3D topology-preserving segmentation with compound multi-slice representation

Jiaqi Yang; Xiaoling Hu; Chao Chen; Chialing Tsai

doi:10.1109/ISBI48211.2021.9433941

3D topology-preserving segmentation with compound multi-slice representation

Jiaqi Yang
, Xiaoling Hu
, Chao Chen
, Chialing Tsai

Biomedical Informatics

City University of New York
Stony Brook University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

We propose a new topology-preserving method for 3D image segmentation. We treat the image as a stack of 2D images so that the topological computation can be carried only within 2D in order to achieve computational efficiency. To enforce the continuity between slices, we propose a compound multi-slice representation and a compound multi-slice topological loss that incorporates rich topological information from adjacent slices. The quantitative and qualitative results show that our proposed method outperforms various strong baselines, especially for structure-related evaluation metrics.

Original language	English
Title of host publication	2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021
Publisher	IEEE Computer Society
Pages	1297-1301
Number of pages	5
ISBN (Electronic)	9781665412469
DOIs	https://doi.org/10.1109/ISBI48211.2021.9433941
State	Published - Apr 13 2021
Event	18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 - Virtual, Online, France Duration: Apr 13 2021 → Apr 16 2021

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2021-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	18th IEEE International Symposium on Biomedical Imaging, ISBI 2021
Country/Territory	France
City	Virtual, Online
Period	04/13/21 → 04/16/21

Keywords

3D Image Segmentation
Compound Multi-Slice
Topology

Access to Document

10.1109/ISBI48211.2021.9433941

Cite this

Yang, J., Hu, X., Chen, C., & Tsai, C. (2021). 3D topology-preserving segmentation with compound multi-slice representation. In 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021 (pp. 1297-1301). Article 9433941 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2021-April). IEEE Computer Society. https://doi.org/10.1109/ISBI48211.2021.9433941

@inproceedings{2bd78d94cf1340ed8c99799e6064cb30,

title = "3D topology-preserving segmentation with compound multi-slice representation",

abstract = "We propose a new topology-preserving method for 3D image segmentation. We treat the image as a stack of 2D images so that the topological computation can be carried only within 2D in order to achieve computational efficiency. To enforce the continuity between slices, we propose a compound multi-slice representation and a compound multi-slice topological loss that incorporates rich topological information from adjacent slices. The quantitative and qualitative results show that our proposed method outperforms various strong baselines, especially for structure-related evaluation metrics.",

keywords = "3D Image Segmentation, Compound Multi-Slice, Topology",

author = "Jiaqi Yang and Xiaoling Hu and Chao Chen and Chialing Tsai",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 ; Conference date: 13-04-2021 Through 16-04-2021",

year = "2021",

month = apr,

day = "13",

doi = "10.1109/ISBI48211.2021.9433941",

language = "English",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "1297--1301",

booktitle = "2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021",

}

Yang, J, Hu, X, Chen, C & Tsai, C 2021, 3D topology-preserving segmentation with compound multi-slice representation. in 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021., 9433941, Proceedings - International Symposium on Biomedical Imaging, vol. 2021-April, IEEE Computer Society, pp. 1297-1301, 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021, Virtual, Online, France, 04/13/21. https://doi.org/10.1109/ISBI48211.2021.9433941

3D topology-preserving segmentation with compound multi-slice representation. / Yang, Jiaqi; Hu, Xiaoling; Chen, Chao et al.
2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021. IEEE Computer Society, 2021. p. 1297-1301 9433941 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2021-April).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - 3D topology-preserving segmentation with compound multi-slice representation

AU - Yang, Jiaqi

AU - Hu, Xiaoling

AU - Chen, Chao

AU - Tsai, Chialing

PY - 2021/4/13

Y1 - 2021/4/13

N2 - We propose a new topology-preserving method for 3D image segmentation. We treat the image as a stack of 2D images so that the topological computation can be carried only within 2D in order to achieve computational efficiency. To enforce the continuity between slices, we propose a compound multi-slice representation and a compound multi-slice topological loss that incorporates rich topological information from adjacent slices. The quantitative and qualitative results show that our proposed method outperforms various strong baselines, especially for structure-related evaluation metrics.

AB - We propose a new topology-preserving method for 3D image segmentation. We treat the image as a stack of 2D images so that the topological computation can be carried only within 2D in order to achieve computational efficiency. To enforce the continuity between slices, we propose a compound multi-slice representation and a compound multi-slice topological loss that incorporates rich topological information from adjacent slices. The quantitative and qualitative results show that our proposed method outperforms various strong baselines, especially for structure-related evaluation metrics.

KW - 3D Image Segmentation

KW - Compound Multi-Slice

KW - Topology

UR - https://www.scopus.com/pages/publications/85107230302

U2 - 10.1109/ISBI48211.2021.9433941

DO - 10.1109/ISBI48211.2021.9433941

M3 - Conference contribution

AN - SCOPUS:85107230302

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1297

EP - 1301

BT - 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021

PB - IEEE Computer Society

T2 - 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021

Y2 - 13 April 2021 through 16 April 2021

ER -

3D topology-preserving segmentation with compound multi-slice representation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this