Deep Learning Approach for Brain Tumor Segmentation and Detection

Abstract

Deep Learning has emerged as a prominent area of focus within the field of machine learning, garnering significant attention from researchers in recent years. This powerful machine learning technique has found widespread application in addressing complex problems necessitating high levels of accuracy and sensitivity, particularly within the medical domain. Among various medical conditions, brain tumors represent a common and aggressive form of malignant disease, often associated with a short life expectancy when diagnosed at advanced stages. Accurate grading of brain tumors following detection is crucial for devising effective treatment strategies. This study employs Convolutional Neural Network (CNN), a widely utilized deep learning architecture, to classify a dataset comprising 3064 T1 weighted contrast-enhanced brain MR images into three tumor classes (Glioma, Meningioma, and Pituitary Tumor). The proposed CNN classifier demonstrates robust performance, achieving an accuracy of 97.52% and 97.39% sensitivity for segmented lesion images.