A NOVEL HYBRID QUANTUM DEEP LEARNING APPROACH FOR CLASSIFICATION OF MULTI-CLASS BRAIN TUMOUR

Abstract

Accurate and timely brain tumor classification from magnetic resonance imaging (MRI) scans is essential for effective diagnosis and treatment planning. Although conventional deep learning models have achieved promising results, they often face challenges in capturing complex spatial patterns and high-dimensional features present in medical images. To address these limitations, this study proposes an efficient hybrid quantum deep learning model for multi-class brain tumor classification. By integrating quantum computing principles with conventional deep learning architectures, the proposed framework enhances feature representation and classification performance while reducing computational complexity. The model employs convolutional neural networks (CNNs) for robust feature extraction, followed by quantum neural network (QNN)-based processing to improve classification of multiple brain tumor categories. A labelled MRI dataset is used to train and evaluate the proposed model using standard performance metrics, including accuracy, precision, recall, and F1-score. Experimental results demonstrate that the hybrid quantum deep learning approach outperforms conventional deep learning models in terms of classification accuracy, scalability, and computational efficiency. The findings highlight the potential of quantumenhanced deep learning as a promising solution for next-generation medical image analysis and intelligent clinical decision support systems. Unlike conventional approaches that rely solely on classical deep learning architectures, the proposed framework integrates quantum computing with deep learning to achieve higher classification accuracy while improving computational efficiency. The model was trained and evaluated on a labelled MRI dataset using standard performance metrics, including accuracy, precision, recall, and F1-score. Experimental results demonstrate that the proposed hybrid model consistently outperforms existing deep learning methods in accurately classifying multiple brain tumor types. These findings highlight the transformative potential of quantum-enhanced deep learning in advancing medical image analysis, enabling faster, more reliable, and intelligent diagnostic systems for future healthcare applications.