DRMIME: Differentiable Mutual Information and Matrix Exponential for Multi-Resolution Image Registration

Abhishek Nan, Matthew Tennant, Uriel Rubin, Nilanjan Ray
Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:527-543, 2020.

Abstract

We present a novel unsupervised image registration algorithm using mutual information (MI). It is differentiable end-to-end and can be used for both multi-modal and mono-modal registration. The novelty here is that rather than using traditional ways of approximating MI which are often histogram based, we use a neural estimator called MINE and supplement it with matrix exponential for transformation matrix computation. The introduction of MINE tackles some of the drawbacks of histogram based MI computation and matrix exponential makes the optimization process smoother. Our use of multi-resolution objective function expedites the optimization process and leads to improved results as compared to the standard algorithms available out-of-the-box in state-of-the-art image registration toolboxes empirically demonstrated on publicly available datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v121-nan20a, title = {DRMIME: Differentiable Mutual Information and Matrix Exponential for Multi-Resolution Image Registration}, author = {Nan, Abhishek and Tennant, Matthew and Rubin, Uriel and Ray, Nilanjan}, booktitle = {Proceedings of the Third Conference on Medical Imaging with Deep Learning}, pages = {527--543}, year = {2020}, editor = {Arbel, Tal and Ben Ayed, Ismail and de Bruijne, Marleen and Descoteaux, Maxime and Lombaert, Herve and Pal, Christopher}, volume = {121}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/nan20a/nan20a.pdf}, url = {https://proceedings.mlr.press/v121/nan20a.html}, abstract = {We present a novel unsupervised image registration algorithm using mutual information (MI). It is differentiable end-to-end and can be used for both multi-modal and mono-modal registration. The novelty here is that rather than using traditional ways of approximating MI which are often histogram based, we use a neural estimator called MINE and supplement it with matrix exponential for transformation matrix computation. The introduction of MINE tackles some of the drawbacks of histogram based MI computation and matrix exponential makes the optimization process smoother. Our use of multi-resolution objective function expedites the optimization process and leads to improved results as compared to the standard algorithms available out-of-the-box in state-of-the-art image registration toolboxes empirically demonstrated on publicly available datasets.} }
Endnote
%0 Conference Paper %T DRMIME: Differentiable Mutual Information and Matrix Exponential for Multi-Resolution Image Registration %A Abhishek Nan %A Matthew Tennant %A Uriel Rubin %A Nilanjan Ray %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-nan20a %I PMLR %P 527--543 %U https://proceedings.mlr.press/v121/nan20a.html %V 121 %X We present a novel unsupervised image registration algorithm using mutual information (MI). It is differentiable end-to-end and can be used for both multi-modal and mono-modal registration. The novelty here is that rather than using traditional ways of approximating MI which are often histogram based, we use a neural estimator called MINE and supplement it with matrix exponential for transformation matrix computation. The introduction of MINE tackles some of the drawbacks of histogram based MI computation and matrix exponential makes the optimization process smoother. Our use of multi-resolution objective function expedites the optimization process and leads to improved results as compared to the standard algorithms available out-of-the-box in state-of-the-art image registration toolboxes empirically demonstrated on publicly available datasets.
APA
Nan, A., Tennant, M., Rubin, U. & Ray, N.. (2020). DRMIME: Differentiable Mutual Information and Matrix Exponential for Multi-Resolution Image Registration. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 121:527-543 Available from https://proceedings.mlr.press/v121/nan20a.html.

Related Material