Share Email Print
cover

Proceedings Paper

Applying knowledge engineering and representation methods to improve support vector machine and multivariate probabilistic neural network CAD performance
Author(s): Walker H. Land; Frances Anderson; Tom Smith; Stephen Fahlbusch; Robert Choma; Lut Wong
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Achieving consistent and correct database cases is crucial to the correct evaluation of any computer-assisted diagnostic (CAD) paradigm. This paper describes the application of artificial intelligence (AI), knowledge engineering (KE) and knowledge representation (KR) to a data set of ≈2500 cases from six separate hospitals, with the objective of removing/reducing inconsistent outlier data. Several support vector machine (SVM) kernels were used to measure diagnostic performance of the original and a “cleaned” data set. Specifically, KE and ER principles were applied to the two data sets which were re-examined with respect to the environment and agents. One data set was found to contain 25 non-characterizable sets. The other data set contained 180 non-characterizable sets. CAD system performance was measured with both the original and “cleaned” data sets using two SVM kernels as well as a multivariate probabilistic neural network (PNN). Results demonstrated: (i) a 10% average improvement in overall Az and (ii) approximately a 50% average improvement in partial Az.

Paper Details

Date Published: 29 April 2005
PDF: 7 pages
Proc. SPIE 5747, Medical Imaging 2005: Image Processing, (29 April 2005); doi: 10.1117/12.593683
Show Author Affiliations
Walker H. Land, Binghamton Univ. (United States)
Frances Anderson, Lourdes Hospital and Regional Cancer Ctr. (United States)
Tom Smith, Binghamton Univ. (United States)
Stephen Fahlbusch, Binghamton Univ. (United States)
Robert Choma, Binghamton Univ. (United States)
Lut Wong, Binghamton Univ. (United States)


Published in SPIE Proceedings Vol. 5747:
Medical Imaging 2005: Image Processing
J. Michael Fitzpatrick; Joseph M. Reinhardt, Editor(s)

© SPIE. Terms of Use
Back to Top