Share Email Print

Proceedings Paper

Spatially aware expectation maximization (SpAEM): application to prostate TRUS segmentation
Author(s): Mahdi Orooji; Rachel Sparks; B. Nicolas Bloch; Ernest Feleppa; Dean Barratt; Anant Madabhushi
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper we introduce Spatially Aware Expectation Maximization (SpAEM), a new parameter estimation method which incorporates information pertaining to spatial prior probability into the traditional expectation- maximization framework. For estimating the parameters of a given class, the spatial prior probability allows us to weight the contribution of any pixel based on the probability of that pixel belonging to the class of interest. In this paper we evaluate SpAEM for the problem of prostate capsule segmentation in transrectal ultrasound (TRUS) images. In cohort of 6 patients, SpAEM qualitatively and quantitatively outperforms traditional EM in distinguishing the foreground (prostate) from background (non-prostate) regions by around 45% in terms of the Sorensen Dice overlap measure, when compared against expert annotations. The variance of the estimated parameters measured via Cramer-Rao Lower Bound suggests that SpAEM yields unbiased estimates. Finally, on a synthetic TRUS image, the Cramer-Von Mises (CVM) criteria shows that SpAEM improves the estimation accuracy by around 51% and 88% for prostate and background, respectively, as compared to traditional EM.

Paper Details

Date Published: 21 March 2014
PDF: 13 pages
Proc. SPIE 9034, Medical Imaging 2014: Image Processing, 90343Y (21 March 2014); doi: 10.1117/12.2043981
Show Author Affiliations
Mahdi Orooji, Case Western Reserve Univ. (United States)
Rachel Sparks, Univ. College London (United Kingdom)
B. Nicolas Bloch, Boston Medical Ctr. and Boston Univ. (United States)
Ernest Feleppa, Lizzi Ctr. for Biomedical Engineering, Riverside Research Institute (United States)
Dean Barratt, Univ. College London (United Kingdom)
Anant Madabhushi, Case Western Reserve Univ. (United States)

Published in SPIE Proceedings Vol. 9034:
Medical Imaging 2014: Image Processing
Sebastien Ourselin; Martin A. Styner, Editor(s)

© SPIE. Terms of Use
Back to Top