Eigenvector Grouping for Point Cloud Vessel Labeling

Patryk Rygiel, Maciej Zieba, Tomasz Konopczynski
Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, PMLR 194:72-84, 2022.

Abstract

Segmentation of coronary arteries from Coronary Computed Tomography Angiography (CCTA) is an essential step in developing various noninvasive diagnostic methods. In this work, we tackle the task of vessel labeling on coronary artery voxel-based prediction by use of point cloud artificial neural network. We propose a novel point aggregation technique Eigenvector Grouping (EVG), tailored to the analysis of tubular-like structures. We further utilize a specifically designed post-processing technique Component-Wise Majority Point Voting (CMPV), to refine point cloud segmentation by enforcing class consistency among connected components. We show that our solution outperforms previously proposed methods in the vessel labeling task on a CCTA dataset especially, in the presence of disrupted segmentations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v194-rygiel22a, title = {Eigenvector Grouping for Point Cloud Vessel Labeling}, author = {Rygiel, Patryk and Zieba, Maciej and Konopczynski, Tomasz}, booktitle = {Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis}, pages = {72--84}, year = {2022}, editor = {Bekkers, Erik and Wolterink, Jelmer M. and Aviles-Rivero, Angelica}, volume = {194}, series = {Proceedings of Machine Learning Research}, month = {18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v194/rygiel22a/rygiel22a.pdf}, url = {https://proceedings.mlr.press/v194/rygiel22a.html}, abstract = {Segmentation of coronary arteries from Coronary Computed Tomography Angiography (CCTA) is an essential step in developing various noninvasive diagnostic methods. In this work, we tackle the task of vessel labeling on coronary artery voxel-based prediction by use of point cloud artificial neural network. We propose a novel point aggregation technique Eigenvector Grouping (EVG), tailored to the analysis of tubular-like structures. We further utilize a specifically designed post-processing technique Component-Wise Majority Point Voting (CMPV), to refine point cloud segmentation by enforcing class consistency among connected components. We show that our solution outperforms previously proposed methods in the vessel labeling task on a CCTA dataset especially, in the presence of disrupted segmentations.} }
Endnote
%0 Conference Paper %T Eigenvector Grouping for Point Cloud Vessel Labeling %A Patryk Rygiel %A Maciej Zieba %A Tomasz Konopczynski %B Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis %C Proceedings of Machine Learning Research %D 2022 %E Erik Bekkers %E Jelmer M. Wolterink %E Angelica Aviles-Rivero %F pmlr-v194-rygiel22a %I PMLR %P 72--84 %U https://proceedings.mlr.press/v194/rygiel22a.html %V 194 %X Segmentation of coronary arteries from Coronary Computed Tomography Angiography (CCTA) is an essential step in developing various noninvasive diagnostic methods. In this work, we tackle the task of vessel labeling on coronary artery voxel-based prediction by use of point cloud artificial neural network. We propose a novel point aggregation technique Eigenvector Grouping (EVG), tailored to the analysis of tubular-like structures. We further utilize a specifically designed post-processing technique Component-Wise Majority Point Voting (CMPV), to refine point cloud segmentation by enforcing class consistency among connected components. We show that our solution outperforms previously proposed methods in the vessel labeling task on a CCTA dataset especially, in the presence of disrupted segmentations.
APA
Rygiel, P., Zieba, M. & Konopczynski, T.. (2022). Eigenvector Grouping for Point Cloud Vessel Labeling. Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, in Proceedings of Machine Learning Research 194:72-84 Available from https://proceedings.mlr.press/v194/rygiel22a.html.

Related Material