Share Email Print
cover

Proceedings Paper

Integrating knowledge representation/engineering, the multivariant PNN, and machine learning to improve breast cancer diagnosis
Author(s): Walker H. Land; Mark J. Embrechts; Frances R. Anderson; Tom Smith; Lut Wong; Steve Fahlbusch; Robert Choma
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Breast cancer is second only to lung cancer as a tumor-related cause of death in women. Currently, the method of choice for the early detection of breast cancer is mammography. While sensitive to the detection of breast cancer, its positive predictive value (PPV) is low. One of the main deterrents to achieving high computer aided diagnostic (CAD) accuracy is carelessly developed databases. These “noisy” data sets have always appeared to disrupt learning agents from learning correctly. A new statistical method for cleaning data sets was developed that improves the performance of CAD systems. Initial research efforts showed the following: PLS Az value improved by 8.79% and partial Az improved by 49.71%. The K-PLS Az value at Sigma 4.1 improved by 9.18% and the partial Az by 43.47%. The K-PLS at Sigma 3.6 (best fit sigma with this data set) Az value improved by 9.24% and the partial Az by 44.29%. With larger data sets, the ROC curves potentially could look much better than they do now. The Az value for K-PLS (0.892565) is better than PLS, PNN, and most SVMs. The SVM-rbf kernel was the only agent that out performed the K-PLS with an Az value of 0.895362. However, K-PLS runs much faster and appears to be just as accurate as the SVM-rbf kernel.

Paper Details

Date Published: 28 March 2005
PDF: 6 pages
Proc. SPIE 5812, Data Mining, Intrusion Detection, Information Assurance, and Data Networks Security 2005, (28 March 2005); doi: 10.1117/12.604575
Show Author Affiliations
Walker H. Land, Binghamton Univ. (United States)
Mark J. Embrechts, Rensselaer Polytechnic Institute (United States)
Frances R. Anderson, Lourdes Hospital and Regional Cancer Ctr. (United States)
Tom Smith, Binghamton Univ. (United States)
Lut Wong, Binghamton Univ. (United States)
Steve Fahlbusch, Binghamton Univ. (United States)
Robert Choma, Binghamton Univ. (United States)


Published in SPIE Proceedings Vol. 5812:
Data Mining, Intrusion Detection, Information Assurance, and Data Networks Security 2005
Belur V. Dasarathy, Editor(s)

© SPIE. Terms of Use
Back to Top