Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study

Jie Yang; Elsa D Angelini; Benjamin M Smith; John H M Austin; Eric A Hoffman; David A Bluemke; R Graham Barr; Andrew F Laine

doi:10.1007/978-3-319-61188-4_7

Back

Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study

Conference proceeding

Peer reviewed

Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study

Jie Yang, Elsa D Angelini, Benjamin M Smith, John H M Austin, Eric A Hoffman, David A Bluemke, R Graham Barr and Andrew F Laine

Medical computer vision and Bayesian and graphical models for biomedical imaging : MICCAI 2016 international workshop, MCV and BAMBI, Athens, Greece, October 21, 2016 : revised selected papers, Vol.2017, pp.69-80

2017

DOI: 10.1007/978-3-319-61188-4_7

PMCID: PMC5708576

PMID: 29202136

Files and links (1)

url

http://doi.org/10.1007/978-3-319-61188-4_7View

Open Access

Abstract

Pulmonary emphysema is traditionally subcategorized into three subtypes, which have distinct radiological appearances on computed tomography (CT) and can help with the diagnosis of chronic obstructive pulmonary disease (COPD). Automated texture-based quantification of emphysema subtypes has been successfully implemented via supervised learning of these three emphysema subtypes. In this work, we demonstrate that unsupervised learning on a large heterogeneous database of CT scans can generate texture prototypes that are visually homogeneous and distinct, reproducible across subjects, and capable of predicting accurately the three standard radiological subtypes. These texture prototypes enable automated labeling of lung volumes, and open the way to new interpretations of lung CT scans with finer subtyping of emphysema.

Details

Title: Subtitle: Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study
Creators: Jie Yang - Dept. of Biomedical Engineering, Columbia University, New York, NY, USA
Elsa D Angelini - Dept. of Radiology, Columbia University Medical Center, New York, NY, USA
Benjamin M Smith - Dept. of Medicine, McGill University Health Center, Montreal, QC, Canada
John H M Austin - Dept. of Radiology, Columbia University Medical Center, New York, NY, USA
Eric A Hoffman - Dept. of Biomedical Engineering, University of Iowa, Iowa City, IA, USA
David A Bluemke - Radiology and Imaging Sciences, National Institutes of Health, Bethesda, MD
R Graham Barr - Dept. of Epidemiology, Columbia University Medical Center, New York, NY, USA
Andrew F Laine - Dept. of Biomedical Engineering, Columbia University, New York, NY, USA
Resource Type: Conference proceeding
Publication Details: Medical computer vision and Bayesian and graphical models for biomedical imaging : MICCAI 2016 international workshop, MCV and BAMBI, Athens, Greece, October 21, 2016 : revised selected papers, Vol.2017, pp.69-80
DOI: 10.1007/978-3-319-61188-4_7
PMID: 29202136
PMCID: PMC5708576
eISBN: 9783319611884; 3319611887
ISSN: 0302-9743
eISSN: 1611-3349
Publisher: Switzerland
Grant note: N01HC95159 / NHLBI NIH HHS N01HC95169 / NHLBI NIH HHS N01 HC095159 / NHLBI NIH HHS UL1 RR025005 / NCRR NIH HHS UL1 RR024156 / NCRR NIH HHS R01 HL077612 / NHLBI NIH HHS R01 HL093081 / NHLBI NIH HHS N01 HC095169 / NHLBI NIH HHS R01 HL112986 / NHLBI NIH HHS R01 HL121270 / NHLBI NIH HHS P30 DK054759 / NIDDK NIH HHS RC1 HL100543 / NHLBI NIH HHS
Language: English
Date published: 2017
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Internal Medicine
Record Identifier: 9984051515002771

Metrics

29 Record Views

4 Times Cited - Web of Science