Other Open Access
Spyridon Bakas; Bjoern Menze; Christos Davatzikos; Jayashree Kalpathy-Cramer; Keyvan Farahani; Michel Bilello; Suyash Mohan; John B. Freymann; Justin S. Kirby; Manmeet Ahluwalia; Volodymyr Statsevych; Raymond Huang; Hassan Fathallah-Shaykh; Roland Wiest; Andras Jakab; Rivka R. Colen; Aikaterini Kotrotsou; Daniel Marcus; Mikhail Milchenko; Arash Nazeri; Marc-Andre Weber; Abhishek Mahajan; Ujjwal Baid
This is the challenge design document for the "MICCAI Brain Tumor Segmentation (BraTS) 2020 Benchmark: 'Prediction of Survival and Pseudoprogression' ", accepted for MICCAI 2020.
BraTS 2020 utilizes multi-institutional MRI scans and focuses on the segmentation of intrinsically heterogeneous (in appearance, shape, and histology) brain tumors, namely gliomas. Compared to BraTS'17-'19, this year BraTS includes both pre-operative and post-operative scans (i.e., including surgically imposed cavities) and attempts to quantify the uncertainty of the predicted segmentations. Furthermore, to pinpoint the clinical relevance of the segmentation task, BraTS’20 also focuses on 1) the prediction of patient overall survival from pre-operative scans (Task 2) and 2) the distinction between true tumor recurrence and treatment related effects on the post-operative scans (Task 3), via integrative analyses of quantitative imaging phenomic features and machine learning algorithms. Ground truth annotations are created and approved by expert neuroradiologists for every subject included in the training, validation, and testing datasets to quantitatively evaluate the predicted tumor segmentations (Task 1). Furthermore, the quantitative evaluation of the clinically-relevant tasks (i.e., overall survival (Task 2) and distinction between tumor recurrence and treatment related effects (Task 3)), is performed according to real clinical data. Participants are free to choose whether they want to focus only on one or multiple tasks.