Peer-Reviewed Publication
Med Image Anal2023;90102962.December 1, 2023Journal Article
A robust and interpretable deep learning framework for multi-modal registration via keypoints.
Alan Q Wang1, Evan M Yu2, Adrian V Dalca3, Mert R Sabuncu4
1School of Electrical and Computer Engineering, Cornell University and Cornell Tech, New York, NY 10044, USA; Department of Radiology, Weill Cornell Medical School, New York, NY 10065, USA. Electronic address: aw847@cornell.edu.
2Iterative Scopes, Cambridge, MA 02139, USA.
3Computer Science and Artificial Intelligence Lab at the Massachusetts Institute of Technology, Cambridge, MA 02139, USA; A.A. Martinos Center for Biomedical Imaging at the Massachusetts General Hospital, Charlestown, MA 02129, USA.
4School of Electrical and Computer Engineering, Cornell University and Cornell Tech, New York, NY 10044, USA; Department of Radiology, Weill Cornell Medical School, New York, NY 10065, USA.
Abstract
We present KeyMorph, a deep learning-based image registration framework that relies on automatically detecting corresponding keypoints. State-of-the-art deep learning methods for registration often are not robust to large misalignments, are not interpretable, and do not incorporate the symmetries of the problem. In addition, most models produce only a single prediction at test-time. Our core insig…
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