Robust cell segmentation for histological images of Glioblastoma

Jun Kong; Pengyue Zhang; Yanhui Liang; George Teodoro; Daniel J. Brat; Fusheng Wang

doi:10.1109/ISBI.2016.7493444

Robust cell segmentation for histological images of Glioblastoma

Jun Kong, Pengyue Zhang, Yanhui Liang, George Teodoro, Daniel J. Brat, Fusheng Wang

Pathology

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

7 Scopus citations

Abstract

Glioblastoma (GBM) is a malignant brain tumor with uniformly dismal prognosis. Quantitative analysis of GBM cells is an important avenue to extract latent histologic disease signatures to correlate with molecular underpinnings and clinical outcomes. As a prerequisite, a robust and accurate cell segmentation is required. In this paper, we present an automated cell segmentation method that can satisfactorily address segmentation of overlapped cells commonly seen in GBM histology specimens. This method first detects cells with seed connectivity, distance constraints, image edge map, and a shape-based voting image. Initialized by identified seeds, cell boundaries are deformed with an improved variational level set method that can handle clumped cells. We test our method on 40 histological images of GBM with human annotations. The validation results suggest that our cell segmentation method is promising and represents an advance in quantitative cancer research.

Original language	English (US)
Title of host publication	2016 IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro, ISBI 2016 - Proceedings
Publisher	IEEE Computer Society Press
Pages	1041-1045
Number of pages	5
Volume	2016-June
ISBN (Electronic)	9781479923502
DOIs	https://doi.org/10.1109/ISBI.2016.7493444
State	Published - Jun 15 2016
Event	2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Prague, Czech Republic Duration: Apr 13 2016 → Apr 16 2016

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2016-June
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016
Country/Territory	Czech Republic
City	Prague
Period	4/13/16 → 4/16/16

Funding

This research is supported by grants from National Institute of Health K25CA181503 and R01CA176659, National Science Foundation ACI 1443054 and IIS 1350885, and CNPq

Keywords

cell segmentation
Hessian
Histological Image
iterative merging
seed detection

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISBI.2016.7493444

Cite this

Kong, J., Zhang, P., Liang, Y., Teodoro, G., Brat, D. J., & Wang, F. (2016). Robust cell segmentation for histological images of Glioblastoma. In 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings (Vol. 2016-June, pp. 1041-1045). Article 7493444 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2016-June). IEEE Computer Society Press. https://doi.org/10.1109/ISBI.2016.7493444

@inproceedings{695fb688d3574f17beffe6954ae0ca26,

title = "Robust cell segmentation for histological images of Glioblastoma",

abstract = "Glioblastoma (GBM) is a malignant brain tumor with uniformly dismal prognosis. Quantitative analysis of GBM cells is an important avenue to extract latent histologic disease signatures to correlate with molecular underpinnings and clinical outcomes. As a prerequisite, a robust and accurate cell segmentation is required. In this paper, we present an automated cell segmentation method that can satisfactorily address segmentation of overlapped cells commonly seen in GBM histology specimens. This method first detects cells with seed connectivity, distance constraints, image edge map, and a shape-based voting image. Initialized by identified seeds, cell boundaries are deformed with an improved variational level set method that can handle clumped cells. We test our method on 40 histological images of GBM with human annotations. The validation results suggest that our cell segmentation method is promising and represents an advance in quantitative cancer research.",

keywords = "cell segmentation, Hessian, Histological Image, iterative merging, seed detection",

author = "Jun Kong and Pengyue Zhang and Yanhui Liang and George Teodoro and Brat, {Daniel J.} and Fusheng Wang",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 ; Conference date: 13-04-2016 Through 16-04-2016",

year = "2016",

month = jun,

day = "15",

doi = "10.1109/ISBI.2016.7493444",

language = "English (US)",

volume = "2016-June",

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

publisher = "IEEE Computer Society Press",

pages = "1041--1045",

booktitle = "2016 IEEE International Symposium on Biomedical Imaging",

}

Kong, J, Zhang, P, Liang, Y, Teodoro, G, Brat, DJ & Wang, F 2016, Robust cell segmentation for histological images of Glioblastoma. in 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. vol. 2016-June, 7493444, Proceedings - International Symposium on Biomedical Imaging, vol. 2016-June, IEEE Computer Society Press, pp. 1041-1045, 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016, Prague, Czech Republic, 4/13/16. https://doi.org/10.1109/ISBI.2016.7493444

Robust cell segmentation for histological images of Glioblastoma. / Kong, Jun; Zhang, Pengyue; Liang, Yanhui et al.
2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. Vol. 2016-June IEEE Computer Society Press, 2016. p. 1041-1045 7493444 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2016-June).

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

TY - GEN

T1 - Robust cell segmentation for histological images of Glioblastoma

AU - Kong, Jun

AU - Zhang, Pengyue

AU - Liang, Yanhui

AU - Teodoro, George

AU - Brat, Daniel J.

AU - Wang, Fusheng

PY - 2016/6/15

Y1 - 2016/6/15

N2 - Glioblastoma (GBM) is a malignant brain tumor with uniformly dismal prognosis. Quantitative analysis of GBM cells is an important avenue to extract latent histologic disease signatures to correlate with molecular underpinnings and clinical outcomes. As a prerequisite, a robust and accurate cell segmentation is required. In this paper, we present an automated cell segmentation method that can satisfactorily address segmentation of overlapped cells commonly seen in GBM histology specimens. This method first detects cells with seed connectivity, distance constraints, image edge map, and a shape-based voting image. Initialized by identified seeds, cell boundaries are deformed with an improved variational level set method that can handle clumped cells. We test our method on 40 histological images of GBM with human annotations. The validation results suggest that our cell segmentation method is promising and represents an advance in quantitative cancer research.

AB - Glioblastoma (GBM) is a malignant brain tumor with uniformly dismal prognosis. Quantitative analysis of GBM cells is an important avenue to extract latent histologic disease signatures to correlate with molecular underpinnings and clinical outcomes. As a prerequisite, a robust and accurate cell segmentation is required. In this paper, we present an automated cell segmentation method that can satisfactorily address segmentation of overlapped cells commonly seen in GBM histology specimens. This method first detects cells with seed connectivity, distance constraints, image edge map, and a shape-based voting image. Initialized by identified seeds, cell boundaries are deformed with an improved variational level set method that can handle clumped cells. We test our method on 40 histological images of GBM with human annotations. The validation results suggest that our cell segmentation method is promising and represents an advance in quantitative cancer research.

KW - cell segmentation

KW - Hessian

KW - Histological Image

KW - iterative merging

KW - seed detection

UR - http://www.scopus.com/inward/record.url?scp=84978410048&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978410048&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2016.7493444

DO - 10.1109/ISBI.2016.7493444

M3 - Conference contribution

C2 - 28392891

AN - SCOPUS:84978410048

VL - 2016-June

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1041

EP - 1045

BT - 2016 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society Press

T2 - 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016

Y2 - 13 April 2016 through 16 April 2016

ER -

Kong J, Zhang P, Liang Y, Teodoro G, Brat DJ, Wang F. Robust cell segmentation for histological images of Glioblastoma. In 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. Vol. 2016-June. IEEE Computer Society Press. 2016. p. 1041-1045. 7493444. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI.2016.7493444

Robust cell segmentation for histological images of Glioblastoma

Abstract

Publication series

Conference

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this