Brain Tumor Detection And Segmentation Analysis With Machine Learning And Sub-Variant Techniques: A Perspective Study

Researchers in the fields of image separation, interpretation, and computer vision are always at work on automating tasks such as tumor segmentation, anomaly detection, classification, and the prediction of other structural disorders with the assistance of a computer. Brain tumors (BT) and other structural brain abnormalities are diagnosed, and their prognoses are determined with the help of several medical imaging modalities. This study aims to encapsulate the accomplishments and advancements in medical image segmentation and classification with reverence to unsupervised, supervised, and hybrid Machine learning and its derivative techniques for detecting abnormalities in the brain. The distinct objective of the research work is to implement descriptive analysis and identify the efficient ML technique. The study is comprehended with DWAE and SVM as efficient hybrid ML techniques foreseeing to enfold prominent features of accurately and precisely classifying brain tumor disorders.