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 journalArticlepeer-review

72 Scopus citations


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.

Original languageEnglish
Pages (from-to)170-177
Number of pages8
JournalIEEE Transactions on Medical Imaging
Issue number2
StatePublished - Feb 2003
Externally publishedYes


  • Bootstrap
  • Breast ultrasonic imaging
  • ROC analysis
  • Tissue characterization


Dive into the research topics of 'ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis'. Together they form a unique fingerprint.

Cite this