Extraction of Airways with Probabilistic State-Space Models and Bayesian Smoothing

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

Segmenting tree structures is common in several image processing applications. In medical image analysis, reliable segmentations of airways, vessels, neurons and other tree structures can enable important clinical. applications. We present a framework for tracking tree structures comprising of elongated branches using probabilistic state-space models and Bayesian smoothing. Unlike most existing methods that proceed with sequential tracking of branches, we present an exploratory method, that is less sensitive to local anomalies in the data due to acquisition noise and/or interfering structures. The evolution of individual branches is modelled using a process model and the observed data is incorporated into the update step of the Bayesian smoother using a measurement model that is based on a multi-scale blob detector. Bayesian smoothing is performed using the RTS (Rauch-Tung-Striebel) smoother, which provides Gaussian density estimates of branch states at each tracking step. We select likely branch seed points automatically based on the response of the blob detection and track from all such seed points using the RTS smoother. We use covariance of the marginal posterior density estimated for each branch to discriminate false positive and true positive branches. The method is evaluated on 3D chest CT scans to track airways. We show that the presented method results in additional branches compared to a baseline method based on region growing on probability images

Original languageEnglish
Title of host publicationGraphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics : First International Workshop, GRAIL 2017, 6th International Workshop, MFCA 2017, and Third International Workshop, MICGen 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10–14, 2017, Proceedings
EditorsM. Jorge Cardoso, Tal Arbel, Enzo Ferrante, Xavier Pennec, Adrian V. Dalca, Sarah Parisot, Sarang Joshi, Nematollah K. Batmanghelich, Aristeidis Sotiras, Mads Nielsen, Mert R. Sabuncu, Tom Fletcher, Li Shen, Stanley Durrleman, Stefan Sommer
PublisherSpringer
Publication date2017
Pages53-63
ISBN (Print)978-3-319-67674-6
ISBN (Electronic)978-3-319-67675-3
DOIs
Publication statusPublished - 2017
Event1st International Workshop on Graphs in Biomedical Image Analysis (GRAIL) / 6th International Workshop on Mathematical Foundations of Computational Anatomy (MFCA) / 3rd International Workshop on Imaging Genetics (MICGen) - Quebec, Canada
Duration: 10 Sep 201714 Sep 2017

Conference

Conference1st International Workshop on Graphs in Biomedical Image Analysis (GRAIL) / 6th International Workshop on Mathematical Foundations of Computational Anatomy (MFCA) / 3rd International Workshop on Imaging Genetics (MICGen)
LandCanada
ByQuebec
Periode10/09/201714/09/2017
SeriesLecture notes in computer science
Volume10551
ISSN0302-9743

    Research areas

  • Probabilistic state-space, Bayesian smoothing, Tree segmentation, Airways, CT, SEGMENTATION

Links

ID: 184144076