Nested graph cut for automatic segmentation of high-frequency ultrasound images of the Mouse Embryo

Jen Wei Kuo, Jonathan Mamou, Orlando Aristizábal, Xuan Zhao, Jeffrey A. Ketterling, Yao Wang

Research output: Contribution to journalArticle

Abstract

We propose a fully automatic segmentation method called nested graph cut to segment images (2D or 3D) that contain multiple objects with a nested structure. Compared to other graphcut- based methods developed for multiple regions, our method can work well for nested objects without requiring manual selection of initial seeds, even if different objects have similar intensity distributions and some object boundaries are missing. Promising results were obtained for separating the brain ventricles, the head, and the uterus region in the mouse-embryo head images obtained using high-frequency ultrasound imaging. The proposed method achieved mean Dice similarity coefficients of 0.87 ± 0.04 and 0.89 ± 0.06 for segmenting BVs and the head, respectively, compared to manual segmentation results by experts on 40 3D images over five gestation stages.

Original languageEnglish (US)
Article number2477395
Pages (from-to)427-441
Number of pages15
JournalIEEE Transactions on Medical Imaging
Volume35
Issue number2
DOIs
StatePublished - Feb 1 2016

Fingerprint

Brain
Embryonic Structures
Ultrasonics
Imaging techniques
Head
Uterus
Ultrasonography
Pregnancy

Keywords

  • Graph cut
  • High-frequency ultrasound
  • Mouse embryo
  • Multi-object
  • Nested structure
  • Segmentation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software

Cite this

Nested graph cut for automatic segmentation of high-frequency ultrasound images of the Mouse Embryo. / Kuo, Jen Wei; Mamou, Jonathan; Aristizábal, Orlando; Zhao, Xuan; Ketterling, Jeffrey A.; Wang, Yao.

In: IEEE Transactions on Medical Imaging, Vol. 35, No. 2, 2477395, 01.02.2016, p. 427-441.

Research output: Contribution to journalArticle

Kuo, Jen Wei ; Mamou, Jonathan ; Aristizábal, Orlando ; Zhao, Xuan ; Ketterling, Jeffrey A. ; Wang, Yao. / Nested graph cut for automatic segmentation of high-frequency ultrasound images of the Mouse Embryo. In: IEEE Transactions on Medical Imaging. 2016 ; Vol. 35, No. 2. pp. 427-441.
@article{35a5eedaf928423ca2ea0c4b5363c908,
title = "Nested graph cut for automatic segmentation of high-frequency ultrasound images of the Mouse Embryo",
abstract = "We propose a fully automatic segmentation method called nested graph cut to segment images (2D or 3D) that contain multiple objects with a nested structure. Compared to other graphcut- based methods developed for multiple regions, our method can work well for nested objects without requiring manual selection of initial seeds, even if different objects have similar intensity distributions and some object boundaries are missing. Promising results were obtained for separating the brain ventricles, the head, and the uterus region in the mouse-embryo head images obtained using high-frequency ultrasound imaging. The proposed method achieved mean Dice similarity coefficients of 0.87 ± 0.04 and 0.89 ± 0.06 for segmenting BVs and the head, respectively, compared to manual segmentation results by experts on 40 3D images over five gestation stages.",
keywords = "Graph cut, High-frequency ultrasound, Mouse embryo, Multi-object, Nested structure, Segmentation",
author = "Kuo, {Jen Wei} and Jonathan Mamou and Orlando Aristiz{\'a}bal and Xuan Zhao and Ketterling, {Jeffrey A.} and Yao Wang",
year = "2016",
month = "2",
day = "1",
doi = "10.1109/TMI.2015.2477395",
language = "English (US)",
volume = "35",
pages = "427--441",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Nested graph cut for automatic segmentation of high-frequency ultrasound images of the Mouse Embryo

AU - Kuo, Jen Wei

AU - Mamou, Jonathan

AU - Aristizábal, Orlando

AU - Zhao, Xuan

AU - Ketterling, Jeffrey A.

AU - Wang, Yao

PY - 2016/2/1

Y1 - 2016/2/1

N2 - We propose a fully automatic segmentation method called nested graph cut to segment images (2D or 3D) that contain multiple objects with a nested structure. Compared to other graphcut- based methods developed for multiple regions, our method can work well for nested objects without requiring manual selection of initial seeds, even if different objects have similar intensity distributions and some object boundaries are missing. Promising results were obtained for separating the brain ventricles, the head, and the uterus region in the mouse-embryo head images obtained using high-frequency ultrasound imaging. The proposed method achieved mean Dice similarity coefficients of 0.87 ± 0.04 and 0.89 ± 0.06 for segmenting BVs and the head, respectively, compared to manual segmentation results by experts on 40 3D images over five gestation stages.

AB - We propose a fully automatic segmentation method called nested graph cut to segment images (2D or 3D) that contain multiple objects with a nested structure. Compared to other graphcut- based methods developed for multiple regions, our method can work well for nested objects without requiring manual selection of initial seeds, even if different objects have similar intensity distributions and some object boundaries are missing. Promising results were obtained for separating the brain ventricles, the head, and the uterus region in the mouse-embryo head images obtained using high-frequency ultrasound imaging. The proposed method achieved mean Dice similarity coefficients of 0.87 ± 0.04 and 0.89 ± 0.06 for segmenting BVs and the head, respectively, compared to manual segmentation results by experts on 40 3D images over five gestation stages.

KW - Graph cut

KW - High-frequency ultrasound

KW - Mouse embryo

KW - Multi-object

KW - Nested structure

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84959346304&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959346304&partnerID=8YFLogxK

U2 - 10.1109/TMI.2015.2477395

DO - 10.1109/TMI.2015.2477395

M3 - Article

C2 - 26357396

AN - SCOPUS:84959346304

VL - 35

SP - 427

EP - 441

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 2

M1 - 2477395

ER -