File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound

TitleAgent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound
Authors
Issue Date2019
PublisherSpringer.
Citation
22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2019), Shenzhen, China, 13-17 October 2019. In Shen, D, Liu, T, Peters, TM, et al. (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part V, p. 290-298. Cham, Switzerland: Springer, 2019 How to Cite?
AbstractStandard plane localization is crucial for ultrasound (US) diagnosis. In prenatal US, dozens of standard planes are manually acquired with a 2D probe. It is time-consuming and operator-dependent. In comparison, 3D US containing multiple standard planes in one shot has the inherent advantages of less user-dependency and more efficiency. However, manual plane localization in US volume is challenging due to the huge search space and large fetal posture variation. In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US. Our contribution is two-fold. First, we equip the RL framework with a landmark-aware alignment module to provide warm start and strong spatial bounds for the agent actions, thus ensuring its effectiveness. Second, instead of passively and empirically terminating the agent inference, we propose a recurrent neural network based strategy for active termination of the agent’s interaction procedure. This improves both the accuracy and efficiency of the localization system. Extensively validated on our in-house large dataset, our approach achieves the accuracy of 3.4 mm/9.6 and 2.7 mm/9.1 for the transcerebellar and transthalamic plane localization, respectively. Our proposed RL framework is general and has the potential to improve the efficiency and standardization of US scanning.
Persistent Identifierhttp://hdl.handle.net/10722/299611
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
ISI Accession Number ID
Series/Report no.Lecture Notes in Computer Science ; 11768

 

DC FieldValueLanguage
dc.contributor.authorDou, Haoran-
dc.contributor.authorYang, Xin-
dc.contributor.authorQian, Jikuan-
dc.contributor.authorXue, Wufeng-
dc.contributor.authorQin, Hao-
dc.contributor.authorWang, Xu-
dc.contributor.authorYu, Lequan-
dc.contributor.authorWang, Shujun-
dc.contributor.authorXiong, Yi-
dc.contributor.authorHeng, Pheng Ann-
dc.contributor.authorNi, Dong-
dc.date.accessioned2021-05-21T03:34:47Z-
dc.date.available2021-05-21T03:34:47Z-
dc.date.issued2019-
dc.identifier.citation22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2019), Shenzhen, China, 13-17 October 2019. In Shen, D, Liu, T, Peters, TM, et al. (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part V, p. 290-298. Cham, Switzerland: Springer, 2019-
dc.identifier.isbn9783030322533-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/299611-
dc.description.abstractStandard plane localization is crucial for ultrasound (US) diagnosis. In prenatal US, dozens of standard planes are manually acquired with a 2D probe. It is time-consuming and operator-dependent. In comparison, 3D US containing multiple standard planes in one shot has the inherent advantages of less user-dependency and more efficiency. However, manual plane localization in US volume is challenging due to the huge search space and large fetal posture variation. In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US. Our contribution is two-fold. First, we equip the RL framework with a landmark-aware alignment module to provide warm start and strong spatial bounds for the agent actions, thus ensuring its effectiveness. Second, instead of passively and empirically terminating the agent inference, we propose a recurrent neural network based strategy for active termination of the agent’s interaction procedure. This improves both the accuracy and efficiency of the localization system. Extensively validated on our in-house large dataset, our approach achieves the accuracy of 3.4 mm/9.6 and 2.7 mm/9.1 for the transcerebellar and transthalamic plane localization, respectively. Our proposed RL framework is general and has the potential to improve the efficiency and standardization of US scanning.-
dc.languageeng-
dc.publisherSpringer.-
dc.relation.ispartofMedical Image Computing and Computer Assisted Intervention – MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part V-
dc.relation.ispartofseriesLecture Notes in Computer Science ; 11768-
dc.titleAgent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-030-32254-0_33-
dc.identifier.scopuseid_2-s2.0-85075641399-
dc.identifier.spage290-
dc.identifier.epage298-
dc.identifier.eissn1611-3349-
dc.identifier.isiWOS:000548735200033-
dc.publisher.placeCham, Switzerland-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats