Maximization of regional probabilities using Optimal Surface Graphs: application to carotid artery segmentation in MRI
Research output: Contribution to journal › Journal article › Research › peer-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 journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
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