This study presents a comparative analysis of traditional deep learning and a novel quantum- assisted neural network for brain stroke identification on brain CT images. We compared traditional convolutional neural network (CNN) architectures such as ResNet18, VGG16, MobileNetV2 and In- ceptionV3. We found a hybrid quantum-classical approach which incorporated ResNet and MobileNet feature extraction tools and combined the extracted features in a quantum circuit for processing. The accuracy obtained for the quantum-assisted model on our validation dataset was 99.15%, which is a significant improvement from the traditional models: ResNet18 98.30%, VGG16 98.30%, MobileNetV2 97.02%, and InceptionV3 97.87%. These results indicate that there are likely advantages in enhanced medical image analysis by incorporating quantum techniques that may be useful in high stakes diagnos- tic like stroke detection. The hybrid architecture reflected some unique dynamic model assignment of importance for prediction assignment, with ResNet features contributing about 51.17% and MobileNet features contributing 48.83% to the overall predictions.
This study presents a comparative analysis of traditional deep learning and a novel quantum- assisted neural network for brain stroke identification on brain CT images. We compared traditional convolutional neural network (CNN) architectures such as ResNet18, VGG16, MobileNetV2 and In- ceptionV3. We found a hybrid quantum-classical approach which incorporated ResNet and MobileNet feature extraction tools and combined the extracted features in a quantum circuit for processing. The accuracy obtained for the quantum-assisted model on our validation dataset was 99.15%, which is a significant improvement from the traditional models: ResNet18 98.30%, VGG16 98.30%, MobileNetV2 97.02%, and InceptionV3 97.87%. These results indicate that there are likely advantages in enhanced medical image analysis by incorporating quantum techniques that may be useful in high stakes diagnos- tic like stroke detection. The hybrid architecture reflected some unique dynamic model assignment of importance for prediction assignment, with ResNet features contributing about 51.17% and MobileNet features contributing 48.83% to the overall predictions.
Medical image classification is considered as very important field of diagnosis and treatment of neurological disorders, which include stroke, tumors, and hemorrhages, it can used to facilitate timely medical intervention. A hybrid quantum-classical convolutional neural network (QCNN) is presented by combining quantum information processing with classical deep learning techniques for improved feature extraction and classification accuracy. The model combines convolutional neural network (CNN), which handles initial feature extraction with a PennyLane and TensorFlow based layer that employs quantum entanglement and superposition principles to enhance classification performance. The model is trained and tested over a computed tomography (CT) scan image dataset which has four classes (normal, stroke, tumor, and hemorrhage). Various learning rates are tested and employed a hybrid backpropagation method to improve efficiency. Confusion matrices, region of conversion receiver operating characteristic (ROC) curves, and plots for the training convergence that all pointed to promising classification accuracy were derived with a detailed analysis accordingly. Overall, the results indicate that combining quantum computing with deep learning architectures could improve classification performance at a lowest computational cost. The results suggest the viability of hybrid quantum-classical models for medical imaging applications and indicate that quantum computing is a promising direction for enhancing diagnostic accuracy in the area of radiology.
Introduction: Brain stroke is still one of the leading causes of death and long-term disability in the world. Early and correct diagnosis is therefore important for patient outcome. Although Convolution Neural Network (CNN), classical machine learning models, have achieved great progress in medical image classification, they have to face the performance saturation problem when dealing with high-dimensional and complex data such as medical images. To tackle these limitations, we propose QBrainNet, a quantum enhanced model, which is to enhance brain stroke prediction from medical imaging datasets. Methods: The model consists of Quantum Neural Networks (QNNs) applied as learning complex patterns in terms of medical images and Variational Quantum Circuits (VQCs) that will be used to optimize the classification. The feature extraction featured in the QNNs utilises quantum properties of superposition and entanglement to extract non-linear high-dimensional patterns in images related to stroke that may not be captured using classical limits. The VQCs, in turn, are applied to optimize the model performance, further allocating the boundaries of the decision and enhancing the model performance in terms of accuracy by optimizing the quantum gates and operators used during the work. QBrainNet utilizes the combination of such quantum properties as entanglement and superposition to represent more complicated non-linear patterns in stroke-specific images in a better manner than a classical application does. Results: This paper proposes a hybrid classical-quantum scheme: preprocessing classically, and learning quantum-enhanced. Quantum gates and operators are used when performing the quantum phase to optimize decision boundaries, achieving vastly enhanced prediction accuracy and efficiency performance. Experimental results indicate that QBrainNet has a better accuracy (96%) and AUC-PR (0.97) than the classical models like CNN, SVM, and Random Forest, proving the superior performance of QBrainNet in stroke detection. Discussion: The inference time is shorter, so the model can be used as a real-time clinical application. This article points to the possibilities quantum computing can have in revolutionizing medical diagnostics, especially stroke prediction.
Brain tumor detection is a vital and challenging task in medical diagnosis, requiring highly precise and efficient methods to improve patient treatment outcomes. Traditional approaches rely on classical machine learning and deep learning techniques, which, while effective to a degree, often struggle with capturing the complex and high-dimensional patterns present in medical imaging data. A significant limitation of these conventional methods is their inability to process and analyze intricate features efficiently, which can impact diagnostic accuracy. To address these challenges, this work proposes a novel Quantum Convolutional Neural Network (QCNN) framework that combines quantum computing principles, via quantum circuits, with classical machine learning architectures implemented through tools like PyTorch and PennyLane. This hybrid approach enhances feature extraction and classification capabilities, leading to superior performance. Experimental results demonstrate that the QCNN model achieves an improved accuracy of 90 percent on the test dataset, surpassing traditional methods and showing promise for advancing brain tumor detection technology. This improvement is supported by consistent decreases in training and validation loss during model training, highlighting the robustness and efficacy of the quantum-enhanced model.
This research presents a new hybrid model that combines the capabilities of a pre-trained ResNet-50 with a Quantum Neural Network (QNN) to enhance the classification of MRI brain images for tumor recognition. Combining conventional deep learning and quantum computing, this technique competes with traditional models regarding accuracy, speed, and computational effectiveness. The ResNet-50 architecture is the foundation for feature extraction, using its demonstrated ability to handle challenging MRI image data. ResNet-50's linear layer weights are converted into angular parameters to take advantage of the potential of quantum computing, allowing the quantum layer to function within a six-angle depth framework. This unique integration allows the model to efficiently execute binary classification and multi-class tumor detection. The hybrid model outperforms conventional models, providing quicker processing speeds and higher classification accuracy, especially when dealing with high-dimensional and noisy data. The model optimizes 512-dimensional data using four qubits, allowing for improved feature representation and better insights into complicated medical imaging patterns. The quantum layer's resistance to noise enhances the model's accuracy, establishing a new standard for medical diagnostic tools. This novel integration of classical and quantum approaches offers a significant advance in MRI-based tumor identification, providing higher performance and opening the path for next-generation medical imaging systems.
Quantum machines enhance the capabilities of classical counterparts across various domains, notably in addressing real-world challenges.The classification of brain MR images for tumor detection is a crucial diagnostic process in the analysis of brain images.Traditional approaches, such as classical machine learning techniques and conventional deep learning structures like convolutional neural networks, are frequently employed for image classification.However, as the network size increases, training these models becomes increasingly arduous.Quantum algorithms offer advantages by optimizing the performance of classical algorithms through the incorporation of the intrinsic properties of quantum bits.In this paper, we proposed a hybrid classical and quantum convolutional neural network for Alzheimer's disease (AD) classification.The proposed model was further validated on the brain tumor classification task.The fundamental concept involves encoding data into quantum states, facilitating quicker information extraction, and subsequently utilizing this information to discern the data class.The proposed model results underscore the reliability and robustness and demonstrated by optimal performance accuracies across various datasets, the proposed model substantiates its efficacy in detecting and classifying AD disease and brain tumors.
Brain tumor detection from MRI images is a critical and challenging task in medical diagnostics, where early identification greatly improves treatment outcomes. This paper presents a Hybrid Quantum– Classical Convolutional Neural Network (HQCNN) that integrates the strengths of ResNet-18 and a Variational Quantum Circuit for efficient and accurate tumor classification. The proposed model first employs ResNet-18 as a classical feature extractor, where 17 convolutional layers and pooling operations capture both low-level and high-level spatial features from MRI images. The final fully connected layer of ResNet-18 is replaced by a quantum processing layer implemented using PennyLane. In this layer, the extracted classical features are encoded onto qubits using RY rotation gates, while CNOT gates introduce entanglement between them, forming a VQC with trainable parameters. After quantum computation, Pauli-Z measurements convert the processed quantum states back into classical values, which are passed to a final fully connected layer for binary classification as Tumor or No Tumor. The hybrid integration of classical CNN feature learning with quantum entanglement– based representation enhances model generalization and interpretability. Experimental analysis demonstrates that the proposed HQCNN achieved 94.65% accuracy, outperforming traditional CNN models and confirming the potential of hybrid quantum–classical architectures for reliable and interpretable medical image diagnosis.