Share Email Print

Proceedings Paper

Multiresolution neural networks for mammographic mass detection
Author(s): Clay D. Spence; Paul Sajda
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

We have previously presented a hierarchical pyramid/neural network (HPNN) architecture which combines multi-scale image processing techniques with neural networks. This coarse-to- fine HPNN was designed to learn large-scale context information for detecting small objects. We have developed a similar architecture to detect mammographic masses (malignant tumors). Since masses are large, extended objects, the coarse-to-fine HPNN architecture is not suitable for the problem. Instead we constructed a fine-to- coarse HPNN architecture which is designed to learn small- scale detail structure associated with the extended objects. Our initial result applying the fine-to-coarse HPNN to mass detection are encouraging, with detection performance improvements of about 30%. We conclude that the ability of the HPNN architecture to integrate information across scales, from fine to coarse in the case of masses, makes it well suited for detecting objects which may have detail structure occurring at scales other than the natural scale of the object.

Paper Details

Date Published: 29 January 1999
PDF: 7 pages
Proc. SPIE 3584, 27th AIPR Workshop: Advances in Computer-Assisted Recognition, (29 January 1999); doi: 10.1117/12.339829
Show Author Affiliations
Clay D. Spence, Sarnoff Corp. (United States)
Paul Sajda, Sarnoff Corp. (United States)

Published in SPIE Proceedings Vol. 3584:
27th AIPR Workshop: Advances in Computer-Assisted Recognition
Robert J. Mericsko, Editor(s)

© SPIE. Terms of Use
Back to Top