Automatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)

Abstract In this paper, we present an original multiple atlases level set framework (MALSF) for automatic, accurate and robust thalamus segmentation in magnetic resonance images (MRI). The contributions of the MALSF method are twofold. First, the main technical contribution is a novel label fusion s...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Minghui Zhang, Zhentai Lu, Qianjin Feng, Yu Zhang
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2017
Materias:
R
Q
Acceso en línea:https://doaj.org/article/08dcd9bf2dba4f949fe3233d2c39b03c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:08dcd9bf2dba4f949fe3233d2c39b03c
record_format dspace
spelling oai:doaj.org-article:08dcd9bf2dba4f949fe3233d2c39b03c2021-12-02T12:32:39ZAutomatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)10.1038/s41598-017-04276-62045-2322https://doaj.org/article/08dcd9bf2dba4f949fe3233d2c39b03c2017-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-04276-6https://doaj.org/toc/2045-2322Abstract In this paper, we present an original multiple atlases level set framework (MALSF) for automatic, accurate and robust thalamus segmentation in magnetic resonance images (MRI). The contributions of the MALSF method are twofold. First, the main technical contribution is a novel label fusion strategy in the level set framework. Label fusion is achieved by seeking an optimal level set function that minimizes energy functional with three terms: label fusion term, image based term, and regularization term. This strategy integrates shape prior, image information and the regularity of the thalamus. Second, we use propagated labels from multiple registration methods with different parameters to take full advantage of the complementary information of different registration methods. Since different registration methods and different atlases can yield complementary information, multiple registration and multiple atlases can be incorporated into the level set framework to improve the segmentation performance. Experiments have shown that the MALSF method can improve the segmentation accuracy for the thalamus. Compared to ground truth segmentation, the mean Dice metrics of our method are 0.9239 and 0.9200 for left and right thalamus.Minghui ZhangZhentai LuQianjin FengYu ZhangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-12 (2017)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Minghui Zhang
Zhentai Lu
Qianjin Feng
Yu Zhang
Automatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)
description Abstract In this paper, we present an original multiple atlases level set framework (MALSF) for automatic, accurate and robust thalamus segmentation in magnetic resonance images (MRI). The contributions of the MALSF method are twofold. First, the main technical contribution is a novel label fusion strategy in the level set framework. Label fusion is achieved by seeking an optimal level set function that minimizes energy functional with three terms: label fusion term, image based term, and regularization term. This strategy integrates shape prior, image information and the regularity of the thalamus. Second, we use propagated labels from multiple registration methods with different parameters to take full advantage of the complementary information of different registration methods. Since different registration methods and different atlases can yield complementary information, multiple registration and multiple atlases can be incorporated into the level set framework to improve the segmentation performance. Experiments have shown that the MALSF method can improve the segmentation accuracy for the thalamus. Compared to ground truth segmentation, the mean Dice metrics of our method are 0.9239 and 0.9200 for left and right thalamus.
format article
author Minghui Zhang
Zhentai Lu
Qianjin Feng
Yu Zhang
author_facet Minghui Zhang
Zhentai Lu
Qianjin Feng
Yu Zhang
author_sort Minghui Zhang
title Automatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)
title_short Automatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)
title_full Automatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)
title_fullStr Automatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)
title_full_unstemmed Automatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)
title_sort automatic thalamus segmentation from magnetic resonance images using multiple atlases level set framework (malsf)
publisher Nature Portfolio
publishDate 2017
url https://doaj.org/article/08dcd9bf2dba4f949fe3233d2c39b03c
work_keys_str_mv AT minghuizhang automaticthalamussegmentationfrommagneticresonanceimagesusingmultipleatlaseslevelsetframeworkmalsf
AT zhentailu automaticthalamussegmentationfrommagneticresonanceimagesusingmultipleatlaseslevelsetframeworkmalsf
AT qianjinfeng automaticthalamussegmentationfrommagneticresonanceimagesusingmultipleatlaseslevelsetframeworkmalsf
AT yuzhang automaticthalamussegmentationfrommagneticresonanceimagesusingmultipleatlaseslevelsetframeworkmalsf
_version_ 1718393959408992256