Web-based multi-observer segmentation evaluation tool

Yaoyao Zhu, Sharon Xiaolei Huang, Daniel Lopresti, Rodeny Long, Sameer Antani, Zhiyun Xue, George Thoma

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

1 Citation (Scopus)

Abstract

Multi-observer segmentation evaluation is useful in the imaging community. We have developed web-based software for automatic performance evaluation of multiple image segmentations which is based on the Baysian Decision framework. It computes a probabilistic estimate of the true segmentation ground truth map) and performance measures for the individual segmentations (sensitivity and specificity). The strength of the tool is that it integrates the two kinds of prior knowledge of segmentations: the truth prior (the prior probability) and the observer prior (the performance measures of observers), which can generate more accurate evaluations.

Original languageEnglish (US)
Title of host publicationProceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008
Pages167-169
Number of pages3
DOIs
StatePublished - Sep 22 2008
Event21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008 - Jyvaskyla, Finland
Duration: Jun 17 2008Jun 19 2008

Publication series

NameProceedings - IEEE Symposium on Computer-Based Medical Systems
ISSN (Print)1063-7125

Conference

Conference21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008
CountryFinland
CityJyvaskyla
Period6/17/086/19/08

Fingerprint

Image segmentation
Imaging techniques
Software
Sensitivity and Specificity

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Cite this

Zhu, Y., Huang, S. X., Lopresti, D., Long, R., Antani, S., Xue, Z., & Thoma, G. (2008). Web-based multi-observer segmentation evaluation tool. In Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008 (pp. 167-169). [4561979] (Proceedings - IEEE Symposium on Computer-Based Medical Systems). https://doi.org/10.1109/CBMS.2008.121
Zhu, Yaoyao ; Huang, Sharon Xiaolei ; Lopresti, Daniel ; Long, Rodeny ; Antani, Sameer ; Xue, Zhiyun ; Thoma, George. / Web-based multi-observer segmentation evaluation tool. Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008. 2008. pp. 167-169 (Proceedings - IEEE Symposium on Computer-Based Medical Systems).
@inproceedings{17c47d50df854ecb8d99ff8bb2f116bd,
title = "Web-based multi-observer segmentation evaluation tool",
abstract = "Multi-observer segmentation evaluation is useful in the imaging community. We have developed web-based software for automatic performance evaluation of multiple image segmentations which is based on the Baysian Decision framework. It computes a probabilistic estimate of the true segmentation ground truth map) and performance measures for the individual segmentations (sensitivity and specificity). The strength of the tool is that it integrates the two kinds of prior knowledge of segmentations: the truth prior (the prior probability) and the observer prior (the performance measures of observers), which can generate more accurate evaluations.",
author = "Yaoyao Zhu and Huang, {Sharon Xiaolei} and Daniel Lopresti and Rodeny Long and Sameer Antani and Zhiyun Xue and George Thoma",
year = "2008",
month = "9",
day = "22",
doi = "10.1109/CBMS.2008.121",
language = "English (US)",
isbn = "9780769531656",
series = "Proceedings - IEEE Symposium on Computer-Based Medical Systems",
pages = "167--169",
booktitle = "Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008",

}

Zhu, Y, Huang, SX, Lopresti, D, Long, R, Antani, S, Xue, Z & Thoma, G 2008, Web-based multi-observer segmentation evaluation tool. in Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008., 4561979, Proceedings - IEEE Symposium on Computer-Based Medical Systems, pp. 167-169, 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008, Jyvaskyla, Finland, 6/17/08. https://doi.org/10.1109/CBMS.2008.121

Web-based multi-observer segmentation evaluation tool. / Zhu, Yaoyao; Huang, Sharon Xiaolei; Lopresti, Daniel; Long, Rodeny; Antani, Sameer; Xue, Zhiyun; Thoma, George.

Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008. 2008. p. 167-169 4561979 (Proceedings - IEEE Symposium on Computer-Based Medical Systems).

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

TY - GEN

T1 - Web-based multi-observer segmentation evaluation tool

AU - Zhu, Yaoyao

AU - Huang, Sharon Xiaolei

AU - Lopresti, Daniel

AU - Long, Rodeny

AU - Antani, Sameer

AU - Xue, Zhiyun

AU - Thoma, George

PY - 2008/9/22

Y1 - 2008/9/22

N2 - Multi-observer segmentation evaluation is useful in the imaging community. We have developed web-based software for automatic performance evaluation of multiple image segmentations which is based on the Baysian Decision framework. It computes a probabilistic estimate of the true segmentation ground truth map) and performance measures for the individual segmentations (sensitivity and specificity). The strength of the tool is that it integrates the two kinds of prior knowledge of segmentations: the truth prior (the prior probability) and the observer prior (the performance measures of observers), which can generate more accurate evaluations.

AB - Multi-observer segmentation evaluation is useful in the imaging community. We have developed web-based software for automatic performance evaluation of multiple image segmentations which is based on the Baysian Decision framework. It computes a probabilistic estimate of the true segmentation ground truth map) and performance measures for the individual segmentations (sensitivity and specificity). The strength of the tool is that it integrates the two kinds of prior knowledge of segmentations: the truth prior (the prior probability) and the observer prior (the performance measures of observers), which can generate more accurate evaluations.

UR - http://www.scopus.com/inward/record.url?scp=51849119776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51849119776&partnerID=8YFLogxK

U2 - 10.1109/CBMS.2008.121

DO - 10.1109/CBMS.2008.121

M3 - Conference contribution

AN - SCOPUS:51849119776

SN - 9780769531656

T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems

SP - 167

EP - 169

BT - Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008

ER -

Zhu Y, Huang SX, Lopresti D, Long R, Antani S, Xue Z et al. Web-based multi-observer segmentation evaluation tool. In Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS 2008. 2008. p. 167-169. 4561979. (Proceedings - IEEE Symposium on Computer-Based Medical Systems). https://doi.org/10.1109/CBMS.2008.121