Semantic similarity metrics for learned image registration

Steffen Czolbe, Oswin Krause, Aasa Feragen
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR 143:105-118, 2021.

Abstract

We propose a semantic similarity metric for image registration. Existing metrics like euclidean distance or normalized cross-correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our approach learns dataset-specific features that drive the optimization of a learning-based registration model. We train both an unsupervised approach using an auto-encoder, and a semi-supervised approach using supplemental segmentation data to extract semantic features for image registration. Comparing to existing methods across multiple image modalities and applications, we achieve consistently high registration accuracy. A learned invariance to noise gives smoother transformations on low-quality images.

Cite this Paper

BibTeX
@InProceedings{pmlr-v143-czolbe21a, title = {Semantic similarity metrics for learned image registration}, author = {Czolbe, Steffen and Krause, Oswin and Feragen, Aasa}, booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning}, pages = {105--118}, year = {2021}, editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris}, volume = {143}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v143/czolbe21a/czolbe21a.pdf}, url = {https://proceedings.mlr.press/v143/czolbe21a.html}, abstract = {We propose a semantic similarity metric for image registration. Existing metrics like euclidean distance or normalized cross-correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our approach learns dataset-specific features that drive the optimization of a learning-based registration model. We train both an unsupervised approach using an auto-encoder, and a semi-supervised approach using supplemental segmentation data to extract semantic features for image registration. Comparing to existing methods across multiple image modalities and applications, we achieve consistently high registration accuracy. A learned invariance to noise gives smoother transformations on low-quality images.} }
Endnote
%0 Conference Paper %T Semantic similarity metrics for learned image registration %A Steffen Czolbe %A Oswin Krause %A Aasa Feragen %B Proceedings of the Fourth Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2021 %E Mattias Heinrich %E Qi Dou %E Marleen de Bruijne %E Jan Lellmann %E Alexander Schläfer %E Floris Ernst %F pmlr-v143-czolbe21a %I PMLR %P 105--118 %U https://proceedings.mlr.press/v143/czolbe21a.html %V 143 %X We propose a semantic similarity metric for image registration. Existing metrics like euclidean distance or normalized cross-correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our approach learns dataset-specific features that drive the optimization of a learning-based registration model. We train both an unsupervised approach using an auto-encoder, and a semi-supervised approach using supplemental segmentation data to extract semantic features for image registration. Comparing to existing methods across multiple image modalities and applications, we achieve consistently high registration accuracy. A learned invariance to noise gives smoother transformations on low-quality images.
APA
Czolbe, S., Krause, O. & Feragen, A.. (2021). Semantic similarity metrics for learned image registration. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 143:105-118 Available from https://proceedings.mlr.press/v143/czolbe21a.html.

Related Material