Learning interpretable multi-modal features for alignment with supervised iterative descent

Max Blendowski, Mattias P. Heinrich
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:73-83, 2019.

Abstract

Methods for deep learning based medical image registration have only recently approached the quality of classical model-based image alignment. The dual challenge of both a very large trainable parameter space and often insufficient availability of expert supervised correspondence annotations has led to slower progress compared to other domains such as image segmentation. Yet, image registration could also more directly benefit from an iterative solution than segmentation. We therefore believe that significant improvements, in particular for multi-modal registration, can be achieved by disentangling appearance-based feature learning and deformation estimation. In contrast to most previous approaches, our model does not require full deformation fields as supervision but rather only small incremental descent targets generated from organ labels during training. By mapping the complex appearance to a common feature space in which update steps of a first-order Taylor approximation (akin to a regularised Demons iteration) match the supervised descent direction, we can train a CNN-model that learns interpretable modality invariant features. Our experimental results demonstrate that these features can be plugged into conventional iterative optimisers and are more robust than state-of-the-art hand-crafted features for aligning MRI and CT images.

Cite this Paper


BibTeX
@InProceedings{pmlr-v102-blendowski19a, title = {Learning interpretable multi-modal features for alignment with supervised iterative descent}, author = {Blendowski, Max and Heinrich, Mattias P.}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {73--83}, year = {2019}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, volume = {102}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v102/blendowski19a/blendowski19a.pdf}, url = {https://proceedings.mlr.press/v102/blendowski19a.html}, abstract = {Methods for deep learning based medical image registration have only recently approached the quality of classical model-based image alignment. The dual challenge of both a very large trainable parameter space and often insufficient availability of expert supervised correspondence annotations has led to slower progress compared to other domains such as image segmentation. Yet, image registration could also more directly benefit from an iterative solution than segmentation. We therefore believe that significant improvements, in particular for multi-modal registration, can be achieved by disentangling appearance-based feature learning and deformation estimation. In contrast to most previous approaches, our model does not require full deformation fields as supervision but rather only small incremental descent targets generated from organ labels during training. By mapping the complex appearance to a common feature space in which update steps of a first-order Taylor approximation (akin to a regularised Demons iteration) match the supervised descent direction, we can train a CNN-model that learns interpretable modality invariant features. Our experimental results demonstrate that these features can be plugged into conventional iterative optimisers and are more robust than state-of-the-art hand-crafted features for aligning MRI and CT images.} }
Endnote
%0 Conference Paper %T Learning interpretable multi-modal features for alignment with supervised iterative descent %A Max Blendowski %A Mattias P. Heinrich %B Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2019 %E M. Jorge Cardoso %E Aasa Feragen %E Ben Glocker %E Ender Konukoglu %E Ipek Oguz %E Gozde Unal %E Tom Vercauteren %F pmlr-v102-blendowski19a %I PMLR %P 73--83 %U https://proceedings.mlr.press/v102/blendowski19a.html %V 102 %X Methods for deep learning based medical image registration have only recently approached the quality of classical model-based image alignment. The dual challenge of both a very large trainable parameter space and often insufficient availability of expert supervised correspondence annotations has led to slower progress compared to other domains such as image segmentation. Yet, image registration could also more directly benefit from an iterative solution than segmentation. We therefore believe that significant improvements, in particular for multi-modal registration, can be achieved by disentangling appearance-based feature learning and deformation estimation. In contrast to most previous approaches, our model does not require full deformation fields as supervision but rather only small incremental descent targets generated from organ labels during training. By mapping the complex appearance to a common feature space in which update steps of a first-order Taylor approximation (akin to a regularised Demons iteration) match the supervised descent direction, we can train a CNN-model that learns interpretable modality invariant features. Our experimental results demonstrate that these features can be plugged into conventional iterative optimisers and are more robust than state-of-the-art hand-crafted features for aligning MRI and CT images.
APA
Blendowski, M. & Heinrich, M.P.. (2019). Learning interpretable multi-modal features for alignment with supervised iterative descent. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:73-83 Available from https://proceedings.mlr.press/v102/blendowski19a.html.

Related Material