Mutual information for unsupervised deep learning image registration

Bob D. de Vos, Bas H.M. van der Velden, Jörg Sander, Kenneth G.A. Gilhuijs, Marius Staring, Ivana Išgum

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

12 Citations (Scopus)


Current unsupervised deep learning-based image registration methods are trained with mean squares or normalized cross correlation as a similarity metric. These metrics are suitable for registration of images where a linear relation between image intensities exists. When such a relation is absent knowledge from conventional image registration literature suggests the use of mutual information. In this work we investigate whether mutual information can be used as a loss for unsupervised deep learning image registration by evaluating it on two datasets: breast dynamic contrast-enhanced MR and cardiac MR images. The results show that training with mutual information as a loss gives on par performance compared with conventional image registration in contrast enhanced images, and the results show that it is generally applicable since it has on par performance compared with normalized cross correlation in single-modality registration.
Original languageEnglish
Title of host publicationMedical Imaging 2020
Subtitle of host publicationImage Processing
EditorsIvana Isgum, Bennett A. Landman
ISBN (Electronic)9781510633933
Publication statusPublished - 10 Mar 2020
Externally publishedYes
EventMedical Imaging 2020: Image Processing - Houston, United States
Duration: 17 Feb 202020 Feb 2020

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ISSN (Print)1605-7422


ConferenceMedical Imaging 2020: Image Processing
Country/TerritoryUnited States


  • Image registration
  • Mutual information
  • Unsupervised machine learning


Dive into the research topics of 'Mutual information for unsupervised deep learning image registration'. Together they form a unique fingerprint.

Cite this