Comparison of atlas-based techniques for whole-body bone segmentation

Hossein Arabi, Habib Zaidi*

*Kontaktforfatter for dette arbejde

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

We evaluate the accuracy of whole-body bone extraction from whole-body MR images using a number of atlas-based segmentation methods. The motivation behind this work is to find the most promising approach for the purpose of MRI-guided derivation of PET attenuation maps in whole-body PET/MRI. To this end, a variety of atlas-based segmentation strategies commonly used in medical image segmentation and pseudo-CT generation were implemented and evaluated in terms of whole-body bone segmentation accuracy. Bone segmentation was performed on 23 whole-body CT/MR image pairs via leave-one-out cross validation procedure. The evaluated segmentation techniques include: (i) intensity averaging (IA), (ii) majority voting (MV), (iii) global and (iv) local (voxel-wise) weighting atlas fusion frameworks implemented utilizing normalized mutual information (NMI), normalized cross-correlation (NCC) and mean square distance (MSD) as image similarity measures for calculating the weighting factors, along with other atlas-dependent algorithms, such as (v) shape-based averaging (SBA) and (vi) Hofmann's pseudo-CT generation method. The performance evaluation of the different segmentation techniques was carried out in terms of estimating bone extraction accuracy from whole-body MRI using standard metrics, such as Dice similarity (DSC) and relative volume difference (RVD) considering bony structures obtained from intensity thresholding of the reference CT images as the ground truth. Considering the Dice criterion, global weighting atlas fusion methods provided moderate improvement of whole-body bone segmentation (DSC ='0.65'±'0.05) compared to non-weighted IA (DSC ='0.60'±'0.02). The local weighed atlas fusion approach using the MSD similarity measure outperformed the other strategies by achieving a DSC of 0.81'±'0.03 while using the NCC and NMI measures resulted in a DSC of 0.78'±'0.05 and 0.75'±'0.04, respectively. Despite very long computation time, the extracted bone obtained from both SBA (DSC ='0.56'±'0.05) and Hofmann's methods (DSC ='0.60'±'0.02) exhibited no improvement compared to non-weighted IA. Finding the optimum parameters for implementation of the atlas fusion approach, such as weighting factors and image similarity patch size, have great impact on the performance of atlas-based segmentation approaches. The voxel-wise atlas fusion approach exhibited excellent performance in terms of cancelling out the non-systematic registration errors leading to accurate and reliable segmentation results. Denoising and normalization of MR images together with optimization of the involved parameters play a key role in improving bone extraction accuracy.

OriginalsprogEngelsk
TidsskriftMedical Image Analysis
Vol/bind36
Sider (fra-til)98-112
ISSN1361-8415
DOI
StatusUdgivet - 2017

Fingeraftryk

Bone
Fusion reactions
Magnetic resonance imaging
Image segmentation

Citer dette

@article{4d8328f808094c74973969278885f9ce,
title = "Comparison of atlas-based techniques for whole-body bone segmentation",
abstract = "We evaluate the accuracy of whole-body bone extraction from whole-body MR images using a number of atlas-based segmentation methods. The motivation behind this work is to find the most promising approach for the purpose of MRI-guided derivation of PET attenuation maps in whole-body PET/MRI. To this end, a variety of atlas-based segmentation strategies commonly used in medical image segmentation and pseudo-CT generation were implemented and evaluated in terms of whole-body bone segmentation accuracy. Bone segmentation was performed on 23 whole-body CT/MR image pairs via leave-one-out cross validation procedure. The evaluated segmentation techniques include: (i) intensity averaging (IA), (ii) majority voting (MV), (iii) global and (iv) local (voxel-wise) weighting atlas fusion frameworks implemented utilizing normalized mutual information (NMI), normalized cross-correlation (NCC) and mean square distance (MSD) as image similarity measures for calculating the weighting factors, along with other atlas-dependent algorithms, such as (v) shape-based averaging (SBA) and (vi) Hofmann's pseudo-CT generation method. The performance evaluation of the different segmentation techniques was carried out in terms of estimating bone extraction accuracy from whole-body MRI using standard metrics, such as Dice similarity (DSC) and relative volume difference (RVD) considering bony structures obtained from intensity thresholding of the reference CT images as the ground truth. Considering the Dice criterion, global weighting atlas fusion methods provided moderate improvement of whole-body bone segmentation (DSC ='0.65'±'0.05) compared to non-weighted IA (DSC ='0.60'±'0.02). The local weighed atlas fusion approach using the MSD similarity measure outperformed the other strategies by achieving a DSC of 0.81'±'0.03 while using the NCC and NMI measures resulted in a DSC of 0.78'±'0.05 and 0.75'±'0.04, respectively. Despite very long computation time, the extracted bone obtained from both SBA (DSC ='0.56'±'0.05) and Hofmann's methods (DSC ='0.60'±'0.02) exhibited no improvement compared to non-weighted IA. Finding the optimum parameters for implementation of the atlas fusion approach, such as weighting factors and image similarity patch size, have great impact on the performance of atlas-based segmentation approaches. The voxel-wise atlas fusion approach exhibited excellent performance in terms of cancelling out the non-systematic registration errors leading to accurate and reliable segmentation results. Denoising and normalization of MR images together with optimization of the involved parameters play a key role in improving bone extraction accuracy.",
keywords = "Atlas-based segmentation, Bone segmentation, MRI, PET/MRI, Whole-body",
author = "Hossein Arabi and Habib Zaidi",
year = "2017",
doi = "10.1016/j.media.2016.11.003",
language = "English",
volume = "36",
pages = "98--112",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

Comparison of atlas-based techniques for whole-body bone segmentation. / Arabi, Hossein; Zaidi, Habib.

I: Medical Image Analysis, Bind 36, 2017, s. 98-112.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Comparison of atlas-based techniques for whole-body bone segmentation

AU - Arabi, Hossein

AU - Zaidi, Habib

PY - 2017

Y1 - 2017

N2 - We evaluate the accuracy of whole-body bone extraction from whole-body MR images using a number of atlas-based segmentation methods. The motivation behind this work is to find the most promising approach for the purpose of MRI-guided derivation of PET attenuation maps in whole-body PET/MRI. To this end, a variety of atlas-based segmentation strategies commonly used in medical image segmentation and pseudo-CT generation were implemented and evaluated in terms of whole-body bone segmentation accuracy. Bone segmentation was performed on 23 whole-body CT/MR image pairs via leave-one-out cross validation procedure. The evaluated segmentation techniques include: (i) intensity averaging (IA), (ii) majority voting (MV), (iii) global and (iv) local (voxel-wise) weighting atlas fusion frameworks implemented utilizing normalized mutual information (NMI), normalized cross-correlation (NCC) and mean square distance (MSD) as image similarity measures for calculating the weighting factors, along with other atlas-dependent algorithms, such as (v) shape-based averaging (SBA) and (vi) Hofmann's pseudo-CT generation method. The performance evaluation of the different segmentation techniques was carried out in terms of estimating bone extraction accuracy from whole-body MRI using standard metrics, such as Dice similarity (DSC) and relative volume difference (RVD) considering bony structures obtained from intensity thresholding of the reference CT images as the ground truth. Considering the Dice criterion, global weighting atlas fusion methods provided moderate improvement of whole-body bone segmentation (DSC ='0.65'±'0.05) compared to non-weighted IA (DSC ='0.60'±'0.02). The local weighed atlas fusion approach using the MSD similarity measure outperformed the other strategies by achieving a DSC of 0.81'±'0.03 while using the NCC and NMI measures resulted in a DSC of 0.78'±'0.05 and 0.75'±'0.04, respectively. Despite very long computation time, the extracted bone obtained from both SBA (DSC ='0.56'±'0.05) and Hofmann's methods (DSC ='0.60'±'0.02) exhibited no improvement compared to non-weighted IA. Finding the optimum parameters for implementation of the atlas fusion approach, such as weighting factors and image similarity patch size, have great impact on the performance of atlas-based segmentation approaches. The voxel-wise atlas fusion approach exhibited excellent performance in terms of cancelling out the non-systematic registration errors leading to accurate and reliable segmentation results. Denoising and normalization of MR images together with optimization of the involved parameters play a key role in improving bone extraction accuracy.

AB - We evaluate the accuracy of whole-body bone extraction from whole-body MR images using a number of atlas-based segmentation methods. The motivation behind this work is to find the most promising approach for the purpose of MRI-guided derivation of PET attenuation maps in whole-body PET/MRI. To this end, a variety of atlas-based segmentation strategies commonly used in medical image segmentation and pseudo-CT generation were implemented and evaluated in terms of whole-body bone segmentation accuracy. Bone segmentation was performed on 23 whole-body CT/MR image pairs via leave-one-out cross validation procedure. The evaluated segmentation techniques include: (i) intensity averaging (IA), (ii) majority voting (MV), (iii) global and (iv) local (voxel-wise) weighting atlas fusion frameworks implemented utilizing normalized mutual information (NMI), normalized cross-correlation (NCC) and mean square distance (MSD) as image similarity measures for calculating the weighting factors, along with other atlas-dependent algorithms, such as (v) shape-based averaging (SBA) and (vi) Hofmann's pseudo-CT generation method. The performance evaluation of the different segmentation techniques was carried out in terms of estimating bone extraction accuracy from whole-body MRI using standard metrics, such as Dice similarity (DSC) and relative volume difference (RVD) considering bony structures obtained from intensity thresholding of the reference CT images as the ground truth. Considering the Dice criterion, global weighting atlas fusion methods provided moderate improvement of whole-body bone segmentation (DSC ='0.65'±'0.05) compared to non-weighted IA (DSC ='0.60'±'0.02). The local weighed atlas fusion approach using the MSD similarity measure outperformed the other strategies by achieving a DSC of 0.81'±'0.03 while using the NCC and NMI measures resulted in a DSC of 0.78'±'0.05 and 0.75'±'0.04, respectively. Despite very long computation time, the extracted bone obtained from both SBA (DSC ='0.56'±'0.05) and Hofmann's methods (DSC ='0.60'±'0.02) exhibited no improvement compared to non-weighted IA. Finding the optimum parameters for implementation of the atlas fusion approach, such as weighting factors and image similarity patch size, have great impact on the performance of atlas-based segmentation approaches. The voxel-wise atlas fusion approach exhibited excellent performance in terms of cancelling out the non-systematic registration errors leading to accurate and reliable segmentation results. Denoising and normalization of MR images together with optimization of the involved parameters play a key role in improving bone extraction accuracy.

KW - Atlas-based segmentation

KW - Bone segmentation

KW - MRI

KW - PET/MRI

KW - Whole-body

U2 - 10.1016/j.media.2016.11.003

DO - 10.1016/j.media.2016.11.003

M3 - Journal article

VL - 36

SP - 98

EP - 112

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -