Keywords:
Artificial Intelligence, Neuroradiology brain, MR, Contrast agent-other, Cancer
Authors:
S. Bhardwaj1, C. Chong1, M. Agzarian1, S. Pati2, U. Baid2, S. Bakas2, M.-S. To1; 1Bedford Park, SA/AU, 2Pennsylvania, Philadelphia/US
DOI:
10.26044/ranzcr2021/R-0362
Purpose
Deep learning (DL) models show promise in a wide variety of medical imaging tasks [1]. Training DL models, however, often requires significant amounts of data. To improve generalizability and overcome biases of individual institutions, extensive and diverse multi-institutional training datasets are desired [1]. The Federated Tumor Segmentation (FeTS, https://www.fets.ai) initiative, spearheaded by the University of Pennsylvania, describes the largest international federation of healthcare sites and a user-friendly software tool that enables training DL models for brain tumor segmentation. FeTS focuses on leveraging information gathered from datasets residing in collaborating sites throughout the world without needing to exchange data [2] Here, we demonstrate our local experience with using this tool and participating in the collaborative initiative.
Keywords:
Glioblastomas, segmentation, multi-institutional collaboration, paradigm shift, federated learning, FeTS, Enhancing part of the tumor, Edematous tissue around the tumor, Necrotic Core of the tumor.