcomes in orthopedic medicine. Convolutional neural networks (CNNs) have demonstrated their ability to automatically extract relevant features from X-ray images, making them a powerful tool for the classification of complex bone fracture patterns. However, as the complexity of the classification task increases, the computational requirements of classical CNNs also grow rapidly. This poses a challenge in high-stakes medical applications, where the accuracy and efficiency of the classification system are paramount. In this work, we present a quantum convolutional neural network (QCNN) for the classification of bone fractures from X-ray images. A quantum convolution layer is integrated as the first layer of the network, which leverages the unique properties of quantum mechanics to extract more informative features from the input X-ray images. A traditional CNN network follows this quantum-based feature extraction step to perform the final bone fracture classification. We tested the proposed QCNN model on the Bone Fracture Multi-Region X-ray Data, a benchmark dataset for evaluating bone fracture classification systems. The QCNN architecture achieved an impressive 96% accuracy and 95.81% F1-score, demonstrating its superior performance compared to state-of-the-art classical CNN models.
Introduction: Medical image classification is a crucial task in cancer diagnosis, relying on the accurate analysis of high-dimensional imaging data. While Convolutional Neural Networks (CNNs) have shown great success in this domain, their performance is often limited by the shallow feature expressiveness and overfitting, particularly in small or heterogeneous datasets. Methods: Quantum machine learning offers new opportunities through high-dimensional representations and nonlinear transformations. In this work, we propose a Quantum-Enhanced Sandwich Convolutional Neural Network (QSCNN), a layered hybrid architecture that integrates quantum and classical modules. The model employs a quanvolutional layer for localized quantum feature extraction, followed by conventional convolution and pooling for hierarchical representation learning, and a variational quantum classifier for nonlinear decision-making. Results: QSCNN achieved higher accuracy and training stability than classical CNNs and QCCNN baselines across three medical imaging tasks.: brain tumor MRI, skin cancer dermoscopy, and lung cancer CT. Circuit depth analysis revealed a trade-off between expressiveness and robustness, and additional experiments with depolarizing noise confirmed the model’s resilience under realistic quantum error conditions. Discussion: This suggests that circuit design choices influence hybrid model behavior and generalization, supporting the feasibility of quantum-enhanced methods for small-sample medical imaging. However, the current evaluation is limited to relatively small benchmark datasets, and broader validation on large-scale data will be essential to confirm clinical applicability. Conclusion: In summary, QSCNN presents a feasible hybrid framework for enhancing medical image classification with quantum features. While preliminary, our results suggest potential advantages in accuracy and stability under NISQ conditions.
In recent years, there has been a growing interest in leveraging the unique properties of quantum computing to develop novel machine learning algorithms and architectures. This research paper presents an investigation of quantum convolutional neural networks (QCNNs), which leverage the unique properties of quantum computing to potentially improve the accuracy and efficiency of image classification tasks. Specifically, the paper explores three different QCNN architectures, including a pure quantum-based QCNN, a hybrid QCNN with a single quantum convolution layer, and a hybrid convolutional architecture with multiple quantum filters. We tested the models on MNIST dataset and the results of the study demonstrate that hybrid architectures that combine quantum and classical processing are more effective than pure quantum-based architectures in image classification tasks. In particular, the third model, the Hybrid Convolution with Multiple Quantum Filters, achieved the highest test set accuracy of 92.7%. The use of multiple quantum filters in conjunction with a classical neural network resulted in enhanced accuracy and efficiency in image classification tasks, highlighting the potential of hybrid architectures for future applications in machine learning tasks.
Convolutional Neural Networks (CNNs) are extensively utilized for image classification due to their ability to exploit data correlations effectively. However, traditional CNNs encounter several challenges, including limitations in accuracy improvement, computational efficiency, explain ability, and generalization. As data dimensionality or model complexity increases, CNNs often become more difficult to train efficiently, leading to slower processing times. To overcome these challenges, Quantum Convolutional Neural Networks (QCNNs) offer a promising quantum-based approach to enhance existing models, particularly by improving training efficiency and reducing processing times. This paper provides a comparative analysis of classical CNNs and a novel quantum circuit architecture tailored for image-based tasks. The analysis emphasizes the adaptability and potential of quantum circuits to enhance feature extraction, recognition accuracy, and processing efficiency.We applied various QCNN architectures to the Chinese-MNIST dataset and compared their performance with traditional CNN models. Although QCNNs achieved slightly lower accuracy, they demonstrated significantly greater stability. These findings high- light QCNNs’ potential to overcome the computational limitations of conventional deep learning, offering a promising pathway for quantum-enhanced solutions in computer vision. Future work will focus on refining quantum circuit designs, developing hybrid quantum-classical models, and extending QCNN applications to larger and more diverse datasets.