Advancing neuroimaging with quantum convolutional neural networks for brain tumor detection

作     者：Ticku, Amrita Sangwan, Vaibhav Balani, Sanket Jha, Sriti Rawat, Sahil Rathee, Anu Yadav, Deepika 

作者机构：Department of Computer Science and Engineering Bharati Vidyapeeth’s College of Engineering New Delhi India Department of Information Technology Maharaja Agrasen Institute of Technology New Delhi India 

出 版 物：《International Journal of Information Technology (Singapore)》 (Int. J. Inf. Technol.)

年 卷 期：2025年

页      面：1-8页

主　　题：Brain tumor classification Feature extraction Healthcare Image processing Machine learning Neuroimaging Quantum Convolutional Neural Networks (QCNNs) 

摘      要：Brain tumor classification is crucial for effective patient care, but traditional MRI-based methods often face accuracy limitations, especially in distinguishing between tumor types. This study introduces a novel Quantum Convolutional Neural Network (QCNN) architecture that leverages quantum embedding, sparse input indexing, and four-qubit quantum convolution layers to enhance classification accuracy and efficiency. Developed using PennyLane and TensorFlow Quantum, our QCNN achieved a testing accuracy of 92.13% on a dataset of over 3000 MRI scans, matching the performance of the classical ResNet50 model while reducing training time from 64.95 s to just 1.1 s. These results suggest that QCNNs offer a promising new approach for improving brain tumor diagnostics, with the potential for faster and more accurate real-time medical applications, despite challenges in hardware limitations and model interpretability. © Bharati Vidyapeeth s Institute of Computer Applications and Management 2025.