Second-order ResU-Net for automatic MRI brain tumor segmentation

Tumor segmentation using magnetic resonance imaging (MRI) plays a significant role in assisting brain tumor diagnosis and treatment. Recently, U-Net architecture with its variants have become prevalent in the field of brain tumor segmentation. However, the existing U-Net models mainly exploit coarse...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ning Sheng, Dongwei Liu, Jianxia Zhang, Chao Che, Jianxin Zhang
Formato:	article
Lenguaje:	EN
Publicado:	AIMS Press 2021
Materias:	brain tumor segmentation second-order statistics u-net residual module Biotechnology TP248.13-248.65 Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/9d33f7d7b37f431c9fcea32d69ab6a53
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9d33f7d7b37f431c9fcea32d69ab6a53
record_format	dspace
spelling	oai:doaj.org-article:9d33f7d7b37f431c9fcea32d69ab6a532021-11-08T02:43:24ZSecond-order ResU-Net for automatic MRI brain tumor segmentation10.3934/mbe.20212511551-0018https://doaj.org/article/9d33f7d7b37f431c9fcea32d69ab6a532021-06-01T00:00:00Zhttp://www.aimspress.com/article/doi/10.3934/mbe.2021251?viewType=HTMLhttps://doaj.org/toc/1551-0018Tumor segmentation using magnetic resonance imaging (MRI) plays a significant role in assisting brain tumor diagnosis and treatment. Recently, U-Net architecture with its variants have become prevalent in the field of brain tumor segmentation. However, the existing U-Net models mainly exploit coarse first-order features for tumor segmentation, and they seldom consider the more powerful second-order statistics of deep features. Therefore, in this work, we aim to explore the effectiveness of second-order statistical features for brain tumor segmentation application, and further propose a novel second-order residual brain tumor segmentation network, i.e., SoResU-Net. SoResU-Net utilizes a number of second-order modules to replace the original skip connection operations, thus augmenting the series of transformation operations and increasing the non-linearity of the segmentation network. Extensive experimental results on the BraTS 2018 and BraTS 2019 datasets demonstrate that SoResU-Net outperforms its baseline, especially on core tumor and enhancing tumor segmentation, illuminating the effectiveness of second-order statistical features for the brain tumor segmentation application.Ning ShengDongwei LiuJianxia Zhang Chao CheJianxin ZhangAIMS Pressarticlebrain tumor segmentationsecond-order statisticsu-netresidual moduleBiotechnologyTP248.13-248.65MathematicsQA1-939ENMathematical Biosciences and Engineering, Vol 18, Iss 5, Pp 4943-4960 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	brain tumor segmentation second-order statistics u-net residual module Biotechnology TP248.13-248.65 Mathematics QA1-939
spellingShingle	brain tumor segmentation second-order statistics u-net residual module Biotechnology TP248.13-248.65 Mathematics QA1-939 Ning Sheng Dongwei Liu Jianxia Zhang Chao Che Jianxin Zhang Second-order ResU-Net for automatic MRI brain tumor segmentation
description	Tumor segmentation using magnetic resonance imaging (MRI) plays a significant role in assisting brain tumor diagnosis and treatment. Recently, U-Net architecture with its variants have become prevalent in the field of brain tumor segmentation. However, the existing U-Net models mainly exploit coarse first-order features for tumor segmentation, and they seldom consider the more powerful second-order statistics of deep features. Therefore, in this work, we aim to explore the effectiveness of second-order statistical features for brain tumor segmentation application, and further propose a novel second-order residual brain tumor segmentation network, i.e., SoResU-Net. SoResU-Net utilizes a number of second-order modules to replace the original skip connection operations, thus augmenting the series of transformation operations and increasing the non-linearity of the segmentation network. Extensive experimental results on the BraTS 2018 and BraTS 2019 datasets demonstrate that SoResU-Net outperforms its baseline, especially on core tumor and enhancing tumor segmentation, illuminating the effectiveness of second-order statistical features for the brain tumor segmentation application.
format	article
author	Ning Sheng Dongwei Liu Jianxia Zhang Chao Che Jianxin Zhang
author_facet	Ning Sheng Dongwei Liu Jianxia Zhang Chao Che Jianxin Zhang
author_sort	Ning Sheng
title	Second-order ResU-Net for automatic MRI brain tumor segmentation
title_short	Second-order ResU-Net for automatic MRI brain tumor segmentation
title_full	Second-order ResU-Net for automatic MRI brain tumor segmentation
title_fullStr	Second-order ResU-Net for automatic MRI brain tumor segmentation
title_full_unstemmed	Second-order ResU-Net for automatic MRI brain tumor segmentation
title_sort	second-order resu-net for automatic mri brain tumor segmentation
publisher	AIMS Press
publishDate	2021
url	https://doaj.org/article/9d33f7d7b37f431c9fcea32d69ab6a53
work_keys_str_mv	AT ningsheng secondorderresunetforautomaticmribraintumorsegmentation AT dongweiliu secondorderresunetforautomaticmribraintumorsegmentation AT jianxiazhang secondorderresunetforautomaticmribraintumorsegmentation AT chaoche secondorderresunetforautomaticmribraintumorsegmentation AT jianxinzhang secondorderresunetforautomaticmribraintumorsegmentation
_version_	1718443026247843840

Second-order ResU-Net for automatic MRI brain tumor segmentation

Ejemplares similares