Methods for 2-D and 3-D Endobronchial Ultrasound Image Segmentation

Xiaonan Zang, Rebecca Bascom, Christopher Gilbert, Jennifer Toth, William Higgins

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Endobronchial ultrasound (EBUS) is now commonly used for cancer-staging bronchoscopy. Unfortunately, EBUS is challenging to use and interpreting EBUS video sequences is difficult. Other ultrasound imaging domains, hampered by related difficulties, have benefited from computer-based image-segmentation methods. Yet, so far, no such methods have been proposed for EBUS. We propose image-segmentation methods for 2-D EBUS frames and 3-D EBUS sequences. Our 2-D method adapts the fast-marching level-set process, anisotropic diffusion, and region growing to the problem of segmenting 2-D EBUS frames. Our 3-D method builds upon the 2-D method while also incorporating the geodesic level-set process for segmenting EBUS sequences. Tests with lung-cancer patient data showed that the methods ran fully automatically for nearly 80% of test cases. For the remaining cases, the only user-interaction required was the selection of a seed point. When compared to ground-truth segmentations, the 2-D method achieved an overall Dice index = 90.0% ± 4.9%, while the 3-D method achieved an overall Dice index = 83.9 ± 6.0%. In addition, the computation time (2-D, 0.070 s/frame; 3-D, 0.088 s/frame) was two orders of magnitude faster than interactive contour definition. Finally, we demonstrate the potential of the methods for EBUS localization in a multimodal image-guided bronchoscopy system.

Original languageEnglish (US)
Article number7307143
Pages (from-to)1426-1439
Number of pages14
JournalIEEE Transactions on Biomedical Engineering
Volume63
Issue number7
DOIs
StatePublished - Jul 2016

Fingerprint

Image segmentation
Ultrasonics
Seed
Imaging techniques

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

@article{918611c4241f4e1e8e7e25e2ca754b4f,
title = "Methods for 2-D and 3-D Endobronchial Ultrasound Image Segmentation",
abstract = "Endobronchial ultrasound (EBUS) is now commonly used for cancer-staging bronchoscopy. Unfortunately, EBUS is challenging to use and interpreting EBUS video sequences is difficult. Other ultrasound imaging domains, hampered by related difficulties, have benefited from computer-based image-segmentation methods. Yet, so far, no such methods have been proposed for EBUS. We propose image-segmentation methods for 2-D EBUS frames and 3-D EBUS sequences. Our 2-D method adapts the fast-marching level-set process, anisotropic diffusion, and region growing to the problem of segmenting 2-D EBUS frames. Our 3-D method builds upon the 2-D method while also incorporating the geodesic level-set process for segmenting EBUS sequences. Tests with lung-cancer patient data showed that the methods ran fully automatically for nearly 80{\%} of test cases. For the remaining cases, the only user-interaction required was the selection of a seed point. When compared to ground-truth segmentations, the 2-D method achieved an overall Dice index = 90.0{\%} ± 4.9{\%}, while the 3-D method achieved an overall Dice index = 83.9 ± 6.0{\%}. In addition, the computation time (2-D, 0.070 s/frame; 3-D, 0.088 s/frame) was two orders of magnitude faster than interactive contour definition. Finally, we demonstrate the potential of the methods for EBUS localization in a multimodal image-guided bronchoscopy system.",
author = "Xiaonan Zang and Rebecca Bascom and Christopher Gilbert and Jennifer Toth and William Higgins",
year = "2016",
month = "7",
doi = "10.1109/TBME.2015.2494838",
language = "English (US)",
volume = "63",
pages = "1426--1439",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "7",

}

Methods for 2-D and 3-D Endobronchial Ultrasound Image Segmentation. / Zang, Xiaonan; Bascom, Rebecca; Gilbert, Christopher; Toth, Jennifer; Higgins, William.

In: IEEE Transactions on Biomedical Engineering, Vol. 63, No. 7, 7307143, 07.2016, p. 1426-1439.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Methods for 2-D and 3-D Endobronchial Ultrasound Image Segmentation

AU - Zang, Xiaonan

AU - Bascom, Rebecca

AU - Gilbert, Christopher

AU - Toth, Jennifer

AU - Higgins, William

PY - 2016/7

Y1 - 2016/7

N2 - Endobronchial ultrasound (EBUS) is now commonly used for cancer-staging bronchoscopy. Unfortunately, EBUS is challenging to use and interpreting EBUS video sequences is difficult. Other ultrasound imaging domains, hampered by related difficulties, have benefited from computer-based image-segmentation methods. Yet, so far, no such methods have been proposed for EBUS. We propose image-segmentation methods for 2-D EBUS frames and 3-D EBUS sequences. Our 2-D method adapts the fast-marching level-set process, anisotropic diffusion, and region growing to the problem of segmenting 2-D EBUS frames. Our 3-D method builds upon the 2-D method while also incorporating the geodesic level-set process for segmenting EBUS sequences. Tests with lung-cancer patient data showed that the methods ran fully automatically for nearly 80% of test cases. For the remaining cases, the only user-interaction required was the selection of a seed point. When compared to ground-truth segmentations, the 2-D method achieved an overall Dice index = 90.0% ± 4.9%, while the 3-D method achieved an overall Dice index = 83.9 ± 6.0%. In addition, the computation time (2-D, 0.070 s/frame; 3-D, 0.088 s/frame) was two orders of magnitude faster than interactive contour definition. Finally, we demonstrate the potential of the methods for EBUS localization in a multimodal image-guided bronchoscopy system.

AB - Endobronchial ultrasound (EBUS) is now commonly used for cancer-staging bronchoscopy. Unfortunately, EBUS is challenging to use and interpreting EBUS video sequences is difficult. Other ultrasound imaging domains, hampered by related difficulties, have benefited from computer-based image-segmentation methods. Yet, so far, no such methods have been proposed for EBUS. We propose image-segmentation methods for 2-D EBUS frames and 3-D EBUS sequences. Our 2-D method adapts the fast-marching level-set process, anisotropic diffusion, and region growing to the problem of segmenting 2-D EBUS frames. Our 3-D method builds upon the 2-D method while also incorporating the geodesic level-set process for segmenting EBUS sequences. Tests with lung-cancer patient data showed that the methods ran fully automatically for nearly 80% of test cases. For the remaining cases, the only user-interaction required was the selection of a seed point. When compared to ground-truth segmentations, the 2-D method achieved an overall Dice index = 90.0% ± 4.9%, while the 3-D method achieved an overall Dice index = 83.9 ± 6.0%. In addition, the computation time (2-D, 0.070 s/frame; 3-D, 0.088 s/frame) was two orders of magnitude faster than interactive contour definition. Finally, we demonstrate the potential of the methods for EBUS localization in a multimodal image-guided bronchoscopy system.

UR - http://www.scopus.com/inward/record.url?scp=84978150729&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978150729&partnerID=8YFLogxK

U2 - 10.1109/TBME.2015.2494838

DO - 10.1109/TBME.2015.2494838

M3 - Article

C2 - 26529748

AN - SCOPUS:84978150729

VL - 63

SP - 1426

EP - 1439

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 7

M1 - 7307143

ER -