Maximization of regional probabilities using Optimal Surface Graphs: application to carotid artery segmentation in MRI

Research output: Contribution to journalJournal articlepeer-review

Standard

Maximization of regional probabilities using Optimal Surface Graphs : application to carotid artery segmentation in MRI. / Arias Lorza, Andres M.; Van Engelen, Arna; Petersen, Jens; Van Der Lugt, Aad; De Bruijne, Marleen.

In: Medical Physics, Vol. 45, No. 3, 01.03.2018, p. 1159-1169.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Arias Lorza, AM, Van Engelen, A, Petersen, J, Van Der Lugt, A & De Bruijne, M 2018, 'Maximization of regional probabilities using Optimal Surface Graphs: application to carotid artery segmentation in MRI', Medical Physics, vol. 45, no. 3, pp. 1159-1169. https://doi.org/10.1002/mp.12771

APA

Arias Lorza, A. M., Van Engelen, A., Petersen, J., Van Der Lugt, A., & De Bruijne, M. (2018). Maximization of regional probabilities using Optimal Surface Graphs: application to carotid artery segmentation in MRI. Medical Physics, 45(3), 1159-1169. https://doi.org/10.1002/mp.12771

Vancouver

Arias Lorza AM, Van Engelen A, Petersen J, Van Der Lugt A, De Bruijne M. Maximization of regional probabilities using Optimal Surface Graphs: application to carotid artery segmentation in MRI. Medical Physics. 2018 Mar 1;45(3):1159-1169. https://doi.org/10.1002/mp.12771

Author

Arias Lorza, Andres M. ; Van Engelen, Arna ; Petersen, Jens ; Van Der Lugt, Aad ; De Bruijne, Marleen. / Maximization of regional probabilities using Optimal Surface Graphs : application to carotid artery segmentation in MRI. In: Medical Physics. 2018 ; Vol. 45, No. 3. pp. 1159-1169.

Bibtex

@article{4deab7ce41aa4370af83a547bcda4a8c,
title = "Maximization of regional probabilities using Optimal Surface Graphs: application to carotid artery segmentation in MRI",
abstract = "Purpose: We present a segmentation method that maximizes regional probabilities enclosed by coupled surfaces using an Optimal Surface Graph (OSG) cut approach. This OSG cut determines the globally optimal solution given a graph constructed around an initial surface. While most methods for vessel wall segmentation only use edge information, we show that maximizing regional probabilities using an OSG improves the segmentation results. We applied this to automatically segment the vessel wall of the carotid artery in magnetic resonance images. Methods: First, voxel-wise regional probability maps were obtained using a Support Vector Machine classifier trained on local image features. Then, the OSG segments the regions which maximizes the regional probabilities considering smoothness and topological constraints. Results: The method was evaluated on 49 carotid arteries from 30 subjects. The proposed method shows good accuracy with a Dice wall overlap of 74.1 ± 4.3%, and significantly outperforms a published method based on an OSG using only surface information, the obtained segmentations using voxel-wise classification alone, and another published artery wall segmentation method based on a deformable surface model. Intraclass correlations (ICC) with manually measured lumen and wall volumes were similar to those obtained between observers. Finally, we show a good reproducibility of the method with ICC = 0.86 between the volumes measured in scans repeated within a short time interval. Conclusions: In this work, a new segmentation method that uses both an OSG and regional probabilities is presented. The method shows good segmentations of the carotid artery in MRI and outperformed another segmentation method that uses OSG and edge information and the voxel-wise segmentation using the probability maps.",
keywords = "carotid artery, graph cut, maximization of regional probabilities, MRI, Optimal Surface Graph, segmentation, support vector machine classifier",
author = "{Arias Lorza}, {Andres M.} and {Van Engelen}, Arna and Jens Petersen and {Van Der Lugt}, Aad and {De Bruijne}, Marleen",
year = "2018",
month = mar,
day = "1",
doi = "10.1002/mp.12771",
language = "English",
volume = "45",
pages = "1159--1169",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "John Wiley and Sons, Inc.",
number = "3",

}

RIS

TY - JOUR

T1 - Maximization of regional probabilities using Optimal Surface Graphs

T2 - application to carotid artery segmentation in MRI

AU - Arias Lorza, Andres M.

AU - Van Engelen, Arna

AU - Petersen, Jens

AU - Van Der Lugt, Aad

AU - De Bruijne, Marleen

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Purpose: We present a segmentation method that maximizes regional probabilities enclosed by coupled surfaces using an Optimal Surface Graph (OSG) cut approach. This OSG cut determines the globally optimal solution given a graph constructed around an initial surface. While most methods for vessel wall segmentation only use edge information, we show that maximizing regional probabilities using an OSG improves the segmentation results. We applied this to automatically segment the vessel wall of the carotid artery in magnetic resonance images. Methods: First, voxel-wise regional probability maps were obtained using a Support Vector Machine classifier trained on local image features. Then, the OSG segments the regions which maximizes the regional probabilities considering smoothness and topological constraints. Results: The method was evaluated on 49 carotid arteries from 30 subjects. The proposed method shows good accuracy with a Dice wall overlap of 74.1 ± 4.3%, and significantly outperforms a published method based on an OSG using only surface information, the obtained segmentations using voxel-wise classification alone, and another published artery wall segmentation method based on a deformable surface model. Intraclass correlations (ICC) with manually measured lumen and wall volumes were similar to those obtained between observers. Finally, we show a good reproducibility of the method with ICC = 0.86 between the volumes measured in scans repeated within a short time interval. Conclusions: In this work, a new segmentation method that uses both an OSG and regional probabilities is presented. The method shows good segmentations of the carotid artery in MRI and outperformed another segmentation method that uses OSG and edge information and the voxel-wise segmentation using the probability maps.

AB - Purpose: We present a segmentation method that maximizes regional probabilities enclosed by coupled surfaces using an Optimal Surface Graph (OSG) cut approach. This OSG cut determines the globally optimal solution given a graph constructed around an initial surface. While most methods for vessel wall segmentation only use edge information, we show that maximizing regional probabilities using an OSG improves the segmentation results. We applied this to automatically segment the vessel wall of the carotid artery in magnetic resonance images. Methods: First, voxel-wise regional probability maps were obtained using a Support Vector Machine classifier trained on local image features. Then, the OSG segments the regions which maximizes the regional probabilities considering smoothness and topological constraints. Results: The method was evaluated on 49 carotid arteries from 30 subjects. The proposed method shows good accuracy with a Dice wall overlap of 74.1 ± 4.3%, and significantly outperforms a published method based on an OSG using only surface information, the obtained segmentations using voxel-wise classification alone, and another published artery wall segmentation method based on a deformable surface model. Intraclass correlations (ICC) with manually measured lumen and wall volumes were similar to those obtained between observers. Finally, we show a good reproducibility of the method with ICC = 0.86 between the volumes measured in scans repeated within a short time interval. Conclusions: In this work, a new segmentation method that uses both an OSG and regional probabilities is presented. The method shows good segmentations of the carotid artery in MRI and outperformed another segmentation method that uses OSG and edge information and the voxel-wise segmentation using the probability maps.

KW - carotid artery

KW - graph cut

KW - maximization of regional probabilities

KW - MRI

KW - Optimal Surface Graph

KW - segmentation

KW - support vector machine classifier

UR - http://www.scopus.com/inward/record.url?scp=85042101327&partnerID=8YFLogxK

U2 - 10.1002/mp.12771

DO - 10.1002/mp.12771

M3 - Journal article

C2 - 29369385

AN - SCOPUS:85042101327

VL - 45

SP - 1159

EP - 1169

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 3

ER -

ID: 195258616