Detecting Large Vessel Occlusions using Graph Deep Learning

Jad Kassam, Florian Thamm, Leonhard Rist, Oliver Taubmann, Andreas Maier
Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, PMLR 194:149-159, 2022.

Abstract

Large vessel occlusions (LVO) typically lead to severe ischemia of brain parenchyma. Identifying such LVOs is thus a crucial objective in stroke diagnosis. As shortening the time to treatment is essential for a good outcome, fast automated detection can be a valuable tool in clinical routine. This can be achieved using deep learning approaches. In a CTA scan, an LVO can be detected as an unexpected interruption in the contrast-enhanced vessel tree. These cerebrovascular trees can be represented as graphs and analyzed using graph deep learning (GDL) methods. Representing the vasculature as a graph instead of a (very sparsely populated) Euclidean volume massively reduces the model input dimensionality, which promotes time and memory efficiency. In this study, we investigate the use of graph deep learning methods for classifying the presence of a large vessel occlusion compared to state-of-the-art image-based methods. Furthermore, the influence of vascular attributes and different graph topologies is investigated. The proposed model achieves performance comparable to the baseline with an accuracy of $0.95$ and an AUC of $0.89$. Compared to the image-based approach, the graph-based approach is ten times faster and requires 80% less memory.

Cite this Paper

BibTeX
@InProceedings{pmlr-v194-kassam22a, title = {Detecting Large Vessel Occlusions using Graph Deep Learning}, author = {Kassam, Jad and Thamm, Florian and Rist, Leonhard and Taubmann, Oliver and Maier, Andreas}, booktitle = {Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis}, pages = {149--159}, 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/kassam22a/kassam22a.pdf}, url = {https://proceedings.mlr.press/v194/kassam22a.html}, abstract = {Large vessel occlusions (LVO) typically lead to severe ischemia of brain parenchyma. Identifying such LVOs is thus a crucial objective in stroke diagnosis. As shortening the time to treatment is essential for a good outcome, fast automated detection can be a valuable tool in clinical routine. This can be achieved using deep learning approaches. In a CTA scan, an LVO can be detected as an unexpected interruption in the contrast-enhanced vessel tree. These cerebrovascular trees can be represented as graphs and analyzed using graph deep learning (GDL) methods. Representing the vasculature as a graph instead of a (very sparsely populated) Euclidean volume massively reduces the model input dimensionality, which promotes time and memory efficiency. In this study, we investigate the use of graph deep learning methods for classifying the presence of a large vessel occlusion compared to state-of-the-art image-based methods. Furthermore, the influence of vascular attributes and different graph topologies is investigated. The proposed model achieves performance comparable to the baseline with an accuracy of $0.95$ and an AUC of $0.89$. Compared to the image-based approach, the graph-based approach is ten times faster and requires 80% less memory.} }
Endnote
%0 Conference Paper %T Detecting Large Vessel Occlusions using Graph Deep Learning %A Jad Kassam %A Florian Thamm %A Leonhard Rist %A Oliver Taubmann %A Andreas Maier %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-kassam22a %I PMLR %P 149--159 %U https://proceedings.mlr.press/v194/kassam22a.html %V 194 %X Large vessel occlusions (LVO) typically lead to severe ischemia of brain parenchyma. Identifying such LVOs is thus a crucial objective in stroke diagnosis. As shortening the time to treatment is essential for a good outcome, fast automated detection can be a valuable tool in clinical routine. This can be achieved using deep learning approaches. In a CTA scan, an LVO can be detected as an unexpected interruption in the contrast-enhanced vessel tree. These cerebrovascular trees can be represented as graphs and analyzed using graph deep learning (GDL) methods. Representing the vasculature as a graph instead of a (very sparsely populated) Euclidean volume massively reduces the model input dimensionality, which promotes time and memory efficiency. In this study, we investigate the use of graph deep learning methods for classifying the presence of a large vessel occlusion compared to state-of-the-art image-based methods. Furthermore, the influence of vascular attributes and different graph topologies is investigated. The proposed model achieves performance comparable to the baseline with an accuracy of $0.95$ and an AUC of $0.89$. Compared to the image-based approach, the graph-based approach is ten times faster and requires 80% less memory.
APA
Kassam, J., Thamm, F., Rist, L., Taubmann, O. & Maier, A.. (2022). Detecting Large Vessel Occlusions using Graph Deep Learning. Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, in Proceedings of Machine Learning Research 194:149-159 Available from https://proceedings.mlr.press/v194/kassam22a.html.

Related Material