Mutual information for unsupervised deep learning image registration
SPIE Medical Imaging: Image Processing, pp. 26
Abstract
Current unsupervised deep learning-based image registration methods are trained with mean squares or nor- malized 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.
Authors 6
-
University Medical Center Utrecht · Amsterdam University Medical Centers
Affiliation as printed
Amsterdam Univ. Medical Ctr. (Netherlands)
Univ. Medical Ctr. Utrecht (Netherlands)
-
University Medical Center Utrecht
Affiliation as printed
Univ. Medical Ctr. Utrecht (Netherlands)
-
University Medical Center Utrecht · Amsterdam University Medical Centers
Affiliation as printed
Amsterdam Univ. Medical Ctr. (Netherlands)
Univ. Medical Ctr. Utrecht (Netherlands)
-
University Medical Center Utrecht
Affiliation as printed
Image Sciences Institute, Univ. Medical Ctr. Utrecht (Netherlands)
-
Leiden University Medical Center
Affiliation as printed
Leiden Univ. Medical Ctr. (Netherlands)
-
University Medical Center Utrecht · Amsterdam University Medical Centers
Affiliation as printed
Amsterdam Univ. Medical Ctr. (Netherlands)
Amsterdan Univ. Medical Ctr. (Netherlands)
Image Sciences Institute, Univ. Medical Ctr. Utrecht (Netherlands)
Cited by 35 stored of 35
Cited by patents worldwide 1 (Lens.org)
-
Unsupervised multitask ensemble for spatial transfer of multi-structures via partial point cloud matchingUS12373963B2 2025-07-29 Active