Spatiotemporal deep learning for scar screening in cardiovascular magnetic resonance: Toward selective use of gadolinium
Amine Amyar, Shiro Nakamori, Jiwon Kim, Martin S Maron, Ethan J Rowin, Karishma Pareek, Alexander Schulz, Robert M Judd, Warren J Manning, Raymond Y Kwong, Frederick L Ruberg, Jonathan W Weinsaft, Reza Nezafat · 2026
Read Spatiotemporal deep learning for scar screening in cardiovascular magnetic resonance: Toward selective use of gadolinium by Amine Amyar, Shiro Nakamori, Jiwon Kim, Martin S Maron, Ethan J Rowin, Karishma Pareek, Alexander Schulz, Robert M Judd, Warren J Manning, Raymond Y Kwong, Frederick L Ruberg, Jonathan W Weinsaft, Reza Nezafat (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13246303.txt.
Description
Amine Amyar and co-authors teach a network to screen for heart scars in a 2026 paper. The gold test for scar in heart muscle uses a contrast drug and magnetic scans. Yet many patients sent for that test turn out to have no scar at all. Those patients got the drug and the long scan for nothing. The team wanted a way to spot them first.
Their model reads plain moving scans, called cine images, with no drug at all. It was trained on scans from 3,000 patients at varied sites and scanner types. A second group of 1,792 patients from other sites tested it. The design pulls out shape and motion traits over time. It adds a focus step that stresses the traits most tied to scar.
Catalog record
| CREATOR | Amine Amyar, Shiro Nakamori, Jiwon Kim, Martin S Maron, Ethan J Rowin, Karishma Pareek, Alexander Schulz, Robert M Judd, Warren J Manning, Raymond Y Kwong, Frederick L Ruberg, Jonathan W Weinsaft, Reza Nezafat |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |