Share Email Print

Proceedings Paper

Characterization of masses on mammograms: significance of using the rubber band straightening transform
Author(s): Berkman Sahiner; Heang-Ping Chan; Nicholas Petrick; Mitchell M. Goodsitt; Mark A. Helvie
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The rubber-band straightening transform (RBST) was developed for characterization of mammographic masses as malignant or benign. The RBST maps a region surrounding a segmented mass on a mammogram onto the Cartesian plane. In this study, the effectiveness of texture features extracted from the RBST images was compared with the effectiveness of those extracted from the original images. Texture features were extracted from (1) a region of interest (ROI) centered at the mass; (2) a 40-pixel-wide gray-scale region surrounding the perimeter of the mass; and (3) the RBST image. Two types of texture features were extracted; spatial gray level dependence (SGLD) features and run-length statistics (RLS) features. Linear discriminant analysis and leave-one-case- out methods were used for classification in the individual or combined feature spaces. The classification accuracy was evaluated by receiver operating characteristic (ROC) analysis and the area Az under the ROC curve. CLABROC analysis was used to estimate the statistical significance of the difference between features extracted using the three different approaches. On a database of 255 ROIs containing biopsy-proven masses, the Az value was 0.92 when combined SGLD and RLS features extracted from RBST images were used for classification. In comparison, the combined texture features extracted from the entire ROIs and the mass perimeter regions resulted in Az values of 0.83 and 0.85, respectively. The improvement in Az obtained by using RBST images was statistically significant (p less than 0.05). Similar levels of significance were observed when the classification was performed in the SGLD feature space alone or the RLS feature space alone.

Paper Details

Date Published: 25 April 1997
PDF: 10 pages
Proc. SPIE 3034, Medical Imaging 1997: Image Processing, (25 April 1997); doi: 10.1117/12.274135
Show Author Affiliations
Berkman Sahiner, Univ. of Michigan (United States)
Heang-Ping Chan, Univ. of Michigan (United States)
Nicholas Petrick, Univ. of Michigan (United States)
Mitchell M. Goodsitt, Univ. of Michigan (United States)
Mark A. Helvie, Univ. of Michigan (United States)

Published in SPIE Proceedings Vol. 3034:
Medical Imaging 1997: Image Processing
Kenneth M. Hanson, Editor(s)

© SPIE. Terms of Use
Back to Top