Extracting tree structures in CT data by tracking multiple statistically ranked hypotheses

TY - JOUR

T1 - Extracting tree structures in CT data by tracking multiple statistically ranked hypotheses

AU - Selvan, Raghavendra

AU - Petersen, Jens

AU - Pedersen, Jesper H

AU - de Bruijne, Marleen

N1 - © 2019 American Association of Physicists in Medicine.

PY - 2019/10/1

Y1 - 2019/10/1

N2 - PURPOSE: In this work, we adapt a method based on multiple hypothesis tracking (MHT) that has been shown to give state-of-the-art vessel segmentation results in interactive settings, for the purpose of extracting trees.METHODS: Regularly spaced tubular templates are fit to image data forming local hypotheses. These local hypotheses are then used to construct the MHT tree, which is then traversed to make segmentation decisions. Some critical parameters in the method, we base ours on, are scale-dependent and have an adverse effect when tracking structures of varying dimensions. We propose to use statistical ranking of local hypotheses in constructing the MHT tree which yields a probabilistic interpretation of scores across scales and helps alleviate the scale dependence of MHT parameters. This enables our method to track trees starting from a single seed point.RESULTS: The proposed method is evaluated on chest computed tomography data to extract airway trees and coronary arteries and compared to relevant baselines. In both cases, we show that our method performs significantly better than the Original MHT method in semiautomatic setting.CONCLUSIONS: The statistical ranking of local hypotheses introduced allows the MHT method to be used in noninteractive settings yielding competitive results for segmenting tree structures.

AB - PURPOSE: In this work, we adapt a method based on multiple hypothesis tracking (MHT) that has been shown to give state-of-the-art vessel segmentation results in interactive settings, for the purpose of extracting trees.METHODS: Regularly spaced tubular templates are fit to image data forming local hypotheses. These local hypotheses are then used to construct the MHT tree, which is then traversed to make segmentation decisions. Some critical parameters in the method, we base ours on, are scale-dependent and have an adverse effect when tracking structures of varying dimensions. We propose to use statistical ranking of local hypotheses in constructing the MHT tree which yields a probabilistic interpretation of scores across scales and helps alleviate the scale dependence of MHT parameters. This enables our method to track trees starting from a single seed point.RESULTS: The proposed method is evaluated on chest computed tomography data to extract airway trees and coronary arteries and compared to relevant baselines. In both cases, we show that our method performs significantly better than the Original MHT method in semiautomatic setting.CONCLUSIONS: The statistical ranking of local hypotheses introduced allows the MHT method to be used in noninteractive settings yielding competitive results for segmenting tree structures.

U2 - 10.1002/mp.13711

DO - 10.1002/mp.13711

M3 - Journal article

C2 - 31306486

SN - 0094-2405

VL - 46

SP - 4431

EP - 4440

JO - Medical Physics

JF - Medical Physics

IS - 10

ER -