Share Email Print
cover

Proceedings Paper

A Naive-Bayes model observer for detection and localization of perfusion defects in cardiac SPECT-MPI
Author(s): Felipe M. Parages; J. Michael O’Connor; P. Hendrik Pretorius; Jovan G. Brankov
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 SPECT myocardial perfusion imaging (MPI), a realistic task-based approach involves detection and localization of perfusion defects, as well as a subsequent assessment of defect severity. In this paper we explore a machine-learning MO based on Naive- Bayes classification (NB-MO). NB-MO uses a set of polar-map image features to predict lesion detection, localization and severity scores given by five human readers for a set of simulated 3D SPECT-MPI patients. The simulated dataset included lesions with different sizes, perfusion-reduction ratios, and locations. Simulated projections were reconstructed using two readily used methods namely: FBP and OSEM. For validation, a multireader multi-case (MRMC) analysis of alternative free-response ROC (AFROC) curve was performed for NB-MO and human observers. For comparison, we also report performances of a statistical Hotelling Observer applied on polar-map images. Results show excellent agreement between NB-MO and humans, as well as model’s good generalization between different reconstruction treatments.

Paper Details

Date Published: 11 March 2014
PDF: 7 pages
Proc. SPIE 9037, Medical Imaging 2014: Image Perception, Observer Performance, and Technology Assessment, 90370N (11 March 2014); doi: 10.1117/12.2044441
Show Author Affiliations
Felipe M. Parages, Illinois Institute of Technology (United States)
J. Michael O’Connor, Univ. of Massachusetts Medical School (United States)
Univ. of Massachusetts Lowell (United States)
P. Hendrik Pretorius, Univ. of Massachusetts Medical School (United States)
Jovan G. Brankov, Illinois Institute of Technology (United States)


Published in SPIE Proceedings Vol. 9037:
Medical Imaging 2014: Image Perception, Observer Performance, and Technology Assessment
Claudia R. Mello-Thoms; Matthew A. Kupinski, Editor(s)

© SPIE. Terms of Use
Back to Top