Hyb_MDM-QCNN: Construction of Hybrid Multiscale Dilated MobileNet and Quantum-Inspired Convolutional Neural Network Architecture for Brain Tumor Classification Form MRI Images

Abstract

Brain tumors’ heterogeneous histology and unpredictable clinical course make them a major healthcare concern. They range from slow-growing benign tumors to aggressive malignancies in sensitive anatomical regions. The pathophysiology of these conditions must be well defined for customized therapy. AI methods for brain tumor segmentation and detection are commonly utilized for segmentation and detection, but the lack of generalizable results precludes medical practitioners from adopting them for diagnosis. Magnetic Resonance Imaging dominates research, although Positron Emission Tomography and Computed Tomography lack open-access datasets.This research introduces a unique hybrid architecture that combines Multiscale Dilated MobileNet with a Quantum-inspired Convolutional Neural Network (Hyb_MDMQCNN) to improve spatial and contextual feature extraction while maintaining model efficiency. Many experiments on Br35H and kaggle brain tumor MRI datasets.