Automatic labeling of vascular structures with topological constraints via HMM

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Wang, Xingceca
• dc.contributor.author Liu, Yueca
• dc.contributor.author Wu, Zhongkeca
• dc.contributor.author Mou, Xiaoca
• dc.contributor.author Zhou, Mingquanca
• dc.contributor.author González Ballester, Miguel Ángel, 1973-ca
• dc.contributor.author Zhang, Chongca
• dc.date.accessioned 2017-09-05T15:38:27Z
• dc.date.available 2017-09-05T15:38:27Z
• dc.date.issued 2017
• dc.description Comunicació presentada a: the 20th International Conference on Medical Image Computing and Computer Assisted Intervention 2017 (MICCAI 2017), celebrada del 10 al 14 de setembre de 2017 a Quebec, Canadà.ca
• dc.description.abstract Identifcation of anatomical vessel branches is a prerequisite task for diagnosis, treatment and inter-subject comparison. We propose a novel graph labeling approach to anatomically label vascular structures of interest. Our method frst extracts bifurcations of interest from the centerlines of vessels, where a set of geometric features are also calculated from. Then the probability distribution of every bifurcation is learned using a XGBoost classifer. Finally a Hidden Markov Model with a restricted transition strategy is constructed in order to nd the most likely labeling confguration of the whole structure, while also enforcing topological consistency. In this paper, the proposed approach has been evaluated through leave-one-out cross validation on 50 subjects of centerlines obtained from MRA images of healthy volunteers' Circle of Willis. Results demonstrate that our method can achieve higher accuracy and specifcity, while obtaining similar precision and recall, when comparing to the best performing state-of-the-art methods. Our algorithm can handle diferent topologies, like circle, chain and tree. By using coordinate independent geometrical features, it does not require prior global alignment. Source code and data are available under.en
• dc.description.sponsorship This research was partially supported by the Chinese High-Technical Research Development Foundation (863) Program (No.2015AA020506), Beijing Natural Science Foundation of China(No.4172033), the Spanish Ministry of Economy and Competitiveness, through the Maria de Maeztu Programme for Centres/Units of Excellence in R&D (MDM-2015-0502), and the Spanish Ministry of Economy and Competitiveness (DEFENSE project, TIN2013-47913-C3-1-R).en
• dc.format.mimetype application/pdf
• dc.identifier.citation Wang X, Liu Y, Wu Z, Zhou M, González Ballester MA, Zhang C. Automatic labeling of vascular structures with topological constraints via HMM. In: Descoteaux M, maier-Hein L, Franz A, Jannin P, collins DL, Duchesne S. Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017. 20th International Conference. Proceedings, Part II. 2017 Sept 10-14; Quebec, Canada. [Cham]: Springer; 2017. p. 208-15. (LNCS; no. 10434). DOI: 10.1007/978-3-319-66185-8_24
• dc.identifier.doi http://dx.doi.org/10.5281/zenodo.809931
• dc.identifier.uri http://hdl.handle.net/10230/32744
• dc.language.iso eng
• dc.publisher Springer
• dc.relation.ispartof Descoteaux M, maier-Hein L, Franz A, Jannin P, collins DL, Duchesne S. Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017. 20th International Conference. Proceedings, Part II. 2017 Sept 10-14; Quebec, Canada. [Cham]: Springer; 2017. p. 208-15. (LNCS; no. 10434).
• dc.relation.isreferencedby http://hdl.handle.net/10230/32858
• dc.relation.projectID info:eu-repo/grantAgreement/ES/1PE/TIN2013-47913-C3-1-R
• dc.rights © Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-66185-8_24
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Vessel labelingen
• dc.subject.keyword Topological constraintsen
• dc.subject.keyword Hidden Markov Modelen
• dc.subject.keyword XGBoosten
• dc.subject.keyword Circle of Willisen
• dc.title Automatic labeling of vascular structures with topological constraints via HMMca
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion