Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces
Classical deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2021
|
| Online Access: | https://hdl.handle.net/1721.1/129526 |
| _version_ | 1826196786049449984 |
|---|---|
| author | Dalca, Adrian Vasile Balakrishnan, Guha Guttag, John V |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Dalca, Adrian Vasile Balakrishnan, Guha Guttag, John V |
| author_sort | Dalca, Adrian Vasile |
| collection | MIT |
| description | Classical deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. However, these approaches use restricted deformation models, require supervised labels, or do not guarantee a diffeomorphic (topology-preserving) registration. Furthermore, learning-based registration tools have not been derived from a probabilistic framework that can offer uncertainty estimates. In this paper, we build a connection between classical and learning-based methods. We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs). We demonstrate our method on a 3D brain registration task for both images and anatomical surfaces, and provide extensive empirical analyses of the algorithm. Our principled approach results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees. Our implementation is available online at http://voxelmorph.csail.mit.edu. |
| first_indexed | 2024-09-23T10:37:59Z |
| format | Article |
| id | mit-1721.1/129526 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:37:59Z |
| publishDate | 2021 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1295262022-09-27T13:51:26Z Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces Dalca, Adrian Vasile Balakrishnan, Guha Guttag, John V Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Classical deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. However, these approaches use restricted deformation models, require supervised labels, or do not guarantee a diffeomorphic (topology-preserving) registration. Furthermore, learning-based registration tools have not been derived from a probabilistic framework that can offer uncertainty estimates. In this paper, we build a connection between classical and learning-based methods. We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs). We demonstrate our method on a 3D brain registration task for both images and anatomical surfaces, and provide extensive empirical analyses of the algorithm. Our principled approach results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees. Our implementation is available online at http://voxelmorph.csail.mit.edu. National Institutes of Health (U.S.) (Grants R01LM012719, R01AG053949 and 1R21AG050122) National Science Foundation (U.S.). Career (Grant 1748377) National Science Foundation (U.S.). NeuroNex Grant (1707312) 2021-01-22T15:28:31Z 2021-01-22T15:28:31Z 2019-10 2020-12-16T18:02:07Z Article http://purl.org/eprint/type/JournalArticle 1361-8415 https://hdl.handle.net/1721.1/129526 Dalca, Adrian V. et al. “Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces.” Medical Image Analysis, 57 (October 2019): 226-236 © 2019 The Author(s) en 10.1016/J.MEDIA.2019.07.006 Medical Image Analysis Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV arXiv |
| spellingShingle | Dalca, Adrian Vasile Balakrishnan, Guha Guttag, John V Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces |
| title | Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces |
| title_full | Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces |
| title_fullStr | Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces |
| title_full_unstemmed | Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces |
| title_short | Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces |
| title_sort | unsupervised learning of probabilistic diffeomorphic registration for images and surfaces |
| url | https://hdl.handle.net/1721.1/129526 |
| work_keys_str_mv | AT dalcaadrianvasile unsupervisedlearningofprobabilisticdiffeomorphicregistrationforimagesandsurfaces AT balakrishnanguha unsupervisedlearningofprobabilisticdiffeomorphicregistrationforimagesandsurfaces AT guttagjohnv unsupervisedlearningofprobabilisticdiffeomorphicregistrationforimagesandsurfaces |