Efficient Brain Tumor Segmentation and Classification Using a Hybrid Qcq-Cnn Model with Quantum Neural Networks

Abstract

Accurate detection and segmentation of brain tumors from magnetic resonance imaging (MRI) remain critical challenges in intelligent medical diagnosis due to the complexity of tumor structures and variability in imaging conditions. This study presents a novel hybrid quantum-classical deep learning framework, termed QCQ-CNN, for enhanced brain tumor segmentation and classification. The proposed approach integrates Gray Level Co-occurrence Matrix (GLCM)-based texture feature extraction with a convolutional neural network (CNN) to capture spatial and textural representations, followed by a U-Net architecture for precise tumor segmentation. To further improve classification performance, a Quantum Neural Network (QNN) is employed as a decision-making module, leveraging parameterized quantum circuits to model complex nonlinear feature relationships. The framework is evaluated on the BRISC 2025 MRI dataset, which includes multi-class tumor categories and expert-annotated segmentation masks. Performance is assessed using standard metrics such as accuracy, precision, recall, F1-score, and Intersection-over-Union (IoU). Experimental results demonstrate that the proposed model achieves superior segmentation accuracy and classification robustness compared to conventional deep learning methods. The integration of quantum computing enhances the model’s generalization capability, particularly in limited and noisy data scenarios. Overall, the proposed hybrid framework provides an efficient and scalable solution for next-generation medical image analysis and intelligent diagnostic systems.