Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images

Abstract Liver segmentation is an essential procedure in computer-assisted surgery, radiotherapy, and volume measurement. It is still a challenging task to extract liver tissue from 3D CT images owing to nearby organs with similar intensities. In this paper, an automatic approach integrating multi-d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xuesong Lu, Qinlan Xie, Yunfei Zha, Defeng Wang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/dab462a1c5404c81a853b6e1c93605f0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dab462a1c5404c81a853b6e1c93605f0
record_format	dspace
spelling	oai:doaj.org-article:dab462a1c5404c81a853b6e1c93605f02021-12-02T16:08:25ZFully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images10.1038/s41598-018-28787-y2045-2322https://doaj.org/article/dab462a1c5404c81a853b6e1c93605f02018-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-28787-yhttps://doaj.org/toc/2045-2322Abstract Liver segmentation is an essential procedure in computer-assisted surgery, radiotherapy, and volume measurement. It is still a challenging task to extract liver tissue from 3D CT images owing to nearby organs with similar intensities. In this paper, an automatic approach integrating multi-dimensional features into graph cut refinement is developed and validated. Multi-atlas segmentation is utilized to estimate the coarse shape of liver on the target image. The unsigned distance field based on initial shape is then calculated throughout the whole image, which aims at automatic graph construction during refinement procedure. Finally, multi-dimensional features and shape constraints are embedded into graph cut framework. The optimal liver region can be precisely detected with a minimal cost. The proposed technique is evaluated on 40 CT scans, obtained from two public databases Sliver07 and 3Dircadb1. The dataset Sliver07 is considered as the training set for parameter learning. On the dataset 3Dircadb1, the average of volume overlap is up to 94%. The experiment results indicate that the proposed method has ability to reach the desired boundary of liver and has potential value for clinical application.Xuesong LuQinlan XieYunfei ZhaDefeng WangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-9 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Xuesong Lu Qinlan Xie Yunfei Zha Defeng Wang Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images
description	Abstract Liver segmentation is an essential procedure in computer-assisted surgery, radiotherapy, and volume measurement. It is still a challenging task to extract liver tissue from 3D CT images owing to nearby organs with similar intensities. In this paper, an automatic approach integrating multi-dimensional features into graph cut refinement is developed and validated. Multi-atlas segmentation is utilized to estimate the coarse shape of liver on the target image. The unsigned distance field based on initial shape is then calculated throughout the whole image, which aims at automatic graph construction during refinement procedure. Finally, multi-dimensional features and shape constraints are embedded into graph cut framework. The optimal liver region can be precisely detected with a minimal cost. The proposed technique is evaluated on 40 CT scans, obtained from two public databases Sliver07 and 3Dircadb1. The dataset Sliver07 is considered as the training set for parameter learning. On the dataset 3Dircadb1, the average of volume overlap is up to 94%. The experiment results indicate that the proposed method has ability to reach the desired boundary of liver and has potential value for clinical application.
format	article
author	Xuesong Lu Qinlan Xie Yunfei Zha Defeng Wang
author_facet	Xuesong Lu Qinlan Xie Yunfei Zha Defeng Wang
author_sort	Xuesong Lu
title	Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images
title_short	Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images
title_full	Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images
title_fullStr	Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images
title_full_unstemmed	Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images
title_sort	fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3d ct images
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/dab462a1c5404c81a853b6e1c93605f0
work_keys_str_mv	AT xuesonglu fullyautomaticliversegmentationcombiningmultidimensionalgraphcutwithshapeinformationin3dctimages AT qinlanxie fullyautomaticliversegmentationcombiningmultidimensionalgraphcutwithshapeinformationin3dctimages AT yunfeizha fullyautomaticliversegmentationcombiningmultidimensionalgraphcutwithshapeinformationin3dctimages AT defengwang fullyautomaticliversegmentationcombiningmultidimensionalgraphcutwithshapeinformationin3dctimages
_version_	1718384501175877632

Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images

Ejemplares similares