Share Email Print
cover

Journal of Medical Imaging

Parenchymal texture analysis in digital mammography: robust texture feature identification and equivalence across devices
Author(s): Brad M. Keller; Andrew Oustimov; Yan Wang; Jinbo Chen; Raymond J. Acciavatti; Yuanjie Zheng; Shonket Ray; James C. Gee; Andrew D. A. Maidment; Despina Kontos
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An analytical framework is presented for evaluating the equivalence of parenchymal texture features across different full-field digital mammography (FFDM) systems using a physical breast phantom. Phantom images (FOR PROCESSING) are acquired from three FFDM systems using their automated exposure control setting. A panel of texture features, including gray-level histogram, co-occurrence, run length, and structural descriptors, are extracted. To identify features that are robust across imaging systems, a series of equivalence tests are performed on the feature distributions, in which the extent of their intersystem variation is compared to their intrasystem variation via the Hodges–Lehmann test statistic. Overall, histogram and structural features tend to be most robust across all systems, and certain features, such as edge enhancement, tend to be more robust to intergenerational differences between detectors of a single vendor than to intervendor differences. Texture features extracted from larger regions of interest (i.e., <63  pixels2) and with a larger offset length (i.e., <7  pixels), when applicable, also appear to be more robust across imaging systems. This framework and observations from our experiments may benefit applications utilizing mammographic texture analysis on images acquired in multivendor settings, such as in multicenter studies of computer-aided detection and breast cancer risk assessment.

Paper Details

Date Published: 3 April 2015
PDF: 13 pages
J. Med. Img. 2(2) 024501 doi: 10.1117/1.JMI.2.2.024501
Published in: Journal of Medical Imaging Volume 2, Issue 2
Show Author Affiliations
Brad M. Keller, Univ. of Pennsylvania School of Medicine (United States)
Andrew Oustimov, Univ. of Pennsylvania School of Medicine (United States)
Yan Wang, Univ. of Pennsylvania School of Medicine (United States)
Jinbo Chen, Univ. of Pennsylvania School of Medicine (United States)
Raymond J. Acciavatti, The Univ. of Pennsylvania Health System (United States)
Yuanjie Zheng, The Univ. of Pennsylvania Health System (United States)
Shonket Ray, Univ. of Pennsylvania School of Medicine (United States)
James C. Gee, Univ. of Pennsylvania (United States)
Andrew D. A. Maidment, The Univ. of Pennsylvania Health System (United States)
Despina Kontos, The Univ. of Pennsylvania Health System (United States)


© SPIE. Terms of Use
Back to Top