Share Email Print

Proceedings Paper

Learning the ideal observer for SKE detection tasks by use of convolutional neural networks (Cum Laude Poster Award)
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

It has been advocated that task-based measures of image quality (IQ) should be employed to evaluate and optimize imaging systems. Task-based measures of IQ quantify the performance of an observer on a medically relevant task. The Bayesian Ideal Observer (IO), which employs complete statistical information of the object and noise, achieves the upper limit of the performance for a binary signal classification task. However, computing the IO performance is generally analytically intractable and can be computationally burdensome when Markov-chain Monte Carlo (MCMC) techniques are employed. In this paper, supervised learning with convolutional neural networks (CNNs) is employed to approximate the IO test statistics for a signal-known-exactly and background-known-exactly (SKE/BKE) binary detection task. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) are compared to those produced by the analytically computed IO. The advantages of the proposed supervised learning approach for approximating the IO are demonstrated.

Paper Details

Date Published: 7 March 2018
PDF: 6 pages
Proc. SPIE 10577, Medical Imaging 2018: Image Perception, Observer Performance, and Technology Assessment, 1057719 (7 March 2018); doi: 10.1117/12.2293772
Show Author Affiliations
Weimin Zhou, Washington Univ. in St. Louis (United States)
Mark A. Anastasio, Washington Univ. in St. Louis (United States)

Published in SPIE Proceedings Vol. 10577:
Medical Imaging 2018: Image Perception, Observer Performance, and Technology Assessment
Robert M. Nishikawa; Frank W. Samuelson, 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?