Spine Computed Tomography to Magnetic Resonance Image Synthesis Using Generative Adversarial Networks : A Preliminary Study

• Published in: Journal of Korean Neurosurgical Society Vol. 63; no. 3; pp. 386 - 396
• Main Authors: Lee, Jung Hwan, Han, In Ho, Kim, Dong Hwan, Yu, Seunghan, Lee, In Sook, Song, You Seon, Joo, Seongsu, Jin, Cheng-Bin, Kim, Hakil
• Format: Journal Article
• Language: English
• Published: Korea (South) Korean Neurosurgical Society 01.05.2020; 대한신경외과학회
• Subjects: Laboratory Investigation; 신경외과학; Deep learning; Computed tomography; Magnetic resonance imaging; Lumbar vertebrae
• DOI: 10.3340/jkns.2019.0084
• ISSN: 2005-3711

To generate synthetic spine magnetic resonance (MR) images from spine computed tomography (CT) using generative adversarial networks (GANs), as well as to determine the similarities between synthesized and real MR images. GANs were trained to transform spine CT image slices into spine magnetic resonance T2 weighted (MRT2) axial image slices by combining adversarial loss and voxel-wise loss. Experiments were performed using 280 pairs of lumbar spine CT scans and MRT2 images. The MRT2 images were then synthesized from 15 other spine CT scans. To evaluate whether the synthetic MR images were realistic, two radiologists, two spine surgeons, and two residents blindly classified the real and synthetic MRT2 images. Two experienced radiologists then evaluated the similarities between subdivisions of the real and synthetic MRT2 images. Quantitative analysis of the synthetic MRT2 images was performed using the mean absolute error (MAE) and peak signal-to-noise ratio (PSNR). The mean overall similarity of the synthetic MRT2 images evaluated by radiologists was 80.2%. In the blind classification of the real MRT2 images, the failure rate ranged from 0% to 40%. The MAE value of each image ranged from 13.75 to 34.24 pixels (mean, 21.19 pixels), and the PSNR of each image ranged from 61.96 to 68.16 dB (mean, 64.92 dB). This was the first study to apply GANs to synthesize spine MR images from CT images. Despite the small dataset of 280 pairs, the synthetic MR images were relatively well implemented. Synthesis of medical images using GANs is a new paradigm of artificial intelligence application in medical imaging. We expect that synthesis of MR images from spine CT images using GANs will improve the diagnostic usefulness of CT. To better inform the clinical applications of this technique, further studies are needed involving a large dataset, a variety of pathologies, and other MR sequence of the lumbar spine.