Quantifying emphysema extent from weakly labeled CT scans of the lungs using label proportions learning

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Documents

Silas Nyboe Ørting, Jens Petersen, Mathilde Wille, Laura Thomsen, Marleen de Bruijne

Quantification of emphysema extent is important in diagnosing and monitoring patients with chronic obstructive pulmonary disease (COPD). Several studies have shown that emphysema quantification by supervised texture classification is more robust and accurate than traditional densitometry. Current techniques require highly time consuming manual annotations of patches or use only weak labels indicating overall disease status (e.g, COPD or healthy). We show how visual scoring of regional emphysema extent can be exploited in a learning with label proportions (LLP) framework to both predict presence of emphysema in smaller patches and estimate regional extent. We evaluate performance on 195 visually scored CT scans and achieve an intraclass correlation of 0.72 (0.65–0.78) between predicted region extent and expert raters. To our knowledge this is the first time that LLP methods have been applied to medical imaging data.
Original languageEnglish
Title of host publicationThe Sixth International Workshop on Pulmonary Image Analysis
EditorsReinhard R. Beichel, Keyvan Farahani, Colin Jacobs, Sven Kabus, Atilla P. Kiraly, Jan-Martin Kuhnigk, Jamie R. McClelland, Kensaku Mori, Jens Petersen, Simon Rit
Number of pages11
PublisherCreateSpace Independent Publishing Platform
Publication date2016
Pages31-42
ISBN (Print)978-1537038582
Publication statusPublished - 2016
EventSixth International Workshop on Pulmonary Image Analysis - Athen, Greece
Duration: 21 Oct 201621 Oct 2016
Conference number: 6

Conference

ConferenceSixth International Workshop on Pulmonary Image Analysis
Nummer6
LandGreece
ByAthen
Periode21/10/201621/10/2016

Number of downloads are based on statistics from Google Scholar and www.ku.dk


No data available

ID: 167582102