Standard

Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images : application to fully automatic detection of healthy wall regions. / Zahnd, Guillaume; Hoogendoorn, Ayla; Combaret, Nicolas; Karanasos, Antonios; Péry, Emilie; Sarry, Laurent; Motreff, Pascal; Niessen, Wiro; Regar, Evelyn; van Soest, Gijs; Gijsen, Frank; van Walsum, Theo.

In: International Journal of Computer Assisted Radiology and Surgery, Vol. 12, No. 11, 2017, p. 1923-1936.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Zahnd, G, Hoogendoorn, A, Combaret, N, Karanasos, A, Péry, E, Sarry, L, Motreff, P, Niessen, W, Regar, E, van Soest, G, Gijsen, F & van Walsum, T 2017, 'Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images: application to fully automatic detection of healthy wall regions' International Journal of Computer Assisted Radiology and Surgery, vol. 12, no. 11, pp. 1923-1936. https://doi.org/10.1007/s11548-017-1657-7

APA

Zahnd, G., Hoogendoorn, A., Combaret, N., Karanasos, A., Péry, E., Sarry, L., ... van Walsum, T. (2017). Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images: application to fully automatic detection of healthy wall regions. International Journal of Computer Assisted Radiology and Surgery, 12(11), 1923-1936. https://doi.org/10.1007/s11548-017-1657-7

Vancouver

Zahnd G, Hoogendoorn A, Combaret N, Karanasos A, Péry E, Sarry L et al. Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images: application to fully automatic detection of healthy wall regions. International Journal of Computer Assisted Radiology and Surgery. 2017;12(11):1923-1936. https://doi.org/10.1007/s11548-017-1657-7

Author

Zahnd, Guillaume ; Hoogendoorn, Ayla ; Combaret, Nicolas ; Karanasos, Antonios ; Péry, Emilie ; Sarry, Laurent ; Motreff, Pascal ; Niessen, Wiro ; Regar, Evelyn ; van Soest, Gijs ; Gijsen, Frank ; van Walsum, Theo. / Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images : application to fully automatic detection of healthy wall regions. In: International Journal of Computer Assisted Radiology and Surgery. 2017 ; Vol. 12, No. 11. pp. 1923-1936.

BibTeX

@article{7284b5c349db409f8b947dae63667d0f,
title = "Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images: application to fully automatic detection of healthy wall regions",
abstract = "Purpose: Quantitative and automatic analysis of intracoronary optical coherence tomography images is useful and time-saving to assess cardiovascular risk in the clinical arena. Methods: First, the interfaces of the intima, media, and adventitia layers are segmented, by means of an original front propagation scheme, running in a 4D multi-parametric space, to simultaneously extract three non-crossing contours in the initial cross-sectional image. Second, information resulting from the tentative contours is exploited by a machine learning approach to identify healthy and diseased regions of the arterial wall. The framework is fully automatic. Results: The method was applied to 40 patients from two different medical centers. The framework was trained on 140 images and validated on 260 other images. For the contour segmentation method, the average segmentation errors were 29±46μm for the intima–media interface, 30±50μm for the media–adventitia interface, and 50±64μm for the adventitia–periadventitia interface. The classification method demonstrated a good accuracy, with a median Dice coefficient equal to 0.93 and an interquartile range of (0.78–0.98). Conclusion: The proposed framework demonstrated promising offline performances and could potentially be translated into a reliable tool for various clinical applications, such as quantification of tissue layer thickness and global summarization of healthy regions in entire pullbacks.",
keywords = "Contour segmentation, Coronary artery, Machine learning, Optical coherence tomography",
author = "Guillaume Zahnd and Ayla Hoogendoorn and Nicolas Combaret and Antonios Karanasos and Emilie P{\'e}ry and Laurent Sarry and Pascal Motreff and Wiro Niessen and Evelyn Regar and {van Soest}, Gijs and Frank Gijsen and {van Walsum}, Theo",
year = "2017",
doi = "10.1007/s11548-017-1657-7",
language = "English",
volume = "12",
pages = "1923--1936",
journal = "International Journal of Computer Assisted Radiology and Surgery",
issn = "1861-6410",
number = "11",

}

RIS

TY - JOUR

T1 - Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images

T2 - International Journal of Computer Assisted Radiology and Surgery

AU - Zahnd, Guillaume

AU - Hoogendoorn, Ayla

AU - Combaret, Nicolas

AU - Karanasos, Antonios

AU - Péry, Emilie

AU - Sarry, Laurent

AU - Motreff, Pascal

AU - Niessen, Wiro

AU - Regar, Evelyn

AU - van Soest, Gijs

AU - Gijsen, Frank

AU - van Walsum, Theo

PY - 2017

Y1 - 2017

N2 - Purpose: Quantitative and automatic analysis of intracoronary optical coherence tomography images is useful and time-saving to assess cardiovascular risk in the clinical arena. Methods: First, the interfaces of the intima, media, and adventitia layers are segmented, by means of an original front propagation scheme, running in a 4D multi-parametric space, to simultaneously extract three non-crossing contours in the initial cross-sectional image. Second, information resulting from the tentative contours is exploited by a machine learning approach to identify healthy and diseased regions of the arterial wall. The framework is fully automatic. Results: The method was applied to 40 patients from two different medical centers. The framework was trained on 140 images and validated on 260 other images. For the contour segmentation method, the average segmentation errors were 29±46μm for the intima–media interface, 30±50μm for the media–adventitia interface, and 50±64μm for the adventitia–periadventitia interface. The classification method demonstrated a good accuracy, with a median Dice coefficient equal to 0.93 and an interquartile range of (0.78–0.98). Conclusion: The proposed framework demonstrated promising offline performances and could potentially be translated into a reliable tool for various clinical applications, such as quantification of tissue layer thickness and global summarization of healthy regions in entire pullbacks.

AB - Purpose: Quantitative and automatic analysis of intracoronary optical coherence tomography images is useful and time-saving to assess cardiovascular risk in the clinical arena. Methods: First, the interfaces of the intima, media, and adventitia layers are segmented, by means of an original front propagation scheme, running in a 4D multi-parametric space, to simultaneously extract three non-crossing contours in the initial cross-sectional image. Second, information resulting from the tentative contours is exploited by a machine learning approach to identify healthy and diseased regions of the arterial wall. The framework is fully automatic. Results: The method was applied to 40 patients from two different medical centers. The framework was trained on 140 images and validated on 260 other images. For the contour segmentation method, the average segmentation errors were 29±46μm for the intima–media interface, 30±50μm for the media–adventitia interface, and 50±64μm for the adventitia–periadventitia interface. The classification method demonstrated a good accuracy, with a median Dice coefficient equal to 0.93 and an interquartile range of (0.78–0.98). Conclusion: The proposed framework demonstrated promising offline performances and could potentially be translated into a reliable tool for various clinical applications, such as quantification of tissue layer thickness and global summarization of healthy regions in entire pullbacks.

KW - Contour segmentation

KW - Coronary artery

KW - Machine learning

KW - Optical coherence tomography

UR - http://www.scopus.com/inward/record.url?scp=85027331627&partnerID=8YFLogxK

U2 - 10.1007/s11548-017-1657-7

DO - 10.1007/s11548-017-1657-7

M3 - Article

VL - 12

SP - 1923

EP - 1936

JO - International Journal of Computer Assisted Radiology and Surgery

JF - International Journal of Computer Assisted Radiology and Surgery

SN - 1861-6410

IS - 11

ER -

ID: 47138187