Because it can reveal the internal architecture of previously invisible human body regions, medical image processing has attracted a lot of attention for use in medical diagnostics. Lung and brain illness has emerged as one of the major medical concerns of our day. At the early period of pregnancy, the difficult challenge is determining the fetal lung's maturity level. During pregnancy, tracking the fetus's growth inside the mother's womb is an essential responsibility. Using image registration and classification techniques, this study effort presents an effective and automated computer-aided methodology for brain tumor detection and segmentation. The following components make up this suggested work: segmentation, classification, contourlet transform, and feature extraction with feature normalization. Adaptive Neuro Fuzzy Inference System (ANFIS) classification approach is utilized to categorize the features for brain Magnetic Resonance Imaging (MRI) tumor segmentation and detection after the retrieved features are optimized using Genetic Algorithm (GA). The suggested methodology for brain tumor detection is assessed quantitatively utilizing the Dice similarity coefficient, segmentation accuracy, precision, sensitivity, and specificity. Additionally, this research effort suggests a productive method for creating a framework for the detection of brain tumors utilizing a fusion-based categorization methodology. The internal low resolution border pixels are improved by fusing the brain MRI images from the public dataset. In order to acquire the non-linear coefficient metric patterns, the merged brain picture is now subjected to the Curvelet transform. In order to distinguish brain images impacted by tumors from brain images unaffected by tumors, features are then generated from these altered non-linear coefficient metric patterns and subsequently classified using the suggested Extreme Learning Adaboost Classification (ELAC) algorithm. The morphological segmentation approach is also used in this work to segment the tumor regions in brain MRI images that have been classified as tumors.