Share Email Print
cover

Proceedings Paper

Multinetwork classification scheme for detection of colonic polyps in CT colonography data sets
Author(s): Anna K. Jerebko; James D. Malley; Marek Franaszek; Ronald M. Summers
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A multi-network decision classification scheme for colonic polyp detection is presented. The approach is based on the results of voting over several neural networks using different variable sets of size N which are selected randomly or by an expert from a general variable set of size M. Detection of colonic polyps is complicated by a large variety of polypoid looking shapes (haustral folds, leftover stool) on the colon surface. Using various shape and curvature characteristics, intensity, size measurements and texture features to distinguish real polyps from false positives leads to an intricate classification problem. We used 17 features including region density, Gaussian and average curvature and sphericity, lesion size, colon wall thickness, and their means and standard deviations in the vicinity of the prospective polyp. Selection of the most important parameters to reduce a feature set to acceptable size is a generally unsolved problem. The method suggested in this paper uses a collection of subsets of variables. These sets of variables are weighted by their effectiveness. The effectiveness cost function is calculated on the basis of the training and test sample mis-classification rates obtained by the training neural net with the given variable set. The final decision is based on the majority vote across the networks generated using the variable subsets, and takes into account the weighted votes of all nets. This method reduces the flst positive rate by a factor of 1.7 compared to single net decisions. The overall sensitivity and specificity rates reached are 100% and 95% correspondingly. Best specificity and sensitivity rates were reached using back propagation neural nets with one hidden layer trained with the Levenberg-Marquardt algorithm. Ten-fold cross-validation is used to better estimate the true error rates.

Paper Details

Date Published: 24 April 2002
PDF: 6 pages
Proc. SPIE 4683, Medical Imaging 2002: Physiology and Function from Multidimensional Images, (24 April 2002); doi: 10.1117/12.463584
Show Author Affiliations
Anna K. Jerebko, National Institutes of Health (United States)
James D. Malley, National Institutes of Health (United States)
Marek Franaszek, National Institutes of Health (United States)
Ronald M. Summers, National Institutes of Health (United States)


Published in SPIE Proceedings Vol. 4683:
Medical Imaging 2002: Physiology and Function from Multidimensional Images
Anne V. Clough; Chin-Tu Chen, Editor(s)

© SPIE. Terms of Use
Back to Top