Automated intracranial vessel labeling with learning boosted by vessel connectivity, radii and spatial context

Jannik Sobisch, Žiga Bizjak, Aichi Chien, Žiga Špiclin
Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, PMLR 194:34-44, 2022.

Abstract

Cerebrovascular diseases are among the world’s top causes of death and their screening and diagnosis rely on angiographic imaging. We focused on automated anatomical labeling of cerebral arteries that enables their cross-sectional quantification and inter-subject comparisons and thereby identification of geometric risk factors correlated to the cerebrovascular diseases. We used 152 cerebral TOF-MRA angiograms from three publicly available datasets and manually created reference labeling using Slicer3D. We extracted centerlines from nnU-net based segmentations using VesselVio and labeled them according to the reference labeling. Vessel centerline coordinates, in combination with additional vessel connectivity, radius and spatial context features were used for training seven distinct PointNet++ models. Model trained solely on the vessel centerline coordinates resulted in ACC of 0.93 and across-labels average TPR was 0.88. Including vessel radius significantly improved ACC to 0.95, and average TPR to 0.91. Finally, focusing spatial context to the Circle of Willis are resulted in best ACC of 0.96 and best average TPR of 0.93. Hence, using vessel radius and spatial context greatly improved vessel labeling, with the attained perfomance opening the avenue for clinical applications of intracranial vessel labeling.

Cite this Paper

BibTeX
@InProceedings{pmlr-v194-sobisch22a, title = {Automated intracranial vessel labeling with learning boosted by vessel connectivity, radii and spatial context}, author = {Sobisch, Jannik and Bizjak, \v{Z}iga and Chien, Aichi and \v{S}piclin, \v{Z}iga}, booktitle = {Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis}, pages = {34--44}, 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/sobisch22a/sobisch22a.pdf}, url = {https://proceedings.mlr.press/v194/sobisch22a.html}, abstract = {Cerebrovascular diseases are among the world’s top causes of death and their screening and diagnosis rely on angiographic imaging. We focused on automated anatomical labeling of cerebral arteries that enables their cross-sectional quantification and inter-subject comparisons and thereby identification of geometric risk factors correlated to the cerebrovascular diseases. We used 152 cerebral TOF-MRA angiograms from three publicly available datasets and manually created reference labeling using Slicer3D. We extracted centerlines from nnU-net based segmentations using VesselVio and labeled them according to the reference labeling. Vessel centerline coordinates, in combination with additional vessel connectivity, radius and spatial context features were used for training seven distinct PointNet++ models. Model trained solely on the vessel centerline coordinates resulted in ACC of 0.93 and across-labels average TPR was 0.88. Including vessel radius significantly improved ACC to 0.95, and average TPR to 0.91. Finally, focusing spatial context to the Circle of Willis are resulted in best ACC of 0.96 and best average TPR of 0.93. Hence, using vessel radius and spatial context greatly improved vessel labeling, with the attained perfomance opening the avenue for clinical applications of intracranial vessel labeling. } }
Endnote
%0 Conference Paper %T Automated intracranial vessel labeling with learning boosted by vessel connectivity, radii and spatial context %A Jannik Sobisch %A Žiga Bizjak %A Aichi Chien %A Žiga Špiclin %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-sobisch22a %I PMLR %P 34--44 %U https://proceedings.mlr.press/v194/sobisch22a.html %V 194 %X Cerebrovascular diseases are among the world’s top causes of death and their screening and diagnosis rely on angiographic imaging. We focused on automated anatomical labeling of cerebral arteries that enables their cross-sectional quantification and inter-subject comparisons and thereby identification of geometric risk factors correlated to the cerebrovascular diseases. We used 152 cerebral TOF-MRA angiograms from three publicly available datasets and manually created reference labeling using Slicer3D. We extracted centerlines from nnU-net based segmentations using VesselVio and labeled them according to the reference labeling. Vessel centerline coordinates, in combination with additional vessel connectivity, radius and spatial context features were used for training seven distinct PointNet++ models. Model trained solely on the vessel centerline coordinates resulted in ACC of 0.93 and across-labels average TPR was 0.88. Including vessel radius significantly improved ACC to 0.95, and average TPR to 0.91. Finally, focusing spatial context to the Circle of Willis are resulted in best ACC of 0.96 and best average TPR of 0.93. Hence, using vessel radius and spatial context greatly improved vessel labeling, with the attained perfomance opening the avenue for clinical applications of intracranial vessel labeling.
APA
Sobisch, J., Bizjak, Ž., Chien, A. & Špiclin, Ž.. (2022). Automated intracranial vessel labeling with learning boosted by vessel connectivity, radii and spatial context. Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, in Proceedings of Machine Learning Research 194:34-44 Available from https://proceedings.mlr.press/v194/sobisch22a.html.

Related Material