Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction

Angel Torrado-Carvajal, Javier Vera-Olmos, David Izquierdo-Garcia, Onofrio Antonio Catalano, Manuel Antonio Morales, Justin Margolin, Andrea Soricelli, Marco Salvatore, Norberto Malpica, Ciprian Catana

Research output: Contribution to journalArticle

Abstract

Whole-body attenuation correction (AC) is still challenging in combined PET/MR scanners. We describe Dixon-VIBE Deep Learning (DIVIDE), a deep learning network architecture that allows synthesizing pelvis pseudo-CT maps based only on the standard Dixon volumetric interpolated breath-hold examination (Dixon-VIBE) images currently acquired for AC in commercial Siemens scanners. Methods: We propose a network that performs a mapping between the four 2D Dixon MRI images (water, fat, in- and out-of-phase) and their corresponding 2D CT image. In contrast to previous methods, we used transposed convolutions to learn the up-sampling parameters, whole 2D slices to provide context information and pretrained the network with brain images. 28 datasets obtained from 19 patients who underwent PET/CT and PET/MR examinations were used to evaluate the proposed method. We assessed the accuracy of the µ-maps and reconstructed PET images by performing voxel- and region-based analysis comparing the standardize uptake values (SUVs, in g/mL) obtained after AC using the Dixon-VIBE (PETDixon), DIVIDE (PETDIVIDE) and CT-based (PETCT) methods. Additionally, the bias in quantification was estimated in synthetic lesions defined in the prostate, rectum, pelvis and spine. Results: Absolute mean relative change (RC) values relative to CT AC were lower than 2% on average for the DIVIDE method in every region of interest (ROI) except for bone tissue where it was lower than 4% and 6.75 times smaller than the RC of the Dixon method. There was an excellent voxel-by-voxel correlation between PETCT and PETDIVIDE (R2=0.9998, p<0.01). The Bland-Altman plot between PETCT and PETDIVIDE showed that the average of the differences and the variability were lower (mean PETCT-PETDIVIDE SUV=0.0003, σ PETCT-PETDIVIDE=0.0094, CI0.95=[-0.0180,0.0188]) than the average of differences between PETCT and PETDixon (mean PETCT-PETDixon SUV=0.0006, σ PETCT-PETDixon = 0.0264, CI0.95=[-0.0510,0.0524]). Statistically significant changes in PET data quantification were observed between the two methods in the synthetic lesions with the largest improvement in femur and spine lesions. Conclusion: The DIVIDE method can accurately synthesize a pelvis pseudo-CT from standard Dixon-VIBE images, allowing for accurate AC in combined PET/MR scanners. Additionally, our implementation allows rapid pseudo-CT synthesis, making it suitable for routine applications and, even allowing the retrospective processing of Dixon-VIBE data.

Original languageEnglish
JournalJournal of Nuclear Medicine
DOIs
Publication statusE-pub ahead of print - Aug 30 2018

Fingerprint

Pelvis
Learning
Spine
Information Services
Rectum
Femur
Prostate
Fats
Bone and Bones
Water
Brain

Cite this

Torrado-Carvajal, A., Vera-Olmos, J., Izquierdo-Garcia, D., Catalano, O. A., Morales, M. A., Margolin, J., ... Catana, C. (2018). Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction. Journal of Nuclear Medicine. https://doi.org/10.2967/jnumed.118.209288

Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction. / Torrado-Carvajal, Angel; Vera-Olmos, Javier; Izquierdo-Garcia, David; Catalano, Onofrio Antonio; Morales, Manuel Antonio; Margolin, Justin; Soricelli, Andrea; Salvatore, Marco; Malpica, Norberto; Catana, Ciprian.

In: Journal of Nuclear Medicine, 30.08.2018.

Research output: Contribution to journalArticle

Torrado-Carvajal, A, Vera-Olmos, J, Izquierdo-Garcia, D, Catalano, OA, Morales, MA, Margolin, J, Soricelli, A, Salvatore, M, Malpica, N & Catana, C 2018, 'Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction', Journal of Nuclear Medicine. https://doi.org/10.2967/jnumed.118.209288
Torrado-Carvajal A, Vera-Olmos J, Izquierdo-Garcia D, Catalano OA, Morales MA, Margolin J et al. Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction. Journal of Nuclear Medicine. 2018 Aug 30. https://doi.org/10.2967/jnumed.118.209288
Torrado-Carvajal, Angel ; Vera-Olmos, Javier ; Izquierdo-Garcia, David ; Catalano, Onofrio Antonio ; Morales, Manuel Antonio ; Margolin, Justin ; Soricelli, Andrea ; Salvatore, Marco ; Malpica, Norberto ; Catana, Ciprian. / Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction. In: Journal of Nuclear Medicine. 2018.
@article{27b166b3f6804a8eb1757d07a495a8ff,
title = "Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction",
abstract = "Whole-body attenuation correction (AC) is still challenging in combined PET/MR scanners. We describe Dixon-VIBE Deep Learning (DIVIDE), a deep learning network architecture that allows synthesizing pelvis pseudo-CT maps based only on the standard Dixon volumetric interpolated breath-hold examination (Dixon-VIBE) images currently acquired for AC in commercial Siemens scanners. Methods: We propose a network that performs a mapping between the four 2D Dixon MRI images (water, fat, in- and out-of-phase) and their corresponding 2D CT image. In contrast to previous methods, we used transposed convolutions to learn the up-sampling parameters, whole 2D slices to provide context information and pretrained the network with brain images. 28 datasets obtained from 19 patients who underwent PET/CT and PET/MR examinations were used to evaluate the proposed method. We assessed the accuracy of the µ-maps and reconstructed PET images by performing voxel- and region-based analysis comparing the standardize uptake values (SUVs, in g/mL) obtained after AC using the Dixon-VIBE (PETDixon), DIVIDE (PETDIVIDE) and CT-based (PETCT) methods. Additionally, the bias in quantification was estimated in synthetic lesions defined in the prostate, rectum, pelvis and spine. Results: Absolute mean relative change (RC) values relative to CT AC were lower than 2{\%} on average for the DIVIDE method in every region of interest (ROI) except for bone tissue where it was lower than 4{\%} and 6.75 times smaller than the RC of the Dixon method. There was an excellent voxel-by-voxel correlation between PETCT and PETDIVIDE (R2=0.9998, p<0.01). The Bland-Altman plot between PETCT and PETDIVIDE showed that the average of the differences and the variability were lower (mean PETCT-PETDIVIDE SUV=0.0003, σ PETCT-PETDIVIDE=0.0094, CI0.95=[-0.0180,0.0188]) than the average of differences between PETCT and PETDixon (mean PETCT-PETDixon SUV=0.0006, σ PETCT-PETDixon = 0.0264, CI0.95=[-0.0510,0.0524]). Statistically significant changes in PET data quantification were observed between the two methods in the synthetic lesions with the largest improvement in femur and spine lesions. Conclusion: The DIVIDE method can accurately synthesize a pelvis pseudo-CT from standard Dixon-VIBE images, allowing for accurate AC in combined PET/MR scanners. Additionally, our implementation allows rapid pseudo-CT synthesis, making it suitable for routine applications and, even allowing the retrospective processing of Dixon-VIBE data.",
author = "Angel Torrado-Carvajal and Javier Vera-Olmos and David Izquierdo-Garcia and Catalano, {Onofrio Antonio} and Morales, {Manuel Antonio} and Justin Margolin and Andrea Soricelli and Marco Salvatore and Norberto Malpica and Ciprian Catana",
note = "Copyright {\circledC} 2018 by the Society of Nuclear Medicine and Molecular Imaging, Inc.",
year = "2018",
month = "8",
day = "30",
doi = "10.2967/jnumed.118.209288",
language = "English",
journal = "Journal of Nuclear Medicine",
issn = "0161-5505",
publisher = "Society of Nuclear Medicine Inc.",

}

TY - JOUR

T1 - Dixon-VIBE Deep Learning (DIVIDE) Pseudo-CT Synthesis for Pelvis PET/MR Attenuation Correction

AU - Torrado-Carvajal, Angel

AU - Vera-Olmos, Javier

AU - Izquierdo-Garcia, David

AU - Catalano, Onofrio Antonio

AU - Morales, Manuel Antonio

AU - Margolin, Justin

AU - Soricelli, Andrea

AU - Salvatore, Marco

AU - Malpica, Norberto

AU - Catana, Ciprian

N1 - Copyright © 2018 by the Society of Nuclear Medicine and Molecular Imaging, Inc.

PY - 2018/8/30

Y1 - 2018/8/30

N2 - Whole-body attenuation correction (AC) is still challenging in combined PET/MR scanners. We describe Dixon-VIBE Deep Learning (DIVIDE), a deep learning network architecture that allows synthesizing pelvis pseudo-CT maps based only on the standard Dixon volumetric interpolated breath-hold examination (Dixon-VIBE) images currently acquired for AC in commercial Siemens scanners. Methods: We propose a network that performs a mapping between the four 2D Dixon MRI images (water, fat, in- and out-of-phase) and their corresponding 2D CT image. In contrast to previous methods, we used transposed convolutions to learn the up-sampling parameters, whole 2D slices to provide context information and pretrained the network with brain images. 28 datasets obtained from 19 patients who underwent PET/CT and PET/MR examinations were used to evaluate the proposed method. We assessed the accuracy of the µ-maps and reconstructed PET images by performing voxel- and region-based analysis comparing the standardize uptake values (SUVs, in g/mL) obtained after AC using the Dixon-VIBE (PETDixon), DIVIDE (PETDIVIDE) and CT-based (PETCT) methods. Additionally, the bias in quantification was estimated in synthetic lesions defined in the prostate, rectum, pelvis and spine. Results: Absolute mean relative change (RC) values relative to CT AC were lower than 2% on average for the DIVIDE method in every region of interest (ROI) except for bone tissue where it was lower than 4% and 6.75 times smaller than the RC of the Dixon method. There was an excellent voxel-by-voxel correlation between PETCT and PETDIVIDE (R2=0.9998, p<0.01). The Bland-Altman plot between PETCT and PETDIVIDE showed that the average of the differences and the variability were lower (mean PETCT-PETDIVIDE SUV=0.0003, σ PETCT-PETDIVIDE=0.0094, CI0.95=[-0.0180,0.0188]) than the average of differences between PETCT and PETDixon (mean PETCT-PETDixon SUV=0.0006, σ PETCT-PETDixon = 0.0264, CI0.95=[-0.0510,0.0524]). Statistically significant changes in PET data quantification were observed between the two methods in the synthetic lesions with the largest improvement in femur and spine lesions. Conclusion: The DIVIDE method can accurately synthesize a pelvis pseudo-CT from standard Dixon-VIBE images, allowing for accurate AC in combined PET/MR scanners. Additionally, our implementation allows rapid pseudo-CT synthesis, making it suitable for routine applications and, even allowing the retrospective processing of Dixon-VIBE data.

AB - Whole-body attenuation correction (AC) is still challenging in combined PET/MR scanners. We describe Dixon-VIBE Deep Learning (DIVIDE), a deep learning network architecture that allows synthesizing pelvis pseudo-CT maps based only on the standard Dixon volumetric interpolated breath-hold examination (Dixon-VIBE) images currently acquired for AC in commercial Siemens scanners. Methods: We propose a network that performs a mapping between the four 2D Dixon MRI images (water, fat, in- and out-of-phase) and their corresponding 2D CT image. In contrast to previous methods, we used transposed convolutions to learn the up-sampling parameters, whole 2D slices to provide context information and pretrained the network with brain images. 28 datasets obtained from 19 patients who underwent PET/CT and PET/MR examinations were used to evaluate the proposed method. We assessed the accuracy of the µ-maps and reconstructed PET images by performing voxel- and region-based analysis comparing the standardize uptake values (SUVs, in g/mL) obtained after AC using the Dixon-VIBE (PETDixon), DIVIDE (PETDIVIDE) and CT-based (PETCT) methods. Additionally, the bias in quantification was estimated in synthetic lesions defined in the prostate, rectum, pelvis and spine. Results: Absolute mean relative change (RC) values relative to CT AC were lower than 2% on average for the DIVIDE method in every region of interest (ROI) except for bone tissue where it was lower than 4% and 6.75 times smaller than the RC of the Dixon method. There was an excellent voxel-by-voxel correlation between PETCT and PETDIVIDE (R2=0.9998, p<0.01). The Bland-Altman plot between PETCT and PETDIVIDE showed that the average of the differences and the variability were lower (mean PETCT-PETDIVIDE SUV=0.0003, σ PETCT-PETDIVIDE=0.0094, CI0.95=[-0.0180,0.0188]) than the average of differences between PETCT and PETDixon (mean PETCT-PETDixon SUV=0.0006, σ PETCT-PETDixon = 0.0264, CI0.95=[-0.0510,0.0524]). Statistically significant changes in PET data quantification were observed between the two methods in the synthetic lesions with the largest improvement in femur and spine lesions. Conclusion: The DIVIDE method can accurately synthesize a pelvis pseudo-CT from standard Dixon-VIBE images, allowing for accurate AC in combined PET/MR scanners. Additionally, our implementation allows rapid pseudo-CT synthesis, making it suitable for routine applications and, even allowing the retrospective processing of Dixon-VIBE data.

U2 - 10.2967/jnumed.118.209288

DO - 10.2967/jnumed.118.209288

M3 - Article

C2 - 30166357

JO - Journal of Nuclear Medicine

JF - Journal of Nuclear Medicine

SN - 0161-5505

ER -