A hybrid M-DbneAlexnet for brain tumour detection using MRI images.

Abstract

Introduction: Brain Tumour (BT) is characterised by the uncontrolled proliferation of the cells within the brain which can result in cancer. Detecting BT at the early stage significantly increases the patient's survival chances. The existing BT detection methods often struggle with high computational complexity, limited feature discrimination, and poor generalisation.

Methods: To mitigate these issues, an effective brain tumour detection and segmentation method based on A hybrid network named MobileNet- Deep Batch-Normalized eLU AlexNet (M-DbneAlexnet) is developed based on Magnetic Resonance Imaging (MRI). The image enhancement is done by Piecewise Linear Transformation (PLT) function. BT region is segmented Transformer Brain Tumour Segmentation (TransBTSV2). Then feature extraction is done. Finally, BT is detected using M-DbneAlexnet model, which is devised by combining MobileNet and Deep Batch-Normalized eLU AlexNet (DbneAlexnet).Results: The proposed model achieved an accuracy of 92.68%, sensitivity of 93.02%, and specificity of 92.85%, demonstrating its effectiveness in accurately detecting brain tumors from MRI images.

Discussion: The proposed model enhances training speed and performs well on limited datasets, making it effective for distinguishing between tumor and healthy tissues. Its practical utility lies in enabling early detection and diagnosis of brain tumors, which can significantly reduce mortality rates.