Deep Reinforcement Learning for Organ Localization in CT

Fernando Navarro, Anjany Sekuboyina, Diana Waldmannstetter, Jan C. Peeken, Stephanie E. Combs, Bjoern H. Menze
; Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:544-554, 2020.

Abstract

Robust localization of organs in computed tomography scans is a constant pre-processing requirement for organ-specific image retrieval, radiotherapy planning, and interventional image analysis. In contrast to current solutions based on exhaustive search or region proposals, which require large amounts of annotated data, we propose a deep reinforcement learning approach for organ localization in CT. In this work, an artificial agent is actively self-taught to localize organs in CT by learning from its asserts and mistakes. Within the context of reinforcement learning, we propose a novel set of actions tailored for organ localization in CT. Our method can use as a plug-and-play module for localizing any organ of interest. We evaluate the proposed solution on the public VISCERAL dataset containing CT scans with varying fields of view and multiple organs. We achieved an overall intersection over union of 0.63, an absolute median wall distance of 2.25 mm and a median distance between centroids of 3.65 mm.

Cite this Paper


BibTeX
@InProceedings{pmlr-v121-navarro20a, title = {Deep Reinforcement Learning for Organ Localization in CT}, author = {Navarro, Fernando and Sekuboyina, Anjany and Waldmannstetter, Diana and Peeken, Jan C. and Combs, Stephanie E. and Menze, Bjoern H.}, pages = {544--554}, year = {2020}, editor = {Tal Arbel and Ismail Ben Ayed and Marleen de Bruijne and Maxime Descoteaux and Herve Lombaert and Christopher Pal}, volume = {121}, series = {Proceedings of Machine Learning Research}, address = {Montreal, QC, Canada}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/navarro20a/navarro20a.pdf}, url = {http://proceedings.mlr.press/v121/navarro20a.html}, abstract = {Robust localization of organs in computed tomography scans is a constant pre-processing requirement for organ-specific image retrieval, radiotherapy planning, and interventional image analysis. In contrast to current solutions based on exhaustive search or region proposals, which require large amounts of annotated data, we propose a deep reinforcement learning approach for organ localization in CT. In this work, an artificial agent is actively self-taught to localize organs in CT by learning from its asserts and mistakes. Within the context of reinforcement learning, we propose a novel set of actions tailored for organ localization in CT. Our method can use as a plug-and-play module for localizing any organ of interest. We evaluate the proposed solution on the public VISCERAL dataset containing CT scans with varying fields of view and multiple organs. We achieved an overall intersection over union of 0.63, an absolute median wall distance of 2.25 mm and a median distance between centroids of 3.65 mm.} }
Endnote
%0 Conference Paper %T Deep Reinforcement Learning for Organ Localization in CT %A Fernando Navarro %A Anjany Sekuboyina %A Diana Waldmannstetter %A Jan C. Peeken %A Stephanie E. Combs %A Bjoern H. Menze %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-navarro20a %I PMLR %J Proceedings of Machine Learning Research %P 544--554 %U http://proceedings.mlr.press %V 121 %W PMLR %X Robust localization of organs in computed tomography scans is a constant pre-processing requirement for organ-specific image retrieval, radiotherapy planning, and interventional image analysis. In contrast to current solutions based on exhaustive search or region proposals, which require large amounts of annotated data, we propose a deep reinforcement learning approach for organ localization in CT. In this work, an artificial agent is actively self-taught to localize organs in CT by learning from its asserts and mistakes. Within the context of reinforcement learning, we propose a novel set of actions tailored for organ localization in CT. Our method can use as a plug-and-play module for localizing any organ of interest. We evaluate the proposed solution on the public VISCERAL dataset containing CT scans with varying fields of view and multiple organs. We achieved an overall intersection over union of 0.63, an absolute median wall distance of 2.25 mm and a median distance between centroids of 3.65 mm.
APA
Navarro, F., Sekuboyina, A., Waldmannstetter, D., Peeken, J.C., Combs, S.E. & Menze, B.H.. (2020). Deep Reinforcement Learning for Organ Localization in CT. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in PMLR 121:544-554

Related Material