Contrastive Multimodal Image Representation for Registration (CoMIR)
Contrastive Multimodal Image Representation for Registration (CoMIR) is a deep learning framework designed to align images from different modalities by transforming them into a shared representational space. The framework archives this using contrastive learning that maximizes the similarity between image representations of aligned multimodal image pairs.[1] These image representations can be used with any typical intensity-based image registration method.
References
- ↑ Lu, Jiahao; Pielawski, Nicki; Wetzer, Emil; Öfverstedt, Johan; Wählby, Carolina; Lindblad, Joakim; Sladoje, Natasa (2022). "Is image-to-image translation the panacea for multimodal image registration? A comparative study". PLOS ONE. 17 (11): e0276196. arXiv:2103.16262. Bibcode:2022PLoSO..1776196L. doi:10.1371/journal.pone.0276196. PMID 36441754 Check
|pmid=value (help).
This article "Contrastive Multimodal Image Representation for Registration (CoMIR)" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Contrastive Multimodal Image Representation for Registration (CoMIR). Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
