Cargando…

CAU-Net: A Deep Learning Method for Deep Gray Matter Nuclei Segmentation

The abnormal iron deposition of the deep gray matter nuclei is related to many neurological diseases. With the quantitative susceptibility mapping (QSM) technique, it is possible to quantitatively measure the brain iron content in vivo. To assess the magnetic susceptibility of the deep gray matter n...

Descripción completa

Detalles Bibliográficos
Autores principales: Chai, Chao, Wu, Mengran, Wang, Huiying, Cheng, Yue, Zhang, Shengtong, Zhang, Kun, Shen, Wen, Liu, Zhiyang, Xia, Shuang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9204516/
https://www.ncbi.nlm.nih.gov/pubmed/35720705
http://dx.doi.org/10.3389/fnins.2022.918623
_version_ 1784728943721447424
author Chai, Chao
Wu, Mengran
Wang, Huiying
Cheng, Yue
Zhang, Shengtong
Zhang, Kun
Shen, Wen
Liu, Zhiyang
Xia, Shuang
author_facet Chai, Chao
Wu, Mengran
Wang, Huiying
Cheng, Yue
Zhang, Shengtong
Zhang, Kun
Shen, Wen
Liu, Zhiyang
Xia, Shuang
author_sort Chai, Chao
collection PubMed
description The abnormal iron deposition of the deep gray matter nuclei is related to many neurological diseases. With the quantitative susceptibility mapping (QSM) technique, it is possible to quantitatively measure the brain iron content in vivo. To assess the magnetic susceptibility of the deep gray matter nuclei in the QSM, it is mandatory to segment the nuclei of interest first, and many automatic methods have been proposed in the literature. This study proposed a contrast attention U-Net for nuclei segmentation and evaluated its performance on two datasets acquired using different sequences with different parameters from different MRI devices. Experimental results revealed that our proposed method was superior on both datasets over other commonly adopted network structures. The impacts of training and inference strategies were also discussed, which showed that adopting test time augmentation during the inference stage can impose an obvious improvement. At the training stage, our results indicated that sufficient data augmentation, deep supervision, and nonuniform patch sampling contributed significantly to improving the segmentation accuracy, which indicated that appropriate choices of training and inference strategies were at least as important as designing more advanced network structures.
format Online
Article
Text
id pubmed-9204516
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-92045162022-06-18 CAU-Net: A Deep Learning Method for Deep Gray Matter Nuclei Segmentation Chai, Chao Wu, Mengran Wang, Huiying Cheng, Yue Zhang, Shengtong Zhang, Kun Shen, Wen Liu, Zhiyang Xia, Shuang Front Neurosci Neuroscience The abnormal iron deposition of the deep gray matter nuclei is related to many neurological diseases. With the quantitative susceptibility mapping (QSM) technique, it is possible to quantitatively measure the brain iron content in vivo. To assess the magnetic susceptibility of the deep gray matter nuclei in the QSM, it is mandatory to segment the nuclei of interest first, and many automatic methods have been proposed in the literature. This study proposed a contrast attention U-Net for nuclei segmentation and evaluated its performance on two datasets acquired using different sequences with different parameters from different MRI devices. Experimental results revealed that our proposed method was superior on both datasets over other commonly adopted network structures. The impacts of training and inference strategies were also discussed, which showed that adopting test time augmentation during the inference stage can impose an obvious improvement. At the training stage, our results indicated that sufficient data augmentation, deep supervision, and nonuniform patch sampling contributed significantly to improving the segmentation accuracy, which indicated that appropriate choices of training and inference strategies were at least as important as designing more advanced network structures. Frontiers Media S.A. 2022-06-02 /pmc/articles/PMC9204516/ /pubmed/35720705 http://dx.doi.org/10.3389/fnins.2022.918623 Text en Copyright © 2022 Chai, Wu, Wang, Cheng, Zhang, Zhang, Shen, Liu and Xia. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Chai, Chao
Wu, Mengran
Wang, Huiying
Cheng, Yue
Zhang, Shengtong
Zhang, Kun
Shen, Wen
Liu, Zhiyang
Xia, Shuang
CAU-Net: A Deep Learning Method for Deep Gray Matter Nuclei Segmentation
title CAU-Net: A Deep Learning Method for Deep Gray Matter Nuclei Segmentation
title_full CAU-Net: A Deep Learning Method for Deep Gray Matter Nuclei Segmentation
title_fullStr CAU-Net: A Deep Learning Method for Deep Gray Matter Nuclei Segmentation
title_full_unstemmed CAU-Net: A Deep Learning Method for Deep Gray Matter Nuclei Segmentation
title_short CAU-Net: A Deep Learning Method for Deep Gray Matter Nuclei Segmentation
title_sort cau-net: a deep learning method for deep gray matter nuclei segmentation
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9204516/
https://www.ncbi.nlm.nih.gov/pubmed/35720705
http://dx.doi.org/10.3389/fnins.2022.918623
work_keys_str_mv AT chaichao caunetadeeplearningmethodfordeepgraymatternucleisegmentation
AT wumengran caunetadeeplearningmethodfordeepgraymatternucleisegmentation
AT wanghuiying caunetadeeplearningmethodfordeepgraymatternucleisegmentation
AT chengyue caunetadeeplearningmethodfordeepgraymatternucleisegmentation
AT zhangshengtong caunetadeeplearningmethodfordeepgraymatternucleisegmentation
AT zhangkun caunetadeeplearningmethodfordeepgraymatternucleisegmentation
AT shenwen caunetadeeplearningmethodfordeepgraymatternucleisegmentation
AT liuzhiyang caunetadeeplearningmethodfordeepgraymatternucleisegmentation
AT xiashuang caunetadeeplearningmethodfordeepgraymatternucleisegmentation