TopoFit: Rapid Reconstruction of Topologically-Correct Cortical Surfaces

Andrew Hoopes, Juan Eugenio Iglesias, Bruce Fischl, Douglas Greve, Adrian V Dalca
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:508-520, 2022.

Abstract

Mesh-based reconstruction of the cerebral cortex is a fundamental component in brain image analysis. Classical, iterative pipelines for cortical modeling are robust but often time-consuming, mostly due to expensive procedures that involve topology correction and spherical mapping. Recent attempts to address reconstruction with machine learning methods have accelerated some components in these pipelines, but these methods still require slow processing steps to enforce topological constraints that comply with known anatomical structure. In this work, we introduce a novel learning-based strategy, TopoFit, which rapidly fits a topologically-correct surface to the white-matter tissue boundary. We design a joint network, with image and graph convolutions, and an efficient symmetric distance loss to learn to predict accurate deformations that map a template mesh to subject-specific anatomy. This technique encompasses the work of current mesh correction, fine-tuning, and inflation processes and, as a result, offers a 150x faster solution to cortical surface reconstruction compared to traditional approaches. We demonstrate that TopoFit is 1.8x more accurate than the current state-of-the-art deep-learning strategy, and it is robust to common failure modes, such as white-matter tissue hypointensities.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-hoopes22a, title = {TopoFit: Rapid Reconstruction of Topologically-Correct Cortical Surfaces}, author = {Hoopes, Andrew and Iglesias, Juan Eugenio and Fischl, Bruce and Greve, Douglas and Dalca, Adrian V}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {508--520}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/hoopes22a/hoopes22a.pdf}, url = {https://proceedings.mlr.press/v172/hoopes22a.html}, abstract = {Mesh-based reconstruction of the cerebral cortex is a fundamental component in brain image analysis. Classical, iterative pipelines for cortical modeling are robust but often time-consuming, mostly due to expensive procedures that involve topology correction and spherical mapping. Recent attempts to address reconstruction with machine learning methods have accelerated some components in these pipelines, but these methods still require slow processing steps to enforce topological constraints that comply with known anatomical structure. In this work, we introduce a novel learning-based strategy, TopoFit, which rapidly fits a topologically-correct surface to the white-matter tissue boundary. We design a joint network, with image and graph convolutions, and an efficient symmetric distance loss to learn to predict accurate deformations that map a template mesh to subject-specific anatomy. This technique encompasses the work of current mesh correction, fine-tuning, and inflation processes and, as a result, offers a 150x faster solution to cortical surface reconstruction compared to traditional approaches. We demonstrate that TopoFit is 1.8x more accurate than the current state-of-the-art deep-learning strategy, and it is robust to common failure modes, such as white-matter tissue hypointensities.} }
Endnote
%0 Conference Paper %T TopoFit: Rapid Reconstruction of Topologically-Correct Cortical Surfaces %A Andrew Hoopes %A Juan Eugenio Iglesias %A Bruce Fischl %A Douglas Greve %A Adrian V Dalca %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-hoopes22a %I PMLR %P 508--520 %U https://proceedings.mlr.press/v172/hoopes22a.html %V 172 %X Mesh-based reconstruction of the cerebral cortex is a fundamental component in brain image analysis. Classical, iterative pipelines for cortical modeling are robust but often time-consuming, mostly due to expensive procedures that involve topology correction and spherical mapping. Recent attempts to address reconstruction with machine learning methods have accelerated some components in these pipelines, but these methods still require slow processing steps to enforce topological constraints that comply with known anatomical structure. In this work, we introduce a novel learning-based strategy, TopoFit, which rapidly fits a topologically-correct surface to the white-matter tissue boundary. We design a joint network, with image and graph convolutions, and an efficient symmetric distance loss to learn to predict accurate deformations that map a template mesh to subject-specific anatomy. This technique encompasses the work of current mesh correction, fine-tuning, and inflation processes and, as a result, offers a 150x faster solution to cortical surface reconstruction compared to traditional approaches. We demonstrate that TopoFit is 1.8x more accurate than the current state-of-the-art deep-learning strategy, and it is robust to common failure modes, such as white-matter tissue hypointensities.
APA
Hoopes, A., Iglesias, J.E., Fischl, B., Greve, D. & Dalca, A.V.. (2022). TopoFit: Rapid Reconstruction of Topologically-Correct Cortical Surfaces. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:508-520 Available from https://proceedings.mlr.press/v172/hoopes22a.html.

Related Material