Virtual magnetic resonance lumbar spine images generated from computed tomography images using conditional generative adversarial networks. Issue 2 (May 2022)

• Record Type: Journal Article
• Authors: Gotoh, M.; Nakaura, T.; Funama, Y.; Morita, K.; Sakabe, D.; Uetani, H.; Nagayama, Y.; Kidoh, M.; Hatemura, M.; Masuda, T.; Hirai, T.
• Is Part Of: Radiography. Volume 28:Issue 2(2022)
• Page Start: 447
• Page End: 453
• Publication Date: 2022-05
• Subjects: Deep learning -- Tomography, X-ray computed -- Image processing, Computer-assisted -- Magnetic resonance imaging -- Lumbar vertebrae; MR Magnetic resonance -- CT Computed tomography -- cGAN conditional generative adversarial network -- MSE mean square error -- SSIM structural similarity index -- GAN generative adversarial network -- MPR multiplanar reconstruction; Diagnostic imaging -- Periodicals; Radiotherapy -- Periodicals; Cancer -- Radiotherapy -- Periodicals; Diagnostic Imaging -- Periodicals; Neoplasms -- Periodicals; Radiotherapy -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Radiothérapie -- Périodiques; Cancer -- Radiothérapie -- Périodiques; Electronic journals; 616.0757
• DOI: 10.1016/j.radi.2021.10.006
• Languages: English
• ISSNs: 1078-8174

Abstract

Abstract: Introduction: The aim of this study was to generate virtual Magnetic resonance (MR) from computed tomography (CT) using conditional generative adversarial networks (cGAN). Methods: We selected examinations from 22 adults who obtained their CT and MR lumbar spine examinations. Overall, 4 examinations were used as test data, and 18 examinations were used as training data. A cGAN was trained to generate virtual MR images from the CT images using the corresponding MR images as targets. After training, the generated virtual MR images from test data in epochs 1, 10, 50, 100, 500, and 1000 were compared with the original ones using the mean square error (MSE) and structural similarity index (SSIM). Additionally, two radiologists also performed qualitative assessments. Results: The MSE of the virtual MR images decreased as the epoch of the cGANs increased from the original CT images: 8876.7 ± 1192.9 (original CT), 1567.5 ± 433.9 (Epoch 1), 1242.4 ± 442.0 (Epoch 10), 1065.8 ± 478.1 (Epoch 50), 1276.1 ± 718.9 (Epoch 100), 1046.7 ± 488.2 (Epoch 500), and 1031.7 ± 400.0 (Epoch 1000). No considerable differences were observed in the qualitative evaluation between the virtual MR images and the original ones, except in the structure of the spinal canal. Conclusion: Virtual MR lumbar spine images using cGANs could be a feasible technique to generate near-MR images from CT without MR examinations for evaluation of the vertebral body and intervertebral disc. Implications for practice: Virtual MR lumbar spine images using cGANs can offer virtual CT images with sufficient quality for attenuation correction for PET or dose planning in radiotherapy.