Cargando…
3D‐MASNet: 3D mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain MR images
Precise segmentation of infant brain magnetic resonance (MR) images into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) are essential for studying neuroanatomical hallmarks of early brain development. However, for 6‐month‐old infants, the extremely low‐intensity contrast caused b...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley & Sons, Inc.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9921327/ https://www.ncbi.nlm.nih.gov/pubmed/36515219 http://dx.doi.org/10.1002/hbm.26174 |
_version_ | 1784887285346467840 |
---|---|
author | Zeng, Zilong Zhao, Tengda Sun, Lianglong Zhang, Yihe Xia, Mingrui Liao, Xuhong Zhang, Jiaying Shen, Dinggang Wang, Li He, Yong |
author_facet | Zeng, Zilong Zhao, Tengda Sun, Lianglong Zhang, Yihe Xia, Mingrui Liao, Xuhong Zhang, Jiaying Shen, Dinggang Wang, Li He, Yong |
author_sort | Zeng, Zilong |
collection | PubMed |
description | Precise segmentation of infant brain magnetic resonance (MR) images into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) are essential for studying neuroanatomical hallmarks of early brain development. However, for 6‐month‐old infants, the extremely low‐intensity contrast caused by inherent myelination hinders accurate tissue segmentation. Existing convolutional neural networks (CNNs) based segmentation models for this task generally employ single‐scale symmetric convolutions, which are inefficient for encoding the isointense tissue boundaries in baby brain images. Here, we propose a 3D mixed‐scale asymmetric convolutional segmentation network (3D‐MASNet) framework for brain MR images of 6‐month‐old infants. We replaced the traditional convolutional layer of an existing to‐be‐trained network with a 3D mixed‐scale convolution block consisting of asymmetric kernels (MixACB) during the training phase and then equivalently converted it into the original network. Five canonical CNN segmentation models were evaluated using both T1‐ and T2‐weighted images of 23 6‐month‐old infants from iSeg‐2019 datasets, which contained manual labels as ground truth. MixACB significantly enhanced the average accuracy of all five models and obtained the most considerable improvement in the fully convolutional network model (CC‐3D‐FCN) and the highest performance in the Dense U‐Net model. This approach further obtained Dice coefficient accuracies of 0.931, 0.912, and 0.961 in GM, WM, and CSF, respectively, ranking first among 30 teams on the validation dataset of the iSeg‐2019 Grand Challenge. Thus, the proposed 3D‐MASNet can improve the accuracy of existing CNNs‐based segmentation models as a plug‐and‐play solution that offers a promising technique for future infant brain MRI studies. |
format | Online Article Text |
id | pubmed-9921327 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | John Wiley & Sons, Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-99213272023-02-13 3D‐MASNet: 3D mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain MR images Zeng, Zilong Zhao, Tengda Sun, Lianglong Zhang, Yihe Xia, Mingrui Liao, Xuhong Zhang, Jiaying Shen, Dinggang Wang, Li He, Yong Hum Brain Mapp Research Articles Precise segmentation of infant brain magnetic resonance (MR) images into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) are essential for studying neuroanatomical hallmarks of early brain development. However, for 6‐month‐old infants, the extremely low‐intensity contrast caused by inherent myelination hinders accurate tissue segmentation. Existing convolutional neural networks (CNNs) based segmentation models for this task generally employ single‐scale symmetric convolutions, which are inefficient for encoding the isointense tissue boundaries in baby brain images. Here, we propose a 3D mixed‐scale asymmetric convolutional segmentation network (3D‐MASNet) framework for brain MR images of 6‐month‐old infants. We replaced the traditional convolutional layer of an existing to‐be‐trained network with a 3D mixed‐scale convolution block consisting of asymmetric kernels (MixACB) during the training phase and then equivalently converted it into the original network. Five canonical CNN segmentation models were evaluated using both T1‐ and T2‐weighted images of 23 6‐month‐old infants from iSeg‐2019 datasets, which contained manual labels as ground truth. MixACB significantly enhanced the average accuracy of all five models and obtained the most considerable improvement in the fully convolutional network model (CC‐3D‐FCN) and the highest performance in the Dense U‐Net model. This approach further obtained Dice coefficient accuracies of 0.931, 0.912, and 0.961 in GM, WM, and CSF, respectively, ranking first among 30 teams on the validation dataset of the iSeg‐2019 Grand Challenge. Thus, the proposed 3D‐MASNet can improve the accuracy of existing CNNs‐based segmentation models as a plug‐and‐play solution that offers a promising technique for future infant brain MRI studies. John Wiley & Sons, Inc. 2022-12-14 /pmc/articles/PMC9921327/ /pubmed/36515219 http://dx.doi.org/10.1002/hbm.26174 Text en © 2022 The Authors. Human Brain Mapping published by Wiley Periodicals LLC. https://creativecommons.org/licenses/by-nc/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc/4.0/ (https://creativecommons.org/licenses/by-nc/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes. |
spellingShingle | Research Articles Zeng, Zilong Zhao, Tengda Sun, Lianglong Zhang, Yihe Xia, Mingrui Liao, Xuhong Zhang, Jiaying Shen, Dinggang Wang, Li He, Yong 3D‐MASNet: 3D mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain MR images |
title |
3D‐MASNet: 3D mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain MR images |
title_full |
3D‐MASNet: 3D mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain MR images |
title_fullStr |
3D‐MASNet: 3D mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain MR images |
title_full_unstemmed |
3D‐MASNet: 3D mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain MR images |
title_short |
3D‐MASNet: 3D mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain MR images |
title_sort | 3d‐masnet: 3d mixed‐scale asymmetric convolutional segmentation network for 6‐month‐old infant brain mr images |
topic | Research Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9921327/ https://www.ncbi.nlm.nih.gov/pubmed/36515219 http://dx.doi.org/10.1002/hbm.26174 |
work_keys_str_mv | AT zengzilong 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT zhaotengda 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT sunlianglong 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT zhangyihe 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT xiamingrui 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT liaoxuhong 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT zhangjiaying 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT shendinggang 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT wangli 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages AT heyong 3dmasnet3dmixedscaleasymmetricconvolutionalsegmentationnetworkfor6montholdinfantbrainmrimages |