Share Email Print

Proceedings Paper

Objective Measures To Evaluate The Performance Of Reconstruction Algorithms
Author(s): K. T. D. Yeung; G. T. Herman
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The relationships of three objective performance measures for the evaluation of image reconstruction algorithms are presented. Two of them are physical metrics - distance and relative error. The third is a numerical observer performance measure. In a demonstration project, three reconstruction algorithms are evaluated on the basis of a specific task using the above measures. Based on a similarity measure between the rank orderings of 30 reconstructions by the performance measures, relative error is seen to have a significant similarity to numerical observer performance. The similarity between distance and numerical observer performance is considerably less. The following hypothesis appears to be worthy of further investigation: judicious use of simple physical metrics, in place of more elaborate and complicated measures, can in certain circumstances be an attractive alternative method for evaluating image reconstruction algorithms.

Paper Details

Date Published: 25 May 1989
PDF: 12 pages
Proc. SPIE 1092, Medical Imaging III: Image Processing, (25 May 1989);
Show Author Affiliations
K. T. D. Yeung, University of Pennsylvania (United States)
G. T. Herman, University of Pennsylvania (United States)

Published in SPIE Proceedings Vol. 1092:
Medical Imaging III: Image Processing
Samuel J. Dwyer III; R. Gilbert Jost M.D.; Roger H. Schneider, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?