Angel Torrado-Carvajal1, Javier Vera-Olmos2, David Izquierdo-Garcia1, Onofrio A Catalano1, Manuel A Morales1,3, Justin Margolin1,4, Andrea Soricelli5,6, Marco Salvatore5, Norberto Malpica2, Ciprian Catana7. 1. Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Charlestown, Massachusetts. 2. Medical Image Analysis and Biometry Lab, Universidad Rey Juan Carlos, Madrid, Spain. 3. Department of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, Massachusetts. 4. Northeastern University, Boston, Massachusetts. 5. SDN-Istituto di Ricerca Diagnostica e Nucleare, IRCCS, Naples, Italy; and. 6. Department of Motor Sciences and Wellness, University of Naples "Parthenope," Naples, Italy. 7. Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Charlestown, Massachusetts ccatana@mgh.harvard.edu.
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 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 some commercial scanners. Methods: We propose a network that maps between the four 2-dimensional (2D) Dixon MR images (water, fat, in-phase, 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, we used whole 2D slices to provide context information, and we pretrained the network with brain images. Twenty-eight 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 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 values relative to CT AC were lower than 2% on average for the DIVIDE method in every region of interest except for bone tissue, where it was lower than 4% and 6.75 times smaller than the relative change of the Dixon method. There was an excellent voxel-by-voxel correlation between PETCT and PETDIVIDE (R 2 = 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; PETCT-PETDIVIDE SD, 0.0094; 95% confidence interval, [-0.0180,0.0188]) than the average of differences between PETCT and PETDixon (mean PETCT-PETDixon SUV, 0.0006; PETCT-PETDixon SD, 0.0264; 95% confidence interval, [-0.0510,0.0524]). Statistically significant changes in PET data quantification were observed between the 2 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 scan 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 retrospective processing of Dixon-VIBE data.
Whole-body attenuation correction (AC) is still challenging in combined PET/MR scanners. We describe Dixon-VIBE Deep Learning (DIVIDE), a deep-learning network 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 some commercial scanners. Methods: We propose a network that maps between the four 2-dimensional (2D) Dixon MR images (water, fat, in-phase, 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, we used whole 2D slices to provide context information, and we pretrained the network with brain images. Twenty-eight 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 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 values relative to CT AC were lower than 2% on average for the DIVIDE method in every region of interest except for bone tissue, where it was lower than 4% and 6.75 times smaller than the relative change of the Dixon method. There was an excellent voxel-by-voxel correlation between PETCT and PETDIVIDE (R 2 = 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; PETCT-PETDIVIDE SD, 0.0094; 95% confidence interval, [-0.0180,0.0188]) than the average of differences between PETCT and PETDixon (mean PETCT-PETDixon SUV, 0.0006; PETCT-PETDixon SD, 0.0264; 95% confidence interval, [-0.0510,0.0524]). Statistically significant changes in PET data quantification were observed between the 2 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 scan 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 retrospective processing of Dixon-VIBE data.
Authors: Thomas A Hope; Zahi A Fayad; Kathryn J Fowler; Dawn Holley; Andrei Iagaru; Alan B McMillan; Patrick Veit-Haiback; Robert J Witte; Greg Zaharchuk; Ciprian Catana Journal: J Nucl Med Date: 2019-05-23 Impact factor: 10.057
Authors: Paul Kyu Han; Debra E Horng; Kuang Gong; Yoann Petibon; Kyungsang Kim; Quanzheng Li; Keith A Johnson; Georges El Fakhri; Jinsong Ouyang; Chao Ma Journal: Med Phys Date: 2020-05-11 Impact factor: 4.071
Authors: Dharshan Chandramohan; Peng Cao; Misung Han; Hongyu An; John J Sunderland; Paul E Kinahan; Richard Laforest; Thomas A Hope; Peder E Z Larson Journal: Med Phys Date: 2020-03-13 Impact factor: 4.071
Authors: Tonghe Wang; Yang Lei; Yabo Fu; Walter J Curran; Tian Liu; Jonathon A Nye; Xiaofeng Yang Journal: Phys Med Date: 2020-07-29 Impact factor: 2.685