Brain Tumor Classification Based on Hybrid Optimized Multi-features Analysis Using Magnetic Resonance Imaging Dataset

Brain tumors are deadly but become deadliest because of delayed and inefficient diagnosis process. Large variations in tumor types also instigate additional complexity. Machine vision brain addresses the problem. This research’s objective was to develop a classification model based on machine techniques using Magnetic Resonance Imaging (MRI). For this purpose, novel hybrid-brain-tumor-classification (HBTC) framework designed evaluated for cystic (cyst), glioma, meningioma (menin), metastatic (meta) tumors. The proposed lessens inherent complexities boosts performance MRI dataset input HBTC framework, pre-processed, segmented localize region. From Co-occurrence matrix (COM), run-length (RLM), gradient features were extracted. After application hybrid multi-features, nine most optimized selected framework’s classifiers, namely multilayer perception (MLP), J48, meta bagging (MB), random tree (RT) classify cyst, menin, Maximum achieved by 98.8%. components show that it is robust framework.