Dynamic Pacemaker Artifact Removal (DyPAR) from CT Data using CNNs

Tanja Lossau (née Elss), Hannes Nickisch, Tobias Wissel, Samer Hakmi, Clemens Spink, Michael M. Morlock, Michael Grass
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:347-357, 2019.

Abstract

Metal objects in the human heart like implanted pacemakers frequently occur in elderly patients. Due to cardiac motion, they are not static during the CT acquisition and lead to heavy artifacts in reconstructed CT image volumes. Furthermore, cardiac motion precludes the application of standard metal artifact reduction methods which assume that the object does not move. We propose a deep-learning-based approach for dynamic pacemaker artifact removal which deals with metal shadow segmentation directly in the projection domain. The data required for supervised learning is generated by introducing synthetic pacemaker leads into 14 clinical data sets without pacemakers. CNNs achieve a Dice coefficient of $0.913$ on test data with synthetic metal leads. Application of the trained CNNs on eight data sets with real pacemakers and subsequent inpainting of the post-processed segmentation masks leads to significantly reduced metal artifacts in the reconstructed CT image volumes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v102-lossau-nee-elss-19a, title = {Dynamic Pacemaker Artifact Removal (DyPAR) from CT Data using CNNs}, author = {{Lossau (n\'{e}e Elss)}, Tanja and Nickisch, Hannes and Wissel, Tobias and Hakmi, Samer and Spink, Clemens and Morlock, {Michael M.} and Grass, Michael}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {347--357}, year = {2019}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, volume = {102}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v102/lossau-nee-elss-19a/lossau-nee-elss-19a.pdf}, url = {https://proceedings.mlr.press/v102/lossau-nee-elss-19a.html}, abstract = {Metal objects in the human heart like implanted pacemakers frequently occur in elderly patients. Due to cardiac motion, they are not static during the CT acquisition and lead to heavy artifacts in reconstructed CT image volumes. Furthermore, cardiac motion precludes the application of standard metal artifact reduction methods which assume that the object does not move. We propose a deep-learning-based approach for dynamic pacemaker artifact removal which deals with metal shadow segmentation directly in the projection domain. The data required for supervised learning is generated by introducing synthetic pacemaker leads into 14 clinical data sets without pacemakers. CNNs achieve a Dice coefficient of $0.913$ on test data with synthetic metal leads. Application of the trained CNNs on eight data sets with real pacemakers and subsequent inpainting of the post-processed segmentation masks leads to significantly reduced metal artifacts in the reconstructed CT image volumes.} }
Endnote
%0 Conference Paper %T Dynamic Pacemaker Artifact Removal (DyPAR) from CT Data using CNNs %A Tanja Lossau (née Elss) %A Hannes Nickisch %A Tobias Wissel %A Samer Hakmi %A Clemens Spink %A Michael M. Morlock %A Michael Grass %B Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2019 %E M. Jorge Cardoso %E Aasa Feragen %E Ben Glocker %E Ender Konukoglu %E Ipek Oguz %E Gozde Unal %E Tom Vercauteren %F pmlr-v102-lossau-nee-elss-19a %I PMLR %P 347--357 %U https://proceedings.mlr.press/v102/lossau-nee-elss-19a.html %V 102 %X Metal objects in the human heart like implanted pacemakers frequently occur in elderly patients. Due to cardiac motion, they are not static during the CT acquisition and lead to heavy artifacts in reconstructed CT image volumes. Furthermore, cardiac motion precludes the application of standard metal artifact reduction methods which assume that the object does not move. We propose a deep-learning-based approach for dynamic pacemaker artifact removal which deals with metal shadow segmentation directly in the projection domain. The data required for supervised learning is generated by introducing synthetic pacemaker leads into 14 clinical data sets without pacemakers. CNNs achieve a Dice coefficient of $0.913$ on test data with synthetic metal leads. Application of the trained CNNs on eight data sets with real pacemakers and subsequent inpainting of the post-processed segmentation masks leads to significantly reduced metal artifacts in the reconstructed CT image volumes.
APA
Lossau (née Elss), T., Nickisch, H., Wissel, T., Hakmi, S., Spink, C., Morlock, M.M. & Grass, M.. (2019). Dynamic Pacemaker Artifact Removal (DyPAR) from CT Data using CNNs. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:347-357 Available from https://proceedings.mlr.press/v102/lossau-nee-elss-19a.html.

Related Material