Brain Tumor Detection via Deep Learning Framework on MRI Images

In medical imaging and diagnostics, identifying brain tumors is crucial. The objective of this study is the automated diagnosis of brain tumors using Magnetic Resonance Imaging (MRI) pictures, and the suggestion of a deep learning approach utilizing the YOLOv7 neural network model is presented. Initially a dataset had been collected which consists of 300 images. The image datasets are labelled in such a way that the area of tumor is correctly annotated. The dataset is then expanded in size as a result of the data augmentation approaches that are used. The model is trained on 80% of the photos, then tested on the remaining 20%. On a sizable dataset of brain MRI images, the suggested approach is assessed, and its performance is compared to that of earlier YOLO algorithm versions. The results demonstrate that the proposed approach of using YOLO7 achieves high accuracy in brain tumor detection, outperforming previous versions by a significant margin. The proposed model of YOLOv7 achieves a mAP score of 94%. These results prove that the YOLOv7 model is capable to detect the brain tumor along with its location which proves, that the model has potential in finding tumors using MRI.