Share Email Print
cover

Proceedings Paper

Derivative-based feature saliency for computer-aided breast cancer detection and diagnosis
Author(s): William E. Polakowski; Steven K. Rogers; Dennis W. Ruck; Richard A. Raines; Jeffrey W. Hoffmeister
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Derivative-based feature saliency techniques were used to define the best of 25 Laws texture features for the classification of 101 malignant mass and benign mass regions. Statistical and derivative-based saliency techniques were used to select the best size, shape, contrast, and Laws texture features for the mass model. Nine features were chosen to define the model, of which four have been used by other researchers. Using this model, the regions were classified using a multilayer perceptron neural network architecture trained with an imbalanced training set weight update algorithm to obtain an overall classification accuracy of 100 percent for the segmented malignant masses with a false-positive rates of 1.8/image. The system has shown a sensitivity of 92 percent for locating malignant ROIs. The database contained 284 images (12 bit, 100 micrometers ).

Paper Details

Date Published: 22 March 1996
PDF: 12 pages
Proc. SPIE 2760, Applications and Science of Artificial Neural Networks II, (22 March 1996); doi: 10.1117/12.235922
Show Author Affiliations
William E. Polakowski, Air Force Institute of Technology (United States)
Steven K. Rogers, Air Force Institute of Technology (United States)
Dennis W. Ruck, Air Force Institute of Technology (United States)
Richard A. Raines, Air Force Institute of Technology (United States)
Jeffrey W. Hoffmeister, Air Force Armstrong Labs. (United States)


Published in SPIE Proceedings Vol. 2760:
Applications and Science of Artificial Neural Networks II
Steven K. Rogers; Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top