Fully automatic and real-time catheter segmentation in X-ray fluoroscopy

Pierre Ambrosini; Daniel Ruijters; Wiro J. Niessen; Adriaan Moelker; Theo van Walsum

doi:10.1007/978-3-319-66185-8_65

Fully automatic and real-time catheter segmentation in X-ray fluoroscopy

Pierre Ambrosini, Daniel Ruijters, Wiro J. Niessen, Adriaan Moelker, Theo van Walsum

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

80 Citaten (Scopus)

Samenvatting

Augmenting X-ray imaging with 3D roadmap to improve guidance is a common strategy. Such approaches benefit from automated analysis of the X-ray images, such as the automatic detection and tracking of instruments. In this paper, we propose a real-time method to segment the catheter and guidewire in 2D X-ray fluoroscopic sequences. The method is based on deep convolutional neural networks. The network takes as input the current image and the three previous ones, and segments the catheter and guidewire in the current image. Subsequently, a centerline model of the catheter is constructed from the segmented image. A small set of annotated data combined with data augmentation is used to train the network. We trained the method on images from 182 X-ray sequences from 23 different interventions. On a testing set with images of 55 X-ray sequences from 5 other interventions, a median centerline distance error of 0.2 mm and a median tip distance error of 0.9 mm was obtained. The segmentation of the instruments in 2D X-ray sequences is performed in a real-time fully-automatic manner.

Originele taal-2	Engels
Titel	Medical Image Computing and Computer Assisted Intervention − MICCAI 2017
Subtitel	20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II
Redacteuren	Maxime Descoteaux, Lena Maier-Hein, Alfred Franz, Pierre Jannin, D. Louis Collins, Simon Duchesne
Plaats van productie	Cham
Uitgeverij	Springer
Hoofdstuk	65
Pagina's	577-585
Aantal pagina's	9
ISBN van elektronische versie	978-3-319-66185-8
ISBN van geprinte versie	978-3-319-66184-1
DOI's	https://doi.org/10.1007/978-3-319-66185-8_65
Status	Gepubliceerd - 2017
Extern gepubliceerd	Ja
Evenement	20th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2017 - Quebec City, Canada Duur: 11 sep. 2017 → 13 sep. 2017

Publicatie series

Naam	Lecture Notes in Computer Science (LNCS)
Volume	10434
ISSN van geprinte versie	0302-9743
ISSN van elektronische versie	1611-3349

Congres

Congres	20th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2017
Land/Regio	Canada
Stad	Quebec City
Periode	11/09/17 → 13/09/17

Bibliografische nota

Publisher Copyright:
© Springer International Publishing AG 2017.

Toegang tot document

10.1007/978-3-319-66185-8_65

Andere bestanden en links

Link naar publicatie in Scopus

Citeer dit

Ambrosini, P., Ruijters, D., Niessen, W. J., Moelker, A., & van Walsum, T. (2017). Fully automatic and real-time catheter segmentation in X-ray fluoroscopy. In M. Descoteaux, L. Maier-Hein, A. Franz, P. Jannin, D. L. Collins, & S. Duchesne (editors), Medical Image Computing and Computer Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II (blz. 577-585). (Lecture Notes in Computer Science (LNCS); Vol. 10434 ). Springer. https://doi.org/10.1007/978-3-319-66185-8_65

Ambrosini, Pierre ; Ruijters, Daniel ; Niessen, Wiro J. et al. / Fully automatic and real-time catheter segmentation in X-ray fluoroscopy. Medical Image Computing and Computer Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II. redacteur / Maxime Descoteaux ; Lena Maier-Hein ; Alfred Franz ; Pierre Jannin ; D. Louis Collins ; Simon Duchesne. Cham : Springer, 2017. blz. 577-585 (Lecture Notes in Computer Science (LNCS)).

@inproceedings{7a0413389c574ebc9d7afebab263ccb4,

title = "Fully automatic and real-time catheter segmentation in X-ray fluoroscopy",

abstract = "Augmenting X-ray imaging with 3D roadmap to improve guidance is a common strategy. Such approaches benefit from automated analysis of the X-ray images, such as the automatic detection and tracking of instruments. In this paper, we propose a real-time method to segment the catheter and guidewire in 2D X-ray fluoroscopic sequences. The method is based on deep convolutional neural networks. The network takes as input the current image and the three previous ones, and segments the catheter and guidewire in the current image. Subsequently, a centerline model of the catheter is constructed from the segmented image. A small set of annotated data combined with data augmentation is used to train the network. We trained the method on images from 182 X-ray sequences from 23 different interventions. On a testing set with images of 55 X-ray sequences from 5 other interventions, a median centerline distance error of 0.2 mm and a median tip distance error of 0.9 mm was obtained. The segmentation of the instruments in 2D X-ray sequences is performed in a real-time fully-automatic manner.",

keywords = "Catheter, Convolutional neural network, Deep learning, Fluoroscopy, Guidewire, Segmentation, Tracking, X-ray",

author = "Pierre Ambrosini and Daniel Ruijters and Niessen, {Wiro J.} and Adriaan Moelker and {van Walsum}, Theo",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2017.; 20th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2017 ; Conference date: 11-09-2017 Through 13-09-2017",

year = "2017",

doi = "10.1007/978-3-319-66185-8_65",

language = "English",

isbn = "978-3-319-66184-1",

series = "Lecture Notes in Computer Science (LNCS)",

publisher = "Springer",

pages = "577--585",

editor = "Maxime Descoteaux and Lena Maier-Hein and Alfred Franz and Pierre Jannin and Collins, {D. Louis} and Simon Duchesne",

booktitle = "Medical Image Computing and Computer Assisted Intervention − MICCAI 2017",

address = "Germany",

}

Ambrosini, P, Ruijters, D, Niessen, WJ, Moelker, A & van Walsum, T 2017, Fully automatic and real-time catheter segmentation in X-ray fluoroscopy. in M Descoteaux, L Maier-Hein, A Franz, P Jannin, DL Collins & S Duchesne (uitgave), Medical Image Computing and Computer Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II. Lecture Notes in Computer Science (LNCS), vol. 10434 , Springer, Cham, blz. 577-585, 20th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2017, Quebec City, Canada, 11/09/17. https://doi.org/10.1007/978-3-319-66185-8_65

Fully automatic and real-time catheter segmentation in X-ray fluoroscopy. / Ambrosini, Pierre; Ruijters, Daniel; Niessen, Wiro J. et al.
Medical Image Computing and Computer Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II. uitgave / Maxime Descoteaux; Lena Maier-Hein; Alfred Franz; Pierre Jannin; D. Louis Collins; Simon Duchesne. Cham: Springer, 2017. blz. 577-585 (Lecture Notes in Computer Science (LNCS); Vol. 10434 ).

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

TY - GEN

T1 - Fully automatic and real-time catheter segmentation in X-ray fluoroscopy

AU - Ambrosini, Pierre

AU - Ruijters, Daniel

AU - Niessen, Wiro J.

AU - Moelker, Adriaan

AU - van Walsum, Theo

N1 - Publisher Copyright: © Springer International Publishing AG 2017.

PY - 2017

Y1 - 2017

N2 - Augmenting X-ray imaging with 3D roadmap to improve guidance is a common strategy. Such approaches benefit from automated analysis of the X-ray images, such as the automatic detection and tracking of instruments. In this paper, we propose a real-time method to segment the catheter and guidewire in 2D X-ray fluoroscopic sequences. The method is based on deep convolutional neural networks. The network takes as input the current image and the three previous ones, and segments the catheter and guidewire in the current image. Subsequently, a centerline model of the catheter is constructed from the segmented image. A small set of annotated data combined with data augmentation is used to train the network. We trained the method on images from 182 X-ray sequences from 23 different interventions. On a testing set with images of 55 X-ray sequences from 5 other interventions, a median centerline distance error of 0.2 mm and a median tip distance error of 0.9 mm was obtained. The segmentation of the instruments in 2D X-ray sequences is performed in a real-time fully-automatic manner.

AB - Augmenting X-ray imaging with 3D roadmap to improve guidance is a common strategy. Such approaches benefit from automated analysis of the X-ray images, such as the automatic detection and tracking of instruments. In this paper, we propose a real-time method to segment the catheter and guidewire in 2D X-ray fluoroscopic sequences. The method is based on deep convolutional neural networks. The network takes as input the current image and the three previous ones, and segments the catheter and guidewire in the current image. Subsequently, a centerline model of the catheter is constructed from the segmented image. A small set of annotated data combined with data augmentation is used to train the network. We trained the method on images from 182 X-ray sequences from 23 different interventions. On a testing set with images of 55 X-ray sequences from 5 other interventions, a median centerline distance error of 0.2 mm and a median tip distance error of 0.9 mm was obtained. The segmentation of the instruments in 2D X-ray sequences is performed in a real-time fully-automatic manner.

KW - Catheter

KW - Convolutional neural network

KW - Deep learning

KW - Fluoroscopy

KW - Guidewire

KW - Segmentation

KW - Tracking

KW - X-ray

UR - http://www.scopus.com/inward/record.url?scp=85029532768&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-66185-8_65

DO - 10.1007/978-3-319-66185-8_65

M3 - Conference contribution

AN - SCOPUS:85029532768

SN - 978-3-319-66184-1

T3 - Lecture Notes in Computer Science (LNCS)

SP - 577

EP - 585

BT - Medical Image Computing and Computer Assisted Intervention − MICCAI 2017

A2 - Descoteaux, Maxime

A2 - Maier-Hein, Lena

A2 - Franz, Alfred

A2 - Jannin, Pierre

A2 - Collins, D. Louis

A2 - Duchesne, Simon

PB - Springer

CY - Cham

T2 - 20th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2017

Y2 - 11 September 2017 through 13 September 2017

ER -

Ambrosini P, Ruijters D, Niessen WJ, Moelker A, van Walsum T. Fully automatic and real-time catheter segmentation in X-ray fluoroscopy. In Descoteaux M, Maier-Hein L, Franz A, Jannin P, Collins DL, Duchesne S, redacteurs, Medical Image Computing and Computer Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II. Cham: Springer. 2017. blz. 577-585. (Lecture Notes in Computer Science (LNCS)). doi: 10.1007/978-3-319-66185-8_65

Fully automatic and real-time catheter segmentation in X-ray fluoroscopy

Samenvatting

Publicatie series

Congres

Bibliografische nota

Toegang tot document

Andere bestanden en links

Vingerafdruk

Citeer dit