Share Email Print
cover

Proceedings Paper

Exploiting context in mammograms: a hierarchical neural network for detecting microcalcifications
Author(s): Paul Sajda; Clay D. Spence; John C. Pearson; Robert M. Nishikawa
Format Member Price Non-Member Price
PDF $14.40 $18.00
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

Microcalcifications are important cues used by radiologists for early detection in breast cancer. Individually, microcalcifications are difficult to detect, and often contextual information (e.g. clustering, location relative to ducts) can be exploited to aid in their detection. We have developed an algorithm for constructing a hierarchical pyramid/neural network (HPNN) architecture to automatically learn context information for detection. To test the HPNN we first examined if the hierarchical architecture improves detection of individual microcalcifications and if context is in fact extracted by the network hierarchy. We compared the performance of our hierarchical architecture versus a single neural network receiving input from all resolutions of a feature pyramid. Receiver operator characteristic (ROC) analysis shows that the hierarchical architecture reduces false positives by a factor of two. We examined hidden units at various levels of the processing hierarchy and found what appears to be representations of ductal location. We next investigated the utility of the HPNN if integrated as part of a complete computer-aided diagnosis (CAD) system for microcalcification detection, such as that being developed at the University of Chicago. Using ROC analysis, we tested the HPNN's ability to eliminate false positive regions of interest generated by the computer, comparing its performance to the neural network currently used in the Chicago system. The HPNN achieves an area under the ROC curve of Az equal to .94 and a false positive fraction of FPF equal to .21 at TPF equals 1.0. This is in comparison to the results reported for the Chicago network; Az equal to .91, FPF equal to .43 at TPF equal to 1.0. These differences are statistically significant. We conclude that the HPNN algorithm is able to utilize contextual information for improving microcalcifications detection and potentially reduce the false positive rates in CAD systems.

Paper Details

Date Published: 16 April 1996
PDF: 10 pages
Proc. SPIE 2710, Medical Imaging 1996: Image Processing, (16 April 1996); doi: 10.1117/12.237978
Show Author Affiliations
Paul Sajda, David Sarnoff Research Ctr. (United States)
Clay D. Spence, David Sarnoff Research Ctr. (United States)
John C. Pearson, David Sarnoff Research Ctr. (United States)
Robert M. Nishikawa, Univ. of Chicago (United States)


Published in SPIE Proceedings Vol. 2710:
Medical Imaging 1996: Image Processing
Murray H. Loew; Kenneth M. Hanson, Editor(s)

© SPIE. Terms of Use
Back to Top