Using Fisher information to approximate ideal-observer performance on detection tasks for lumpy-background images

Fangfang Shen1, Eric Clarkson

  • 1Department of Radiology, University of Arizona, Tucson 85724-5067, USA.

Summary

This study introduces a computationally efficient approximation for evaluating Bayesian ideal observer performance in medical imaging systems. The Fisher information matrix provides a reliable figure of merit for system evaluation and links detection and estimation tasks.