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

doi:10.1109/ISBI.2019.8759537

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 proceeding › Conference contribution

12 Citations (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 language	English
Title of host publication	ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
Publisher	IEEE Computer Society
Pages	1882-1886
Number of pages	5
ISBN (Electronic)	9781538636411
DOIs	https://doi.org/10.1109/ISBI.2019.8759537
Publication status	Published - 2019 Apr
Event	16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy Duration: 2019 Apr 8 → 2019 Apr 11

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2019-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
Country/Territory	Italy
City	Venice
Period	19/4/8 → 19/4/11

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Spherical u-net
Surface parcellation

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2019.8759537

Cite this

Zhao, F., Xia, S., Wu, Z., Wang, L., Chen, Z., Lin, W., Gilmore, J. H., Shen, D., & Li, G. (2019). Spherical u-net for infant cortical surface parcellation. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (pp. 1882-1886). Article 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 et al.
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 proceeding › Conference 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

@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",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 ; Conference date: 08-04-2019 Through 11-04-2019",

year = "2019",

month = apr,

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

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

T2 - 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019

Y2 - 8 April 2019 through 11 April 2019

ER -

Spherical u-net for infant cortical surface parcellation

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this