ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis

Smadar Gefen; Oleh J. Tretiak; Catherine W. Piccoli; Kevin D. Donohue; Athina P. Petropulu; P. Mohana Shankar; Vishruta A. Dumane; Lexun Huang; M. Alper Kutay; Vladimir Genis; Flemming Forsberg; John M. Reid; Barry B. Goldberg

doi:10.1109/TMI.2002.808361

ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis

Smadar Gefen, Oleh J. Tretiak, Catherine W. Piccoli, Kevin D. Donohue, Athina P. Petropulu, P. Mohana Shankar, Vishruta A. Dumane, Lexun Huang, M. Alper Kutay, Vladimir Genis, Flemming Forsberg, John M. Reid, Barry B. Goldberg

Research output: Contribution to journal › Article › peer-review

72 Scopus citations

Abstract

Breast cancer diagnosis through ultrasound tissue characterization was studied using receiver operating characteristic (ROC) analysis of combinations of acoustic features, patient age, and radiological findings. A features fusion method was devised that operates even if only partial diagnostic data are available. The ROC methodology uses ordinal dominance theory and bootstrap resampling to evaluate A_z and confidence intervals in simple as well as paired data analyses. The combined diagnostic feature had an A_z of 0.96 with a confidence interval of [0.93, 0.99] at a significance level of 0.05. The combined features show statistically significant improvement over prebiopsy radiological findings. These results indicate that ultrasound tissue characterization, in combination with patient record and clinical findings, may greatly reduce the need to perform biopsies of benign breast lesions.

Original language	English
Pages (from-to)	170-177
Number of pages	8
Journal	IEEE Transactions on Medical Imaging
Volume	22
Issue number	2
DOIs	https://doi.org/10.1109/TMI.2002.808361
State	Published - Feb 2003
Externally published	Yes

Keywords

Bootstrap
Breast ultrasonic imaging
ROC analysis
Tissue characterization

Access to Document

10.1109/TMI.2002.808361

Cite this

Gefen, S., Tretiak, O. J., Piccoli, C. W., Donohue, K. D., Petropulu, A. P., Shankar, P. M., Dumane, V. A., Huang, L., Kutay, M. A., Genis, V., Forsberg, F., Reid, J. M., & Goldberg, B. B. (2003). ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis. IEEE Transactions on Medical Imaging, 22(2), 170-177. https://doi.org/10.1109/TMI.2002.808361

@article{ca187758a514403cb0ec2fb36a93a7f0,

title = "ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis",

abstract = "Breast cancer diagnosis through ultrasound tissue characterization was studied using receiver operating characteristic (ROC) analysis of combinations of acoustic features, patient age, and radiological findings. A features fusion method was devised that operates even if only partial diagnostic data are available. The ROC methodology uses ordinal dominance theory and bootstrap resampling to evaluate Az and confidence intervals in simple as well as paired data analyses. The combined diagnostic feature had an Az of 0.96 with a confidence interval of [0.93, 0.99] at a significance level of 0.05. The combined features show statistically significant improvement over prebiopsy radiological findings. These results indicate that ultrasound tissue characterization, in combination with patient record and clinical findings, may greatly reduce the need to perform biopsies of benign breast lesions.",

keywords = "Bootstrap, Breast ultrasonic imaging, ROC analysis, Tissue characterization",

author = "Smadar Gefen and Tretiak, {Oleh J.} and Piccoli, {Catherine W.} and Donohue, {Kevin D.} and Petropulu, {Athina P.} and Shankar, {P. Mohana} and Dumane, {Vishruta A.} and Lexun Huang and Kutay, {M. Alper} and Vladimir Genis and Flemming Forsberg and Reid, {John M.} and Goldberg, {Barry B.}",

note = "Funding Information: Manuscript received December 15, 2001; revised October 24, 2002. This work was supported by the National Institutes of Health (NIH) under Grant CA52823-06S1. The Associate Editor responsible for coordinating the review of this paper and recommending its publication was M. Giger. Asterisk indicates corresponding author.",

year = "2003",

month = feb,

doi = "10.1109/TMI.2002.808361",

language = "English",

volume = "22",

pages = "170--177",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis

AU - Gefen, Smadar

AU - Tretiak, Oleh J.

AU - Piccoli, Catherine W.

AU - Donohue, Kevin D.

AU - Petropulu, Athina P.

AU - Shankar, P. Mohana

AU - Dumane, Vishruta A.

AU - Huang, Lexun

AU - Kutay, M. Alper

AU - Genis, Vladimir

AU - Forsberg, Flemming

AU - Reid, John M.

AU - Goldberg, Barry B.

N1 - Funding Information: Manuscript received December 15, 2001; revised October 24, 2002. This work was supported by the National Institutes of Health (NIH) under Grant CA52823-06S1. The Associate Editor responsible for coordinating the review of this paper and recommending its publication was M. Giger. Asterisk indicates corresponding author.

PY - 2003/2

Y1 - 2003/2

N2 - Breast cancer diagnosis through ultrasound tissue characterization was studied using receiver operating characteristic (ROC) analysis of combinations of acoustic features, patient age, and radiological findings. A features fusion method was devised that operates even if only partial diagnostic data are available. The ROC methodology uses ordinal dominance theory and bootstrap resampling to evaluate Az and confidence intervals in simple as well as paired data analyses. The combined diagnostic feature had an Az of 0.96 with a confidence interval of [0.93, 0.99] at a significance level of 0.05. The combined features show statistically significant improvement over prebiopsy radiological findings. These results indicate that ultrasound tissue characterization, in combination with patient record and clinical findings, may greatly reduce the need to perform biopsies of benign breast lesions.

AB - Breast cancer diagnosis through ultrasound tissue characterization was studied using receiver operating characteristic (ROC) analysis of combinations of acoustic features, patient age, and radiological findings. A features fusion method was devised that operates even if only partial diagnostic data are available. The ROC methodology uses ordinal dominance theory and bootstrap resampling to evaluate Az and confidence intervals in simple as well as paired data analyses. The combined diagnostic feature had an Az of 0.96 with a confidence interval of [0.93, 0.99] at a significance level of 0.05. The combined features show statistically significant improvement over prebiopsy radiological findings. These results indicate that ultrasound tissue characterization, in combination with patient record and clinical findings, may greatly reduce the need to perform biopsies of benign breast lesions.

KW - Bootstrap

KW - Breast ultrasonic imaging

KW - ROC analysis

KW - Tissue characterization

UR - http://www.scopus.com/inward/record.url?scp=0037722717&partnerID=8YFLogxK

U2 - 10.1109/TMI.2002.808361

DO - 10.1109/TMI.2002.808361

M3 - Article

C2 - 12715993

AN - SCOPUS:0037722717

SN - 0278-0062

VL - 22

SP - 170

EP - 177

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 2

ER -

ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis

Abstract

Keywords

Access to Document

Fingerprint

Cite this