Share Email Print

Proceedings Paper

A novel technique for assessing the case-specific reliability of decisions made by CAD tools
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 present a novel technique that provides a case-specific confidence measure for artificial neural network (ANN) based computer-assisted diagnostic (CAD) decisions. The technique relies on the analysis of the feature space neighborhood for each query case and dynamically creates a validation set that allows estimation of a local accuracy of the decisions made by the network. Then a case-specific reliability measure is assigned to each system's response, which can be used to stratify network's predictions according to the acceptable validation error value. The study was performed using a database containing 1,337 mammographic regions of interest (ROIs) with biopsy-proven diagnosis (681 with masses, 656 with normal parenchyma). Two types of neural networks (1) a feed forward network with error back propagation (BPNN) and (2) a generalized regression neural network with RBF nodes (GRNN) were developed to detect masses based on 8 morphological features automatically extracted from each ROI. The performance of the networks was evaluated with Receiver Operating Characteristics (ROC) analysis. The study shows that as the threshold on the acceptable validation error declines, the technique rejects more CAD decisions as not reliable enough. However, the ROC performance for the reliable results steadily improves (from Az = 0.88 to Az = 0.98 for BPNN, from Az = 0.86 to Az = 0.97 for GRNN). The proposed technique provides a stratification strategy for predictions made by CAD tools and can be applied to any type of decision algorithms.

Paper Details

Date Published: 29 April 2005
PDF: 8 pages
Proc. SPIE 5747, Medical Imaging 2005: Image Processing, (29 April 2005); doi: 10.1117/12.595597
Show Author Affiliations
Piotr A. Habas, Univ. of Louisville (United States)
Georgia D. Tourassi, Duke Univ. Medical Center (United States)
Nevine H. Eltonsy, Univ. of Louisville (United States)
Adel S. Elmaghraby, Univ. of Louisville (United States)
Jacek M Zurada, Univ. of Louisville (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