JSM 2015 Online Program

Online Program Home
My Program

Abstract Details

Activity Number: 128
Type: Contributed
Date/Time: Monday, August 10, 2015 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics in Imaging
Abstract #317146 View Presentation
Title: Quantitative Lung Image Analysis Using a Spatial Point Process Framework
Author(s): Brian Vestal* and Nichole Carlson
Companies: University of Colorado Denver and University of Colorado Anshutz Medical Campus
Keywords: COPDGene

Recently there has been a movement towards augmenting visual assessment of medical images with more automated computer based tools. Here we propose a new method for quantitative image analysis of lung Computed Tomography (CT) scans in an effort to better differentiate underlying disease etiology. We frame our problem as a spatial Cox cluster process where events are the voxels that meet a clinically derived criteria for being diseased. Under a Bayesian setting we use spatial birth-death MCMC to characterize clusters of diseased tissue. From the posterior distributions of model parameters we are able to create clinically relevant summary measures that describe the clustering of events in an individual scan. These measures can then be considered as a quantitative phenotype and associated with other clinical data or used as covariates in classification models in an effort to discriminate between, or potentially discover, disease subtypes. A simulation study that shows the feasibility of our model fitting algorithm and initial results from an example application of the method exploring the spatial distribution of emphysema in CT scans from the COPDGene cohort will be presented.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2015 program

For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

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

2015 JSM Online Program Home