3D ROC analysis for medical imaging diagnosis

Su Wang, Chein I. Chang, Sheng Chih Yang, Giu Cheng Hsu, Hsian He Hsu, Pau Choo Chung, Shu Mei Guo, San Kan Lee

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

9 Citations (Scopus)

Abstract

Receiver operating characteristics (ROC) has been widely used as a performance evaluation tool to measure effectiveness of medical modalities. It is derived from a standard detection theory with false alarm and detection power interpreted as false positive (FP) and true positive (TP) respectively in terms of medical diagnosis. The ROC curve is plotted based on TP versus FP via hard decisions. This paper presents a three dimensional (3D) ROC analysis which extends the traditional two-dimensional (2D) ROC analysis by including a threshold parameter in a third dimension resulting from soft decisions, (SD). As a result, a 3D ROC curve can be plotted based on three parameters, TP, FP and SD. By virtue of such a 3D ROC curve three two-dimensional (2D) ROC curves can be derived, one of which is the traditional 2D ROC curve of TP versus FP with SD reduced to hard decision. In order to illustrate its utility in medical diagnosis, its application to magnetic resonance (MR) image classification is demonstrated.

Original languageEnglish
Title of host publicationProceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
Pages7545-7548
Number of pages4
Publication statusPublished - 2005 Dec 1
Event2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 - Shanghai, China
Duration: 2005 Sep 12005 Sep 4

Publication series

NameAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume7 VOLS
ISSN (Print)0589-1019

Other

Other2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
CountryChina
CityShanghai
Period05-09-0105-09-04

Fingerprint

Medical imaging
Diagnostic Imaging
ROC Curve
Image classification
Magnetic resonance
Magnetic Resonance Spectroscopy

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Wang, S., Chang, C. I., Yang, S. C., Hsu, G. C., Hsu, H. H., Chung, P. C., ... Lee, S. K. (2005). 3D ROC analysis for medical imaging diagnosis. In Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 (pp. 7545-7548). [1616258] (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings; Vol. 7 VOLS).
Wang, Su ; Chang, Chein I. ; Yang, Sheng Chih ; Hsu, Giu Cheng ; Hsu, Hsian He ; Chung, Pau Choo ; Guo, Shu Mei ; Lee, San Kan. / 3D ROC analysis for medical imaging diagnosis. Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. 2005. pp. 7545-7548 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).
@inproceedings{582e00230d5e43609b4db511ef03be23,
title = "3D ROC analysis for medical imaging diagnosis",
abstract = "Receiver operating characteristics (ROC) has been widely used as a performance evaluation tool to measure effectiveness of medical modalities. It is derived from a standard detection theory with false alarm and detection power interpreted as false positive (FP) and true positive (TP) respectively in terms of medical diagnosis. The ROC curve is plotted based on TP versus FP via hard decisions. This paper presents a three dimensional (3D) ROC analysis which extends the traditional two-dimensional (2D) ROC analysis by including a threshold parameter in a third dimension resulting from soft decisions, (SD). As a result, a 3D ROC curve can be plotted based on three parameters, TP, FP and SD. By virtue of such a 3D ROC curve three two-dimensional (2D) ROC curves can be derived, one of which is the traditional 2D ROC curve of TP versus FP with SD reduced to hard decision. In order to illustrate its utility in medical diagnosis, its application to magnetic resonance (MR) image classification is demonstrated.",
author = "Su Wang and Chang, {Chein I.} and Yang, {Sheng Chih} and Hsu, {Giu Cheng} and Hsu, {Hsian He} and Chung, {Pau Choo} and Guo, {Shu Mei} and Lee, {San Kan}",
year = "2005",
month = "12",
day = "1",
language = "English",
isbn = "0780387406",
series = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",
pages = "7545--7548",
booktitle = "Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005",

}

Wang, S, Chang, CI, Yang, SC, Hsu, GC, Hsu, HH, Chung, PC, Guo, SM & Lee, SK 2005, 3D ROC analysis for medical imaging diagnosis. in Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005., 1616258, Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, vol. 7 VOLS, pp. 7545-7548, 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005, Shanghai, China, 05-09-01.

3D ROC analysis for medical imaging diagnosis. / Wang, Su; Chang, Chein I.; Yang, Sheng Chih; Hsu, Giu Cheng; Hsu, Hsian He; Chung, Pau Choo; Guo, Shu Mei; Lee, San Kan.

Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. 2005. p. 7545-7548 1616258 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings; Vol. 7 VOLS).

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

TY - GEN

T1 - 3D ROC analysis for medical imaging diagnosis

AU - Wang, Su

AU - Chang, Chein I.

AU - Yang, Sheng Chih

AU - Hsu, Giu Cheng

AU - Hsu, Hsian He

AU - Chung, Pau Choo

AU - Guo, Shu Mei

AU - Lee, San Kan

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Receiver operating characteristics (ROC) has been widely used as a performance evaluation tool to measure effectiveness of medical modalities. It is derived from a standard detection theory with false alarm and detection power interpreted as false positive (FP) and true positive (TP) respectively in terms of medical diagnosis. The ROC curve is plotted based on TP versus FP via hard decisions. This paper presents a three dimensional (3D) ROC analysis which extends the traditional two-dimensional (2D) ROC analysis by including a threshold parameter in a third dimension resulting from soft decisions, (SD). As a result, a 3D ROC curve can be plotted based on three parameters, TP, FP and SD. By virtue of such a 3D ROC curve three two-dimensional (2D) ROC curves can be derived, one of which is the traditional 2D ROC curve of TP versus FP with SD reduced to hard decision. In order to illustrate its utility in medical diagnosis, its application to magnetic resonance (MR) image classification is demonstrated.

AB - Receiver operating characteristics (ROC) has been widely used as a performance evaluation tool to measure effectiveness of medical modalities. It is derived from a standard detection theory with false alarm and detection power interpreted as false positive (FP) and true positive (TP) respectively in terms of medical diagnosis. The ROC curve is plotted based on TP versus FP via hard decisions. This paper presents a three dimensional (3D) ROC analysis which extends the traditional two-dimensional (2D) ROC analysis by including a threshold parameter in a third dimension resulting from soft decisions, (SD). As a result, a 3D ROC curve can be plotted based on three parameters, TP, FP and SD. By virtue of such a 3D ROC curve three two-dimensional (2D) ROC curves can be derived, one of which is the traditional 2D ROC curve of TP versus FP with SD reduced to hard decision. In order to illustrate its utility in medical diagnosis, its application to magnetic resonance (MR) image classification is demonstrated.

UR - http://www.scopus.com/inward/record.url?scp=33846930152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846930152&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33846930152

SN - 0780387406

SN - 9780780387409

T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

SP - 7545

EP - 7548

BT - Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005

ER -

Wang S, Chang CI, Yang SC, Hsu GC, Hsu HH, Chung PC et al. 3D ROC analysis for medical imaging diagnosis. In Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. 2005. p. 7545-7548. 1616258. (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).