Federated learning improves site performance in multicenter deep learning without data sharing

Karthik V. Sarma, Stephanie A. Harmon, Thomas Sanford, Holger R. Roth, Ziyue Xu, Jesse Tetreault, Daguang Xu, Mona G. Flores, Alex G. Raman, Rushikesh Kulkarni, Bradford J. Wood, Peter L. Choyke, Alan Priester, Leonard S. Marks, Steven S. Raman, Dieter Enzmann, Baris Turkbey, William Speier, Corey W. Arnold

Abstract

To demonstrate enabling multi-institutional training without centralizing or sharing the underlying physical data via federated learning (FL).
BibTeX
@article{sarma2021federated,
  author = {Karthik V. Sarma and Stephanie A. Harmon and Thomas Sanford and Holger R. Roth and Ziyue Xu and Jesse Tetreault and Daguang Xu and Mona G. Flores and Alex G. Raman and Rushikesh Kulkarni and Bradford J. Wood and Peter L. Choyke and Alan Priester and Leonard S. Marks and Steven S. Raman and Dieter Enzmann and Baris Turkbey and William Speier and Corey W. Arnold},
  title = {{Federated learning improves site performance in multicenter deep learning without data sharing}},
  journal = {J. Am. Medical Informatics Assoc.},
  year = {2021},
  doi = {10.1093/jamia/ocaa341},
}

Loading related content...

Figure