Catheter segmentation in three-dimensional ultrasound images by feature fusion and model fitting

H. Yang (Corresponding author), C. Shan, A. Pourtaherian, Alexander F. Kolen, P.H.N. de With

Research output: Contribution to journalArticleAcademicpeer-review

4 Citations (Scopus)
34 Downloads (Pure)

Abstract

Ultrasound (US) has been increasingly used during interventions, such as cardiac catheterization. To accurately identify the catheter inside US images, extra training for physicians and sonographers is needed. As a consequence, automated segmentation of the catheter in US images and optimized presentation viewing to the physician can be beneficial to accelerate the efficiency and safety of interventions and improve their outcome. For cardiac catheterization, a three-dimensional (3-D) US image is potentially attractive because of no radiation modality and richer spatial information. However, due to a limited spatial resolution of 3-D cardiac US and complex anatomical structures inside the heart, image-based catheter segmentation is challenging. We propose a cardiac catheter segmentation method in 3-D US data through image processing techniques. Our method first applies a voxel-based classification through newly designed multiscale and multidefinition features, which provide a robust catheter voxel segmentation in 3-D US. Second, a modified catheter model fitting is applied to segment the curved catheter in 3-D US images. The proposed method is validated with extensive experiments, using different in-vitro, ex-vivo, and in-vivo datasets. The proposed method can segment the catheter within an average tip-point error that is smaller than the catheter diameter (1.9 mm) in the volumetric images. Based on automated catheter segmentation and combined with optimal viewing, physicians do not have to interpret US images and can focus on the procedure itself to improve the quality of cardiac intervention.

Original languageEnglish
Article number015001
Number of pages13
JournalJournal of Medical Imaging
Volume6
Issue number1
DOIs
Publication statusPublished - 14 Jan 2019

Fingerprint

Three-Dimensional Imaging
Catheters
Cardiac Catheterization
Physicians
Cardiac Catheters
Radiation
Safety

Keywords

  • catheter segmentation
  • feature fusion
  • intervention guidance
  • model fitting
  • three-dimensional ultrasound

Cite this

@article{4ae2965d9bb4416494d96e0c1a7bf928,
title = "Catheter segmentation in three-dimensional ultrasound images by feature fusion and model fitting",
abstract = "Ultrasound (US) has been increasingly used during interventions, such as cardiac catheterization. To accurately identify the catheter inside US images, extra training for physicians and sonographers is needed. As a consequence, automated segmentation of the catheter in US images and optimized presentation viewing to the physician can be beneficial to accelerate the efficiency and safety of interventions and improve their outcome. For cardiac catheterization, a three-dimensional (3-D) US image is potentially attractive because of no radiation modality and richer spatial information. However, due to a limited spatial resolution of 3-D cardiac US and complex anatomical structures inside the heart, image-based catheter segmentation is challenging. We propose a cardiac catheter segmentation method in 3-D US data through image processing techniques. Our method first applies a voxel-based classification through newly designed multiscale and multidefinition features, which provide a robust catheter voxel segmentation in 3-D US. Second, a modified catheter model fitting is applied to segment the curved catheter in 3-D US images. The proposed method is validated with extensive experiments, using different in-vitro, ex-vivo, and in-vivo datasets. The proposed method can segment the catheter within an average tip-point error that is smaller than the catheter diameter (1.9 mm) in the volumetric images. Based on automated catheter segmentation and combined with optimal viewing, physicians do not have to interpret US images and can focus on the procedure itself to improve the quality of cardiac intervention.",
keywords = "catheter segmentation, feature fusion, intervention guidance, model fitting, three-dimensional ultrasound",
author = "H. Yang and C. Shan and A. Pourtaherian and Kolen, {Alexander F.} and {de With}, P.H.N.",
year = "2019",
month = "1",
day = "14",
doi = "10.1117/1.JMI.6.1.015001",
language = "English",
volume = "6",
journal = "Journal of Medical Imaging",
issn = "2329-4302",
publisher = "SPIE",
number = "1",

}

Catheter segmentation in three-dimensional ultrasound images by feature fusion and model fitting. / Yang, H. (Corresponding author); Shan, C.; Pourtaherian, A.; Kolen, Alexander F.; de With, P.H.N.

In: Journal of Medical Imaging, Vol. 6, No. 1, 015001, 14.01.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Catheter segmentation in three-dimensional ultrasound images by feature fusion and model fitting

AU - Yang, H.

AU - Shan, C.

AU - Pourtaherian, A.

AU - Kolen, Alexander F.

AU - de With, P.H.N.

PY - 2019/1/14

Y1 - 2019/1/14

N2 - Ultrasound (US) has been increasingly used during interventions, such as cardiac catheterization. To accurately identify the catheter inside US images, extra training for physicians and sonographers is needed. As a consequence, automated segmentation of the catheter in US images and optimized presentation viewing to the physician can be beneficial to accelerate the efficiency and safety of interventions and improve their outcome. For cardiac catheterization, a three-dimensional (3-D) US image is potentially attractive because of no radiation modality and richer spatial information. However, due to a limited spatial resolution of 3-D cardiac US and complex anatomical structures inside the heart, image-based catheter segmentation is challenging. We propose a cardiac catheter segmentation method in 3-D US data through image processing techniques. Our method first applies a voxel-based classification through newly designed multiscale and multidefinition features, which provide a robust catheter voxel segmentation in 3-D US. Second, a modified catheter model fitting is applied to segment the curved catheter in 3-D US images. The proposed method is validated with extensive experiments, using different in-vitro, ex-vivo, and in-vivo datasets. The proposed method can segment the catheter within an average tip-point error that is smaller than the catheter diameter (1.9 mm) in the volumetric images. Based on automated catheter segmentation and combined with optimal viewing, physicians do not have to interpret US images and can focus on the procedure itself to improve the quality of cardiac intervention.

AB - Ultrasound (US) has been increasingly used during interventions, such as cardiac catheterization. To accurately identify the catheter inside US images, extra training for physicians and sonographers is needed. As a consequence, automated segmentation of the catheter in US images and optimized presentation viewing to the physician can be beneficial to accelerate the efficiency and safety of interventions and improve their outcome. For cardiac catheterization, a three-dimensional (3-D) US image is potentially attractive because of no radiation modality and richer spatial information. However, due to a limited spatial resolution of 3-D cardiac US and complex anatomical structures inside the heart, image-based catheter segmentation is challenging. We propose a cardiac catheter segmentation method in 3-D US data through image processing techniques. Our method first applies a voxel-based classification through newly designed multiscale and multidefinition features, which provide a robust catheter voxel segmentation in 3-D US. Second, a modified catheter model fitting is applied to segment the curved catheter in 3-D US images. The proposed method is validated with extensive experiments, using different in-vitro, ex-vivo, and in-vivo datasets. The proposed method can segment the catheter within an average tip-point error that is smaller than the catheter diameter (1.9 mm) in the volumetric images. Based on automated catheter segmentation and combined with optimal viewing, physicians do not have to interpret US images and can focus on the procedure itself to improve the quality of cardiac intervention.

KW - catheter segmentation

KW - feature fusion

KW - intervention guidance

KW - model fitting

KW - three-dimensional ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85062693534&partnerID=8YFLogxK

U2 - 10.1117/1.JMI.6.1.015001

DO - 10.1117/1.JMI.6.1.015001

M3 - Article

C2 - 30662926

VL - 6

JO - Journal of Medical Imaging

JF - Journal of Medical Imaging

SN - 2329-4302

IS - 1

M1 - 015001

ER -