Deep Learning Based Brain Tumor Detection and Classification
Nadim Mahmud Dipu, Sifatul Alam Shohan, K. M. A. Salam
Abstract
One of the most crucial tasks of neurologists and radiologists is early brain tumor detection. However, manually detecting and segmenting brain tumors from Magnetic Resonance Imaging (MRI) scans is challenging, and prone to errors. That is why an automated brain tumor detection system is required for early diagnosis of the disease. This paper proposes two deep learning based approaches for brain tumor detection and classification using the cutting-edge object detection framework YOLO (You Only Look Once) and the deep learning library FastAi, respectively. This study was done on a subset of the BRATS 2018 dataset that contained 1,992 Brain MRI scans. The YOLOv5 model achieved an accuracy of 85.95% and the FastAi classification model achieved an accuracy of 95.78%. These two models can be applied in real-time brain tumor detection for early diagnosis of brain cancer.