Share Email Print
cover

Proceedings Paper

Evaluation of CNN as anthropomorphic model observer
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

Model observers (MO) are widely used in medical imaging to act as surrogates of human observers in task-based image quality evaluation, frequently towards optimization of reconstruction algorithms. In this paper, we explore the use of convolutional neural networks (CNN) to be used as MO. We will compare CNN MO to alternative MO currently being proposed and used such as the relevance vector machine based MO and channelized Hotelling observer (CHO). As the success of the CNN, and other deep learning approaches, is rooted in large data sets availability, which is rarely the case in medical imaging systems task-performance evaluation, we will evaluate CNN performance on both large and small training data sets.

Paper Details

Date Published: 10 March 2017
PDF: 7 pages
Proc. SPIE 10136, Medical Imaging 2017: Image Perception, Observer Performance, and Technology Assessment, 101360Q (10 March 2017); doi: 10.1117/12.2254603
Show Author Affiliations
Francesc Massanes, Illinois Institute of Technology (United States)
Jovan G. Brankov, Illinois Institute of Technology (United States)


Published in SPIE Proceedings Vol. 10136:
Medical Imaging 2017: Image Perception, Observer Performance, and Technology Assessment
Matthew A. Kupinski; Robert M. Nishikawa, Editor(s)

© SPIE. Terms of Use
Back to Top