AN OPTIMIZED INTELLIGENT SEVERITY ANALYSIS FRAMEWORK FOR BRAIN LESION PREDICTION
Brain lesion forecasting is the most trending study in the medical industry because of this disease severity rate. Several intelligent prediction models existed to offer the finest brain lesion prediction outcome. However, a suitable outcome is not attained because of its poor image quality. Usually, the Magnetic resonance image (MRI) is high in noise content, which maximizes the prediction complexity. These drawbacks resulted in low prediction exactness and severity calculation scores. So, the current work aimed to develop a novel Dove-based multilayer perceptron Severity analysis (DbMPSA) framework for improving the disease severity analysis rate. Initially, the MRI images were preprocessed, and the meaningful features were extracted; then, the disease region was tracked and segmented. Finally, the severity rate was measured based on the affection range. Subsequently, the presented model has attained a high exactness score in specifying the severity and segmentation.
Brain Lesion, Severity Classification, Multilayer Perceptron, Disease Region Segmentation, Feature Extraction.