GU-Net: Diffuse Glioma Segmentation in Brain MRIs Using a Modified U-Net under Data Constraints

Dataset: https://www.kaggle.com/datasets/dschettler8845/brats-2021-task1

Diffuse gliomas account for nearly 80% of all malignant brain tumors in adults and often require precise surgical treatment. Our model, caled GU-Net is trained to segemnt gliomas from T2-Flair brain MRIs scans from the BraTS 2021 dataset. It is trained on only 1647 images stemming from 549 different brain MRIs. Our work specifically advances diagnosis in underprivileged areas and hospitals with less funding, as GU-Net requires less data to be used and has higher efficiency compared to existing solutions.