Classifying and Localizing Abnormalities in Brain MRI using Channel Attention Based Semi-Bayesian Ensemble Voting Mechanism and Convolutional Auto-Encoder

Brain tumors represent a severe and often life-threatening condition in adults, as the rapid multiplication of cancerous cells within tumor can critically impair patient’s normal functioning. The clinical practice commonly utilizes imaging modalities such MRI, PET CT scans to assess brain tumor’s size, type, location. purpose this research is create computer aided diagnosis (CAD) system that segment categorize automatically. designed work specifically with T1W-CE Magnetic Resonance Images (MRI) brain. classification task involves determining type present image, while segmentation separating region from surrounding healthy tissue. By automating these tasks, proposed aims increase accuracy effectiveness treatment planning for patients. multi-class (BCT) considered one most daunting problems medical imaging. This article proposes model named VS-BEAM be used efficiently decision-making. (Voting Based Semi-Supervised Bayesian Ensemble Attention Mechanism) has been examined classification. achieved highest level possible. achieves maximum sensitivity, specificity, diagnostic compared existing models using MRI images. A convolutional autoencoder utilized extracting obtained testing data 264 was 98.91%, indicating method effective context assist detecting larger or even smaller tumors.