In the recent past artificial intelligence applications in Magnetic Resonance Imaging (MRI) is applied in various clinical researches. However, for analyzing brain tumor without human intervention is considered as a significant area of research because the extracted brain images need to be optimized using segmentation algorithm which should have high resilient towards noise and cluster size sensitivity problem with automatic region of Interest (ROI) detection. In this research, an improved orthogonal gamma distribution based machine-learning approach is used to analyses the under segment and over segments of the brain tumor regions to detect the abnormality with automatic ROI detection. Further data imbalance due to improper edge matching in the abnormality region has been sampled by matching the edge coordinates and the sensitivity, selectivity parameters are measured using machine learning algorithm. The benchmark medical image database has been collected and experimentally analyze to validate the efficiency, accuracy, optimal automatic detection for tumor and non-tumor region and mean error rate of the algorithm using mathematical formulation. This research pays its proficiency in the field of brain abnormality detection and analysis in health care sector without human intermediation.