Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning

Purpose Twin-to-twin transfusion syndrome (TTTS) is a serious condition that occurs in about 10–15% of monochorionic twin pregnancies. In most instances, the blood flow is unevenly distributed throughout the placenta anastomoses leading to the death of both fetuses if no surgical procedure is perfor...

Descripción completa

Detalles Bibliográficos
Autores: Perera Bel, Enric, Ceresa, Mario, Torrents Barrena, Jordina, Masoller, Narcís, Valenzuela Alcaraz, Brenda, Gratacós Solsona, Eduard, Eixarch, Elisenda, González Ballester, Miguel Ángel, 1973-
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2020
País:España
Institución:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/46189
Acceso en línea:http://hdl.handle.net/10230/46189
http://dx.doi.org/10.1007/s11548-020-02256-2
Access Level:acceso abierto
Palabra clave:Fetal surgery
Doppler US
TTTS
Placenta and vessel detection
Random walker
GPU optimization
id ES_af42fcfde116cdf951ccda212b51f2b1
oai_identifier_str oai:repositori.upf.edu:10230/46189
network_acronym_str ES
network_name_str España
repository_id_str
spelling Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planningPerera Bel, EnricCeresa, MarioTorrents Barrena, JordinaMasoller, NarcísValenzuela Alcaraz, BrendaGratacós Solsona, EduardEixarch, ElisendaGonzález Ballester, Miguel Ángel, 1973-Fetal surgeryDoppler USTTTSPlacenta and vessel detectionRandom walkerGPU optimizationPurpose Twin-to-twin transfusion syndrome (TTTS) is a serious condition that occurs in about 10–15% of monochorionic twin pregnancies. In most instances, the blood flow is unevenly distributed throughout the placenta anastomoses leading to the death of both fetuses if no surgical procedure is performed. Fetoscopic laser coagulation is the optimal therapy to considerably improve co-twin prognosis by clogging the abnormal anastomoses. Notwithstanding progress in recent years, TTTS surgery is highly risky. Computer-assisted planning of the intervention can thus improve the outcome. Methods In this work, we implement a GPU-accelerated random walker (RW) algorithm to detect the placenta, both umbilical cord insertions and the placental vasculature from Doppler ultrasound (US). Placenta and background seeds are manually initialized in 10–20 slices (out of 245). Vessels are automatically initialized in the same slices by means of Otsu thresholding. The RW finds the boundaries of the placenta and reconstructs the vasculature. Results We evaluate our semiautomatic method in 5 monochorionic and 24 singleton pregnancies. Although satisfactory performance is achieved on placenta segmentation (Dice ≥ 84.0%), some vascular connections are still neglected due to the presence of US reverberation artifacts (Dice ≥ 56.9%). We also compared inter-user variability and obtained Dice coefficients of ≥ 76.8% and ≥ 97.42% for placenta and vasculature, respectively. After a 3-min manual initialization, our GPU approach speeds the computation 10.6 times compared to the CPU. Conclusions Our semiautomatic method provides a near real-time user experience and requires short training without compromising the segmentation accuracy. A powerful approach is thus presented to rapidly plan the fetoscope insertion point ahead of TTTS surgery.The research leading to these results has received funding by The Cellex Foundation, “LaCaixa” Foundation under Grant Agreements LCF/PR/GN14/10270005 and LCF/PR/GN18/10310003, AGAUR under Grant 2017 SGR nº 1531, the Spanish Ministry of Economy and Competitiveness under the María de Maeztu Units of Excellence Programme [MDM-2015-0502], and the European Commission under the H2020 ATTRACT project MIIFI. Additionally, Enric Perera-Bel has received funding from the Spanish Ministry of Economy and Competitiveness under the Programme for the Formation of Doctors [BES-2017-081164], and Elisenda Eixarch from the Departament de Salut under the Grant SLT008/18/00156.Springer20212020info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/46189http://dx.doi.org/10.1007/s11548-020-02256-2reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésInternational Journal of Computer Assisted Radiology and Surgery. 2020 Sep 19;15:1869-79info:eu-repo/grantAgreement/ES/2PE/BES-2017-081164info:eu-repo/grantAgreement/EC/H2020/777222© Springer The final publication is available at Springer via http://dx.doi.org/10.1007/s11548-020-02256-2info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/461892026-06-12T07:21:37Z
dc.title.none.fl_str_mv Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning
title Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning
spellingShingle Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning
Perera Bel, Enric
Fetal surgery
Doppler US
TTTS
Placenta and vessel detection
Random walker
GPU optimization
title_short Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning
title_full Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning
title_fullStr Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning
title_full_unstemmed Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning
title_sort Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning
dc.creator.none.fl_str_mv Perera Bel, Enric
Ceresa, Mario
Torrents Barrena, Jordina
Masoller, Narcís
Valenzuela Alcaraz, Brenda
Gratacós Solsona, Eduard
Eixarch, Elisenda
González Ballester, Miguel Ángel, 1973-
author Perera Bel, Enric
author_facet Perera Bel, Enric
Ceresa, Mario
Torrents Barrena, Jordina
Masoller, Narcís
Valenzuela Alcaraz, Brenda
Gratacós Solsona, Eduard
Eixarch, Elisenda
González Ballester, Miguel Ángel, 1973-
author_role author
author2 Ceresa, Mario
Torrents Barrena, Jordina
Masoller, Narcís
Valenzuela Alcaraz, Brenda
Gratacós Solsona, Eduard
Eixarch, Elisenda
González Ballester, Miguel Ángel, 1973-
author2_role author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Fetal surgery
Doppler US
TTTS
Placenta and vessel detection
Random walker
GPU optimization
topic Fetal surgery
Doppler US
TTTS
Placenta and vessel detection
Random walker
GPU optimization
description Purpose Twin-to-twin transfusion syndrome (TTTS) is a serious condition that occurs in about 10–15% of monochorionic twin pregnancies. In most instances, the blood flow is unevenly distributed throughout the placenta anastomoses leading to the death of both fetuses if no surgical procedure is performed. Fetoscopic laser coagulation is the optimal therapy to considerably improve co-twin prognosis by clogging the abnormal anastomoses. Notwithstanding progress in recent years, TTTS surgery is highly risky. Computer-assisted planning of the intervention can thus improve the outcome. Methods In this work, we implement a GPU-accelerated random walker (RW) algorithm to detect the placenta, both umbilical cord insertions and the placental vasculature from Doppler ultrasound (US). Placenta and background seeds are manually initialized in 10–20 slices (out of 245). Vessels are automatically initialized in the same slices by means of Otsu thresholding. The RW finds the boundaries of the placenta and reconstructs the vasculature. Results We evaluate our semiautomatic method in 5 monochorionic and 24 singleton pregnancies. Although satisfactory performance is achieved on placenta segmentation (Dice ≥ 84.0%), some vascular connections are still neglected due to the presence of US reverberation artifacts (Dice ≥ 56.9%). We also compared inter-user variability and obtained Dice coefficients of ≥ 76.8% and ≥ 97.42% for placenta and vasculature, respectively. After a 3-min manual initialization, our GPU approach speeds the computation 10.6 times compared to the CPU. Conclusions Our semiautomatic method provides a near real-time user experience and requires short training without compromising the segmentation accuracy. A powerful approach is thus presented to rapidly plan the fetoscope insertion point ahead of TTTS surgery.
publishDate 2020
dc.date.none.fl_str_mv 2020
2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/46189
http://dx.doi.org/10.1007/s11548-020-02256-2
url http://hdl.handle.net/10230/46189
http://dx.doi.org/10.1007/s11548-020-02256-2
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv International Journal of Computer Assisted Radiology and Surgery. 2020 Sep 19;15:1869-79
info:eu-repo/grantAgreement/ES/2PE/BES-2017-081164
info:eu-repo/grantAgreement/EC/H2020/777222
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869416669209690112
score 15,198674