ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis
Gefen, S.
Tretiak, O.J.
Piccoli, C.W.
Donohue, K.D.
Petropulu, A.P.
Shankar, P.M.
Dumane, V.A.
Lexun Huang
Kutay, M.A.
Genis, V.
Forsberg, F.
Reid, J.M.
Goldberg, B.B.
Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA;
This paper appears in: Medical Imaging, IEEE Transactions on
Publication Date: Feb. 2003
Volume: 22,
Issue: 2
On page(s): 170-177
Location: Davis, CA, USA,
ISSN: 0278-0062
INSPEC Accession Number: 7593142
Digital Object Identifier: 10.1109/TMI.2002.808361
Current Version Published: 2003-04-22
|
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 feature 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.
|
Cart
