Extracting tree structures in CT data by tracking multiple statistically ranked hypotheses
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Extracting tree structures in CT data by tracking multiple statistically ranked hypotheses. / Selvan, Raghavendra; Petersen, Jens; Pedersen, Jesper H; de Bruijne, Marleen.
In: Medical Physics, Vol. 46, No. 10, 18.10.2019, p. 4431-4440.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
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 - 2019/10/18
Y1 - 2019/10/18
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
VL - 46
SP - 4431
EP - 4440
JO - Medical Physics
JF - Medical Physics
SN - 0094-2405
IS - 10
ER -
ID: 225920173