Extraction of airways with probabilistic state-space models and Bayesian smoothing

TY - GEN

T1 - Extraction of airways with probabilistic state-space models and Bayesian smoothing

AU - Raghavendra, Selvan

AU - Petersen, Jens

AU - Pedersen, Jesper Johannes Holst

AU - de Bruijne, Marleen

N1 - Conference code: 1

PY - 2017

Y1 - 2017

N2 - 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

AB - 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

U2 - 10.1007/978-3-319-67675-3_6

DO - 10.1007/978-3-319-67675-3_6

M3 - Article in proceedings

SN - 978-3-319-67674-6

T3 - Lecture notes in computer science

SP - 53

EP - 63

BT - Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics

A2 - Cardoso, M. Jorge

A2 - Arbel, Tal

A2 - Ferrante, Enzo

A2 - Pennec, Xavier

A2 - Dalca, Adrian V.

A2 - Parisot, Sarah

A2 - Joshi, Sarang

A2 - Batmanghelich, Nematollah K.

A2 - Sotiras, Aristeidis

A2 - Nielsen, Mads

A2 - Sabuncu, Mert R.

A2 - Fletcher, Tom

A2 - Shen, Li

A2 - Durrleman, Stanley

A2 - Sommer, Stefan

PB - Springer

T2 - 1st International Workshop on Graphs in Biomedical Image Analysis

Y2 - 10 September 2017 through 14 September 2017

ER -