Cancelled: Federated Learning in Medical Imaging: Framework, Use Case, and Research

May 02, 2022 1:00 p.m. - 2:00 p.m. ET

This event has been cancelled. We apologize for the inconvenience. If you’d like to learn more about similar work done in the imaging and informatics community, check out the recent recording of University of Chicago’s Dr. Maryellen Giger discussion on data science in medical imaging of breast cancer and COVID-19.

Federated Learning (FL) has emerged as a potential solution due to its capability in training models without sharing data. To enable effective FL in real applications, a robust communication framework is crucial.

Join Drs. Jayashree Kalpathy-Cramer and Ziyue Xu during the May NCI Imaging and Informatics Community Webinar as they cover the open-source NVIDIA Federated Learning Application Runtime (FLAIR) environment infrastructure for orchestrating an FL study. Also discussed will be Project MONAI, a medical imaging use case, recent research towards better performing FL pipelines, and the introduction of a current Medical Image Computing and Computer Assisted Intervention challenge on breast density FL.   

The accuracy and robustness of AI algorithms rely heavily on the quantity, quality, and diversity of the training data set. For medical imaging applications, the challenge of constructing such a data set is particularly significant, mainly due to the privacy concerns in data sharing across multiple institutions.

This event is free and open to the public.

Jayashree Kalpathy-Cramer, Ph.D., M.G.H

Dr. Kalpathy-Cramer is an associate professor of radiology at Harvard Medical School, co-director of the QTIM Laboratory and the Center for Machine Learning at the Athinoula A. Martinos Center, and scientific director at the MGH & BWH Center for Clinical Data Science. Her research areas include machine learning (ML), informatics, image analysis, and statistical methods. In addition to developing novel ML algorithms, her lab is also actively engaged in the applications of these to clinical problems in radiology, oncology, and ophthalmology.

Ziyue Xu, Ph.D.

Dr. Xu is a senior scientist at Nvidia Corporation. His research interests lie in image analysis and ML with applications in biomedical and clinical imaging. Before joining Nvidia, Dr. Xu was an NIH staff scientist. He is an associate editor for the IEEE Transactions on Medical Imaging, Journal of Biomedical and Health Informatics, Computerized Medical Imaging and Graphics, and Computers in Biology and Medicine. He also serves as a program chair and committee member for multiple conferences (e.g., MICCAI, AAAI, etc.).


Vote below about this page’s helpfulness.