JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home
My Program

Abstract Details

Activity Number: 588
Type: Invited
Date/Time: Thursday, August 2, 2012 : 8:30 AM to 10:20 AM
Sponsor: Biopharmaceutical Section
Abstract - #303868
Title: Modeling and Inference in Medical Image Analysis
Author(s): William Mercer Wells III*+
Companies: Harvard Medical School/Brigham and Women's Hospital
Address: 75 Francis St., Boston, MA, 02115, USA
Keywords: medical ; image ; segmentation ; registration
Abstract:

Before we can do meaningful statistics on medical images, we usually need to perform a substantial amount of post-processing to reveal the useful information that is latent in the images.

This talk will provide a historically-organized overview of probabilistic modeling and inference in medical image analysis. For each method discussed, in addition to showing typical results, I will summarize the background, and where appropriate, illustrate the basic mechanisms involved by way of probabilistic graphical models.

Topics will be drawn from the broad categories of segmentation, the process of labeling the contents of images, and registration, the process of bringing medical images into geometric agreement, as well as the analysis of functional brain images. The application areas include disease focused research in humans and animals, and the translation of algorithms into clinical use in image-guided neurosurgery.

Specific topics will illustrate ML and MAP formulations, the use of atlas-based prior models, minimum-entropy and maximum mutual-information methods, and MCMC methods for estimating posterior distributions.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2012 program




2012 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.