Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets

Autores
Ziemer, Paulo G. P.; Bulant, Carlos Alberto; Orlando, José Ignacio; Maso Talou, Gonzalo D.; Mansilla Álvarez, Luis A.; Guedes Bezerra, Cristiano; Lemos, Pedro A.; García García, Héctor M.; Blanco, Pablo J.
Año de publicación
2020
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Aims: Assessment of minimum lumen areas in intravascular ultrasound (IVUS) pullbacks is time-consuming and demands adequately trained personnel. In this work, we introduce a novel and fully automated pipeline to segment the lumen boundary in IVUS datasets. Methods and results First, an automated gating is applied to select end-diastolic frames and bypass saw-tooth artefacts. Second, within a machine learning (ML) environment, we automatically segment the lumen boundary using a multi-frame (MF) convolutional neural network (MFCNN). Finally, we use the theory of Gaussian processes (GPs) to regress the final lumen boundary. The dataset consisted of 85 IVUS pullbacks (52 patients). The dataset was partitioned at the pullback-level using 73 pullbacks for training (20 586 frames), 6 pullbacks for validation (1692 frames), and 6 for testing (1692 frames). The degree of overlapping, between the ground truth and ML contours, median (interquartile range, IQR) systematically increased from 0.896 (0.874–0.933) for MF1 to 0.925 (0.911–0.948) for MF11. The median (IQR) of the distance error was also reduced from 3.83 (2.94–4.98)% for MF1 to 3.02 (2.25–3.95)% for MF11-GP. The corresponding median (IQR) in the lumen area error remained between 5.49 (2.50–10.50)% for MF1 and 5.12 (2.15–9.00)% for MF11-GP. The dispersion in the relative distance and area errors consistently decreased as we increased the number of frames, and also when the GP regressor was coupled to the MFCNN output. Conclusion: These results demonstrate that the proposed ML approach is suitable to effectively segment the lumen boundary in IVUS scans, reducing the burden of costly and time-consuming manual delineation.
Fil: Ziemer, Paulo G. P.. Laboratorio Nacional de Computacao Cientifica; Brasil
Fil: Bulant, Carlos Alberto. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comision de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; Argentina
Fil: Orlando, José Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; Argentina. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comision de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina
Fil: Maso Talou, Gonzalo D.. University of Auckland; Nueva Zelanda
Fil: Mansilla Álvarez, Luis A.. Laboratorio Nacional de Computacao Cientifica; Brasil
Fil: Guedes Bezerra, Cristiano. Universidade de Sao Paulo; Brasil
Fil: Lemos, Pedro A.. Universidade de Sao Paulo; Brasil
Fil: García García, Héctor M.. Georgetown University School of Medicine; Estados Unidos
Fil: Blanco, Pablo J.. Laboratorio Nacional de Computacao Cientifica; Brasil
Materia
IVUS
SEGMENTATION
GATING
NEURAL NETWORKS
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/128682
Acceder
id CONICETDig_e00f6ebc7364957a7dd60bfdacb80378
oai_identifier_str oai:ri.conicet.gov.ar:11336/128682
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasetsZiemer, Paulo G. P.Bulant, Carlos AlbertoOrlando, José IgnacioMaso Talou, Gonzalo D.Mansilla Álvarez, Luis A.Guedes Bezerra, CristianoLemos, Pedro A.García García, Héctor M.Blanco, Pablo J.IVUSSEGMENTATIONGATINGNEURAL NETWORKShttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Aims: Assessment of minimum lumen areas in intravascular ultrasound (IVUS) pullbacks is time-consuming and demands adequately trained personnel. In this work, we introduce a novel and fully automated pipeline to segment the lumen boundary in IVUS datasets. Methods and results First, an automated gating is applied to select end-diastolic frames and bypass saw-tooth artefacts. Second, within a machine learning (ML) environment, we automatically segment the lumen boundary using a multi-frame (MF) convolutional neural network (MFCNN). Finally, we use the theory of Gaussian processes (GPs) to regress the final lumen boundary. The dataset consisted of 85 IVUS pullbacks (52 patients). The dataset was partitioned at the pullback-level using 73 pullbacks for training (20 586 frames), 6 pullbacks for validation (1692 frames), and 6 for testing (1692 frames). The degree of overlapping, between the ground truth and ML contours, median (interquartile range, IQR) systematically increased from 0.896 (0.874–0.933) for MF1 to 0.925 (0.911–0.948) for MF11. The median (IQR) of the distance error was also reduced from 3.83 (2.94–4.98)% for MF1 to 3.02 (2.25–3.95)% for MF11-GP. The corresponding median (IQR) in the lumen area error remained between 5.49 (2.50–10.50)% for MF1 and 5.12 (2.15–9.00)% for MF11-GP. The dispersion in the relative distance and area errors consistently decreased as we increased the number of frames, and also when the GP regressor was coupled to the MFCNN output. Conclusion: These results demonstrate that the proposed ML approach is suitable to effectively segment the lumen boundary in IVUS scans, reducing the burden of costly and time-consuming manual delineation.Fil: Ziemer, Paulo G. P.. Laboratorio Nacional de Computacao Cientifica; BrasilFil: Bulant, Carlos Alberto. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comision de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; ArgentinaFil: Orlando, José Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; Argentina. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comision de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; ArgentinaFil: Maso Talou, Gonzalo D.. University of Auckland; Nueva ZelandaFil: Mansilla Álvarez, Luis A.. Laboratorio Nacional de Computacao Cientifica; BrasilFil: Guedes Bezerra, Cristiano. Universidade de Sao Paulo; BrasilFil: Lemos, Pedro A.. Universidade de Sao Paulo; BrasilFil: García García, Héctor M.. Georgetown University School of Medicine; Estados UnidosFil: Blanco, Pablo J.. Laboratorio Nacional de Computacao Cientifica; BrasilOxford University Press2020-11info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/128682Ziemer, Paulo G. P.; Bulant, Carlos Alberto; Orlando, José Ignacio; Maso Talou, Gonzalo D.; Mansilla Álvarez, Luis A.; et al.; Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets; Oxford University Press; European Heart Journal - Digital Health; 1; 1; 11-2020; 1-82634-3916CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://academic.oup.com/ehjdh/advance-article/doi/10.1093/ehjdh/ztaa014/5998645info:eu-repo/semantics/altIdentifier/doi/10.1093/ehjdh/ztaa014info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T09:55:21Zoai:ri.conicet.gov.ar:11336/128682instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 09:55:21.404CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets
title Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets
spellingShingle Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets
Ziemer, Paulo G. P.
IVUS
SEGMENTATION
GATING
NEURAL NETWORKS
title_short Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets
title_full Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets
title_fullStr Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets
title_full_unstemmed Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets
title_sort Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets
dc.creator.none.fl_str_mv Ziemer, Paulo G. P.
Bulant, Carlos Alberto
Orlando, José Ignacio
Maso Talou, Gonzalo D.
Mansilla Álvarez, Luis A.
Guedes Bezerra, Cristiano
Lemos, Pedro A.
García García, Héctor M.
Blanco, Pablo J.
author Ziemer, Paulo G. P.
author_facet Ziemer, Paulo G. P.
Bulant, Carlos Alberto
Orlando, José Ignacio
Maso Talou, Gonzalo D.
Mansilla Álvarez, Luis A.
Guedes Bezerra, Cristiano
Lemos, Pedro A.
García García, Héctor M.
Blanco, Pablo J.
author_role author
author2 Bulant, Carlos Alberto
Orlando, José Ignacio
Maso Talou, Gonzalo D.
Mansilla Álvarez, Luis A.
Guedes Bezerra, Cristiano
Lemos, Pedro A.
García García, Héctor M.
Blanco, Pablo J.
author2_role author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv IVUS
SEGMENTATION
GATING
NEURAL NETWORKS
topic IVUS
SEGMENTATION
GATING
NEURAL NETWORKS
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Aims: Assessment of minimum lumen areas in intravascular ultrasound (IVUS) pullbacks is time-consuming and demands adequately trained personnel. In this work, we introduce a novel and fully automated pipeline to segment the lumen boundary in IVUS datasets. Methods and results First, an automated gating is applied to select end-diastolic frames and bypass saw-tooth artefacts. Second, within a machine learning (ML) environment, we automatically segment the lumen boundary using a multi-frame (MF) convolutional neural network (MFCNN). Finally, we use the theory of Gaussian processes (GPs) to regress the final lumen boundary. The dataset consisted of 85 IVUS pullbacks (52 patients). The dataset was partitioned at the pullback-level using 73 pullbacks for training (20 586 frames), 6 pullbacks for validation (1692 frames), and 6 for testing (1692 frames). The degree of overlapping, between the ground truth and ML contours, median (interquartile range, IQR) systematically increased from 0.896 (0.874–0.933) for MF1 to 0.925 (0.911–0.948) for MF11. The median (IQR) of the distance error was also reduced from 3.83 (2.94–4.98)% for MF1 to 3.02 (2.25–3.95)% for MF11-GP. The corresponding median (IQR) in the lumen area error remained between 5.49 (2.50–10.50)% for MF1 and 5.12 (2.15–9.00)% for MF11-GP. The dispersion in the relative distance and area errors consistently decreased as we increased the number of frames, and also when the GP regressor was coupled to the MFCNN output. Conclusion: These results demonstrate that the proposed ML approach is suitable to effectively segment the lumen boundary in IVUS scans, reducing the burden of costly and time-consuming manual delineation.
Fil: Ziemer, Paulo G. P.. Laboratorio Nacional de Computacao Cientifica; Brasil
Fil: Bulant, Carlos Alberto. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comision de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; Argentina
Fil: Orlando, José Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil; Argentina. Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ciencias Exactas. Grupo de Plasmas Densos Magnetizados. Provincia de Buenos Aires. Gobernación. Comision de Investigaciones Científicas. Grupo de Plasmas Densos Magnetizados; Argentina
Fil: Maso Talou, Gonzalo D.. University of Auckland; Nueva Zelanda
Fil: Mansilla Álvarez, Luis A.. Laboratorio Nacional de Computacao Cientifica; Brasil
Fil: Guedes Bezerra, Cristiano. Universidade de Sao Paulo; Brasil
Fil: Lemos, Pedro A.. Universidade de Sao Paulo; Brasil
Fil: García García, Héctor M.. Georgetown University School of Medicine; Estados Unidos
Fil: Blanco, Pablo J.. Laboratorio Nacional de Computacao Cientifica; Brasil
description Aims: Assessment of minimum lumen areas in intravascular ultrasound (IVUS) pullbacks is time-consuming and demands adequately trained personnel. In this work, we introduce a novel and fully automated pipeline to segment the lumen boundary in IVUS datasets. Methods and results First, an automated gating is applied to select end-diastolic frames and bypass saw-tooth artefacts. Second, within a machine learning (ML) environment, we automatically segment the lumen boundary using a multi-frame (MF) convolutional neural network (MFCNN). Finally, we use the theory of Gaussian processes (GPs) to regress the final lumen boundary. The dataset consisted of 85 IVUS pullbacks (52 patients). The dataset was partitioned at the pullback-level using 73 pullbacks for training (20 586 frames), 6 pullbacks for validation (1692 frames), and 6 for testing (1692 frames). The degree of overlapping, between the ground truth and ML contours, median (interquartile range, IQR) systematically increased from 0.896 (0.874–0.933) for MF1 to 0.925 (0.911–0.948) for MF11. The median (IQR) of the distance error was also reduced from 3.83 (2.94–4.98)% for MF1 to 3.02 (2.25–3.95)% for MF11-GP. The corresponding median (IQR) in the lumen area error remained between 5.49 (2.50–10.50)% for MF1 and 5.12 (2.15–9.00)% for MF11-GP. The dispersion in the relative distance and area errors consistently decreased as we increased the number of frames, and also when the GP regressor was coupled to the MFCNN output. Conclusion: These results demonstrate that the proposed ML approach is suitable to effectively segment the lumen boundary in IVUS scans, reducing the burden of costly and time-consuming manual delineation.
publishDate 2020
dc.date.none.fl_str_mv 2020-11
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/128682
Ziemer, Paulo G. P.; Bulant, Carlos Alberto; Orlando, José Ignacio; Maso Talou, Gonzalo D.; Mansilla Álvarez, Luis A.; et al.; Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets; Oxford University Press; European Heart Journal - Digital Health; 1; 1; 11-2020; 1-8
2634-3916
CONICET Digital
CONICET
url http://hdl.handle.net/11336/128682
identifier_str_mv Ziemer, Paulo G. P.; Bulant, Carlos Alberto; Orlando, José Ignacio; Maso Talou, Gonzalo D.; Mansilla Álvarez, Luis A.; et al.; Automated lumen segmentation using multi-frame convolutional neural networks in Intravascular Ultrasound datasets; Oxford University Press; European Heart Journal - Digital Health; 1; 1; 11-2020; 1-8
2634-3916
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://academic.oup.com/ehjdh/advance-article/doi/10.1093/ehjdh/ztaa014/5998645
info:eu-repo/semantics/altIdentifier/doi/10.1093/ehjdh/ztaa014
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Oxford University Press
publisher.none.fl_str_mv Oxford University Press
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842269339524268032
score 13.13397

Publicaciones similares