Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.

Ultrasound segmentation is a challenging problem due to the inherent speckle and some artifacts like shadows, attenuation and signal dropout. Existing methods need to include strong priors like shape priors or analytical intensity models to succeed in the segmentation. However, such priors tend to l...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Anca Ciurte, Xavier Bresson, Olivier Cuisenaire, Nawal Houhou, Sergiu Nedevschi, Jean-Philippe Thiran, Meritxell Bach Cuadra
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2014
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f945a5e1db33426b855324143ca4c36d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f945a5e1db33426b855324143ca4c36d
record_format	dspace
spelling	oai:doaj.org-article:f945a5e1db33426b855324143ca4c36d2021-11-25T06:08:58ZSemi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.1932-620310.1371/journal.pone.0100972https://doaj.org/article/f945a5e1db33426b855324143ca4c36d2014-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/25010530/?tool=EBIhttps://doaj.org/toc/1932-6203Ultrasound segmentation is a challenging problem due to the inherent speckle and some artifacts like shadows, attenuation and signal dropout. Existing methods need to include strong priors like shape priors or analytical intensity models to succeed in the segmentation. However, such priors tend to limit these methods to a specific target or imaging settings, and they are not always applicable to pathological cases. This work introduces a semi-supervised segmentation framework for ultrasound imaging that alleviates the limitation of fully automatic segmentation, that is, it is applicable to any kind of target and imaging settings. Our methodology uses a graph of image patches to represent the ultrasound image and user-assisted initialization with labels, which acts as soft priors. The segmentation problem is formulated as a continuous minimum cut problem and solved with an efficient optimization algorithm. We validate our segmentation framework on clinical ultrasound imaging (prostate, fetus, and tumors of the liver and eye). We obtain high similarity agreement with the ground truth provided by medical expert delineations in all applications (94% DICE values in average) and the proposed algorithm performs favorably with the literature.Anca CiurteXavier BressonOlivier CuisenaireNawal HouhouSergiu NedevschiJean-Philippe ThiranMeritxell Bach CuadraPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 9, Iss 7, p e100972 (2014)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Anca Ciurte Xavier Bresson Olivier Cuisenaire Nawal Houhou Sergiu Nedevschi Jean-Philippe Thiran Meritxell Bach Cuadra Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
description	Ultrasound segmentation is a challenging problem due to the inherent speckle and some artifacts like shadows, attenuation and signal dropout. Existing methods need to include strong priors like shape priors or analytical intensity models to succeed in the segmentation. However, such priors tend to limit these methods to a specific target or imaging settings, and they are not always applicable to pathological cases. This work introduces a semi-supervised segmentation framework for ultrasound imaging that alleviates the limitation of fully automatic segmentation, that is, it is applicable to any kind of target and imaging settings. Our methodology uses a graph of image patches to represent the ultrasound image and user-assisted initialization with labels, which acts as soft priors. The segmentation problem is formulated as a continuous minimum cut problem and solved with an efficient optimization algorithm. We validate our segmentation framework on clinical ultrasound imaging (prostate, fetus, and tumors of the liver and eye). We obtain high similarity agreement with the ground truth provided by medical expert delineations in all applications (94% DICE values in average) and the proposed algorithm performs favorably with the literature.
format	article
author	Anca Ciurte Xavier Bresson Olivier Cuisenaire Nawal Houhou Sergiu Nedevschi Jean-Philippe Thiran Meritxell Bach Cuadra
author_facet	Anca Ciurte Xavier Bresson Olivier Cuisenaire Nawal Houhou Sergiu Nedevschi Jean-Philippe Thiran Meritxell Bach Cuadra
author_sort	Anca Ciurte
title	Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
title_short	Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
title_full	Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
title_fullStr	Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
title_full_unstemmed	Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
title_sort	semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
publisher	Public Library of Science (PLoS)
publishDate	2014
url	https://doaj.org/article/f945a5e1db33426b855324143ca4c36d
work_keys_str_mv	AT ancaciurte semisupervisedsegmentationofultrasoundimagesbasedonpatchrepresentationandcontinuousmincut AT xavierbresson semisupervisedsegmentationofultrasoundimagesbasedonpatchrepresentationandcontinuousmincut AT oliviercuisenaire semisupervisedsegmentationofultrasoundimagesbasedonpatchrepresentationandcontinuousmincut AT nawalhouhou semisupervisedsegmentationofultrasoundimagesbasedonpatchrepresentationandcontinuousmincut AT sergiunedevschi semisupervisedsegmentationofultrasoundimagesbasedonpatchrepresentationandcontinuousmincut AT jeanphilippethiran semisupervisedsegmentationofultrasoundimagesbasedonpatchrepresentationandcontinuousmincut AT meritxellbachcuadra semisupervisedsegmentationofultrasoundimagesbasedonpatchrepresentationandcontinuousmincut
_version_	1718414140207267840

Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.

Ejemplares similares