Using manifold learning for atlas selection in multi-atlas segmentation.

Multi-atlas segmentation has been widely used to segment various anatomical structures. The success of this technique partly relies on the selection of atlases that are best mapped to a new target image after registration. Recently, manifold learning has been proposed as a method for atlas selection...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Albert K Hoang Duc, Marc Modat, Kelvin K Leung, M Jorge Cardoso, Josephine Barnes, Timor Kadir, Sébastien Ourselin, Alzheimer’s Disease Neuroimaging Initiative
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2013
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/ab9490bb40ea451eba6a2f67dc11cada
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ab9490bb40ea451eba6a2f67dc11cada
record_format	dspace
spelling	oai:doaj.org-article:ab9490bb40ea451eba6a2f67dc11cada2021-11-18T09:01:32ZUsing manifold learning for atlas selection in multi-atlas segmentation.1932-620310.1371/journal.pone.0070059https://doaj.org/article/ab9490bb40ea451eba6a2f67dc11cada2013-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/23936376/pdf/?tool=EBIhttps://doaj.org/toc/1932-6203Multi-atlas segmentation has been widely used to segment various anatomical structures. The success of this technique partly relies on the selection of atlases that are best mapped to a new target image after registration. Recently, manifold learning has been proposed as a method for atlas selection. Each manifold learning technique seeks to optimize a unique objective function. Therefore, different techniques produce different embeddings even when applied to the same data set. Previous studies used a single technique in their method and gave no reason for the choice of the manifold learning technique employed nor the theoretical grounds for the choice of the manifold parameters. In this study, we compare side-by-side the results given by 3 manifold learning techniques (Isomap, Laplacian Eigenmaps and Locally Linear Embedding) on the same data set. We assess the ability of those 3 different techniques to select the best atlases to combine in the framework of multi-atlas segmentation. First, a leave-one-out experiment is used to optimize our method on a set of 110 manually segmented atlases of hippocampi and find the manifold learning technique and associated manifold parameters that give the best segmentation accuracy. Then, the optimal parameters are used to automatically segment 30 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). For our dataset, the selection of atlases with Locally Linear Embedding gives the best results. Our findings show that selection of atlases with manifold learning leads to segmentation accuracy close to or significantly higher than the state-of-the-art method and that accuracy can be increased by fine tuning the manifold learning process.Albert K Hoang DucMarc ModatKelvin K LeungM Jorge CardosoJosephine BarnesTimor KadirSébastien OurselinAlzheimer’s Disease Neuroimaging InitiativePublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 8, Iss 8, p e70059 (2013)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Albert K Hoang Duc Marc Modat Kelvin K Leung M Jorge Cardoso Josephine Barnes Timor Kadir Sébastien Ourselin Alzheimer’s Disease Neuroimaging Initiative Using manifold learning for atlas selection in multi-atlas segmentation.
description	Multi-atlas segmentation has been widely used to segment various anatomical structures. The success of this technique partly relies on the selection of atlases that are best mapped to a new target image after registration. Recently, manifold learning has been proposed as a method for atlas selection. Each manifold learning technique seeks to optimize a unique objective function. Therefore, different techniques produce different embeddings even when applied to the same data set. Previous studies used a single technique in their method and gave no reason for the choice of the manifold learning technique employed nor the theoretical grounds for the choice of the manifold parameters. In this study, we compare side-by-side the results given by 3 manifold learning techniques (Isomap, Laplacian Eigenmaps and Locally Linear Embedding) on the same data set. We assess the ability of those 3 different techniques to select the best atlases to combine in the framework of multi-atlas segmentation. First, a leave-one-out experiment is used to optimize our method on a set of 110 manually segmented atlases of hippocampi and find the manifold learning technique and associated manifold parameters that give the best segmentation accuracy. Then, the optimal parameters are used to automatically segment 30 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). For our dataset, the selection of atlases with Locally Linear Embedding gives the best results. Our findings show that selection of atlases with manifold learning leads to segmentation accuracy close to or significantly higher than the state-of-the-art method and that accuracy can be increased by fine tuning the manifold learning process.
format	article
author	Albert K Hoang Duc Marc Modat Kelvin K Leung M Jorge Cardoso Josephine Barnes Timor Kadir Sébastien Ourselin Alzheimer’s Disease Neuroimaging Initiative
author_facet	Albert K Hoang Duc Marc Modat Kelvin K Leung M Jorge Cardoso Josephine Barnes Timor Kadir Sébastien Ourselin Alzheimer’s Disease Neuroimaging Initiative
author_sort	Albert K Hoang Duc
title	Using manifold learning for atlas selection in multi-atlas segmentation.
title_short	Using manifold learning for atlas selection in multi-atlas segmentation.
title_full	Using manifold learning for atlas selection in multi-atlas segmentation.
title_fullStr	Using manifold learning for atlas selection in multi-atlas segmentation.
title_full_unstemmed	Using manifold learning for atlas selection in multi-atlas segmentation.
title_sort	using manifold learning for atlas selection in multi-atlas segmentation.
publisher	Public Library of Science (PLoS)
publishDate	2013
url	https://doaj.org/article/ab9490bb40ea451eba6a2f67dc11cada
work_keys_str_mv	AT albertkhoangduc usingmanifoldlearningforatlasselectioninmultiatlassegmentation AT marcmodat usingmanifoldlearningforatlasselectioninmultiatlassegmentation AT kelvinkleung usingmanifoldlearningforatlasselectioninmultiatlassegmentation AT mjorgecardoso usingmanifoldlearningforatlasselectioninmultiatlassegmentation AT josephinebarnes usingmanifoldlearningforatlasselectioninmultiatlassegmentation AT timorkadir usingmanifoldlearningforatlasselectioninmultiatlassegmentation AT sebastienourselin usingmanifoldlearningforatlasselectioninmultiatlassegmentation AT alzheimersdiseaseneuroimaginginitiative usingmanifoldlearningforatlasselectioninmultiatlassegmentation
_version_	1718421042064523264

Using manifold learning for atlas selection in multi-atlas segmentation.

Ejemplares similares