Peer-Reviewed Publication
Int Conf Learn Represent2025;2025100815-100851.April 1, 2025Journal Article
Time-to-Event Pretraining for 3D Medical Imaging.
Zepeng Huo1, Jason Alan Fries1, Alejandro Lozano2, Jeya Maria Jose Valanarasu3,4, Ethan Steinberg1,5, Louis Blankemeier2, Akshay S Chaudhari2,4,6,7, Curtis Langlotz8,4,9,7, Nigam H Shah8,4,10,9,6,11
1Center for Biomedical Informatics Research, Stanford University.
2Department of Biomedical Data Science, Stanford University.
3Department of Computer Science, Stanford University.
4Stanford Center for Artificial Intelligence in Medicine and Imaging.
5Prealize Health.
6Human-Centered Artificial Intelligence Institute, Stanford University.
7Department of Radiology, Stanford University.
8Stanford Medical Center, Stanford Health Care.
9Department of Medicine, Stanford School of Medicine.
10Technology and Digital Solutions, Stanford Health Care.
11Clinical Excellence Research Center, Stanford School of Medicine.
Abstract
With the rise of medical foundation models and the growing availability of imaging data, scalable pretraining techniques offer a promising way to identify imaging biomarkers predictive of future disease risk. While current self-supervised methods for 3D medical imaging models capture local structural features like organ morphology, they fail to link pixel biomarkers with long-term health outcomes…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans