Share Email Print

Proceedings Paper

ROC study: effects of computer-aided diagnosis on radiologists' characterization of malignant and benign breast masses in temporal pairs of mammograms
Author(s): Lubomir M. Hadjiiski; Heang-Ping Chan; Berkman Sahiner; Mark A. Helvie; Marilyn A. Roubidoux; Caroline E. Blane; Chintana Paramagul; Nicholas Petrick; Janet E. Bailey; Katherine Klein; Michelle Foster; Stephanie Patterson; Dorit D. Adler; Alexis Nees; Joseph Shen
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We conducted an observer performance study using receiver operating characteristic (ROC) methodology to evaluate the effects of computer-aided diagnosis (CAD) on radiologists’ performance for characterization of masses on serial mammograms. The automated CAD system, previously developed in our laboratory, can classify masses as malignant or benign based on interval change information on serial mammograms. In this study, 126 temporal image pairs (73 malignant and 53 benign) from 52 patients containing masses on serial mammograms were used. The corresponding masses on each temporal pair were identified by an experienced radiologist and automatically segmented by the CAD program. Morphological, texture, and spiculation features of the mass on the current and the prior mammograms were extracted. The individual features and the difference between the corresponding current and prior features formed a multidimensional feature space. A subset of the most effective features that contained the current, prior, and interval change information was selected by a stepwise procedure and used as input predictor variables to a linear discriminant classifier in a leave-one-case-out training and testing resampling scheme. The linear discriminant classifier estimated the relative likelihood of malignancy of each mass. The classifier achieved a test Az value of 0.87. For the ROC study, 4 MQSA radiologists and 1 breast imaging fellow assessed the masses on the temporal pairs and provided estimates of the likelihood of malignancy without and with CAD. The average Az value for the likelihood of malignancy estimated by the radiologists was 0.79 without CAD and improved to 0.87 with CAD. The improvement was statistically significant (p=0.0003). This preliminary result indicated that CAD using interval change analysis can significantly improve radiologists’ accuracy in classification of masses and thereby may increase the positive predictive value of mammography.

Paper Details

Date Published: 15 May 2003
PDF: 8 pages
Proc. SPIE 5032, Medical Imaging 2003: Image Processing, (15 May 2003); doi: 10.1117/12.483549
Show Author Affiliations
Lubomir M. Hadjiiski, Univ. of Michigan (United States)
Heang-Ping Chan, Univ. of Michigan (United States)
Berkman Sahiner, Univ. of Michigan (United States)
Mark A. Helvie, Univ. of Michigan (United States)
Marilyn A. Roubidoux, Univ. of Michigan (United States)
Caroline E. Blane, Univ. of Michigan (United States)
Chintana Paramagul, Univ. of Michigan (United States)
Nicholas Petrick, FDA Ctr. for Devices and Radiological Health (United States)
Janet E. Bailey, Univ. of Michigan (United States)
Katherine Klein, Univ. of Michigan (United States)
Michelle Foster, Univ. of Michigan (United States)
Stephanie Patterson, Univ. of Michigan (United States)
Dorit D. Adler, Univ. of Michigan (United States)
Alexis Nees, Univ. of Michigan (United States)
Joseph Shen, Univ. of Michigan (United States)

Published in SPIE Proceedings Vol. 5032:
Medical Imaging 2003: Image Processing
Milan Sonka; J. Michael Fitzpatrick, Editor(s)

© SPIE. Terms of Use
Back to Top