Spherical u-net for infant cortical surface parcellation

Fenqiang Zhao, Shunren Xia, Zhengwang Wu, Li Wang, Zengsi Chen, Weili Lin, John H. Gilmore, Dinggang Shen, Gang Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In human brain MRI studies, it is of great importance to accurately parcellate cortical surfaces into anatomically and functionally meaningful regions. In this paper, we propose a novel end-to-end deep learning method by formulating surface parcellation as a semantic segmentation task on the sphere. To extend the convolutional neural networks (CNNs) to the spherical space, corresponding operations of surface convolution, pooling and upsampling are first developed to deal with data representation on spherical surface meshes, and then spherical CNNs are constructed accordingly. Specifically, the U-Net and SegNet architectures are transformed to the spherical representation for neonatal cortical surface parcellation. Experimental results on 90 neonates indicate the effectiveness and efficiency of our proposed spherical U-Net, in comparison with the spherical SegNet and the previous patch-wise classification method.

Original languageEnglish
Title of host publicationISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages1882-1886
Number of pages5
ISBN (Electronic)9781538636411
DOIs
Publication statusPublished - 2019 Apr
Externally publishedYes
Event16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy
Duration: 2019 Apr 82019 Apr 11

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2019-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
CountryItaly
CityVenice
Period19/4/819/4/11

Fingerprint

Semantics
Learning
Newborn Infant
Efficiency
Brain
Neural networks
Convolution
Magnetic resonance imaging
Deep learning

Keywords

  • Spherical u-net
  • Surface parcellation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Zhao, F., Xia, S., Wu, Z., Wang, L., Chen, Z., Lin, W., ... Li, G. (2019). Spherical u-net for infant cortical surface parcellation. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (pp. 1882-1886). [8759537] (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April). IEEE Computer Society. https://doi.org/10.1109/ISBI.2019.8759537

Spherical u-net for infant cortical surface parcellation. / Zhao, Fenqiang; Xia, Shunren; Wu, Zhengwang; Wang, Li; Chen, Zengsi; Lin, Weili; Gilmore, John H.; Shen, Dinggang; Li, Gang.

ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. p. 1882-1886 8759537 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhao, F, Xia, S, Wu, Z, Wang, L, Chen, Z, Lin, W, Gilmore, JH, Shen, D & Li, G 2019, Spherical u-net for infant cortical surface parcellation. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759537, Proceedings - International Symposium on Biomedical Imaging, vol. 2019-April, IEEE Computer Society, pp. 1882-1886, 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, Italy, 19/4/8. https://doi.org/10.1109/ISBI.2019.8759537
Zhao F, Xia S, Wu Z, Wang L, Chen Z, Lin W et al. Spherical u-net for infant cortical surface parcellation. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society. 2019. p. 1882-1886. 8759537. (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2019.8759537
Zhao, Fenqiang ; Xia, Shunren ; Wu, Zhengwang ; Wang, Li ; Chen, Zengsi ; Lin, Weili ; Gilmore, John H. ; Shen, Dinggang ; Li, Gang. / Spherical u-net for infant cortical surface parcellation. ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. pp. 1882-1886 (Proceedings - International Symposium on Biomedical Imaging).
@inproceedings{1880ce16b62a417c85be37653dee4690,
title = "Spherical u-net for infant cortical surface parcellation",
abstract = "In human brain MRI studies, it is of great importance to accurately parcellate cortical surfaces into anatomically and functionally meaningful regions. In this paper, we propose a novel end-to-end deep learning method by formulating surface parcellation as a semantic segmentation task on the sphere. To extend the convolutional neural networks (CNNs) to the spherical space, corresponding operations of surface convolution, pooling and upsampling are first developed to deal with data representation on spherical surface meshes, and then spherical CNNs are constructed accordingly. Specifically, the U-Net and SegNet architectures are transformed to the spherical representation for neonatal cortical surface parcellation. Experimental results on 90 neonates indicate the effectiveness and efficiency of our proposed spherical U-Net, in comparison with the spherical SegNet and the previous patch-wise classification method.",
keywords = "Spherical u-net, Surface parcellation",
author = "Fenqiang Zhao and Shunren Xia and Zhengwang Wu and Li Wang and Zengsi Chen and Weili Lin and Gilmore, {John H.} and Dinggang Shen and Gang Li",
year = "2019",
month = "4",
doi = "10.1109/ISBI.2019.8759537",
language = "English",
series = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",
pages = "1882--1886",
booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Spherical u-net for infant cortical surface parcellation

AU - Zhao, Fenqiang

AU - Xia, Shunren

AU - Wu, Zhengwang

AU - Wang, Li

AU - Chen, Zengsi

AU - Lin, Weili

AU - Gilmore, John H.

AU - Shen, Dinggang

AU - Li, Gang

PY - 2019/4

Y1 - 2019/4

N2 - In human brain MRI studies, it is of great importance to accurately parcellate cortical surfaces into anatomically and functionally meaningful regions. In this paper, we propose a novel end-to-end deep learning method by formulating surface parcellation as a semantic segmentation task on the sphere. To extend the convolutional neural networks (CNNs) to the spherical space, corresponding operations of surface convolution, pooling and upsampling are first developed to deal with data representation on spherical surface meshes, and then spherical CNNs are constructed accordingly. Specifically, the U-Net and SegNet architectures are transformed to the spherical representation for neonatal cortical surface parcellation. Experimental results on 90 neonates indicate the effectiveness and efficiency of our proposed spherical U-Net, in comparison with the spherical SegNet and the previous patch-wise classification method.

AB - In human brain MRI studies, it is of great importance to accurately parcellate cortical surfaces into anatomically and functionally meaningful regions. In this paper, we propose a novel end-to-end deep learning method by formulating surface parcellation as a semantic segmentation task on the sphere. To extend the convolutional neural networks (CNNs) to the spherical space, corresponding operations of surface convolution, pooling and upsampling are first developed to deal with data representation on spherical surface meshes, and then spherical CNNs are constructed accordingly. Specifically, the U-Net and SegNet architectures are transformed to the spherical representation for neonatal cortical surface parcellation. Experimental results on 90 neonates indicate the effectiveness and efficiency of our proposed spherical U-Net, in comparison with the spherical SegNet and the previous patch-wise classification method.

KW - Spherical u-net

KW - Surface parcellation

UR - http://www.scopus.com/inward/record.url?scp=85073909149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073909149&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759537

DO - 10.1109/ISBI.2019.8759537

M3 - Conference contribution

AN - SCOPUS:85073909149

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1882

EP - 1886

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -