Deep learning synthesis of cone-beam computed tomography from zero echo time magnetic resonance imaging

• Published in: Scientific reports Vol. 13; no. 1; p. 6031
• Main Authors: Choi, Hyeyeon, Yun, Jong Pil, Lee, Ari, Han, Sang-Sun, Kim, Sang Woo, Lee, Chena
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 13.04.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 692/698/3008; 692/700/3032/3093; Computed tomography; Cone-Beam Computed Tomography - methods; Deep Learning; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted - methods; Magnetic Resonance Imaging; multidisciplinary; Phantoms, Imaging; Radiation; Science; Science (multidisciplinary); Tomography
• DOI: 10.1038/s41598-023-33288-8
• ISSN: 2045-2322

Cone-beam computed tomography (CBCT) produces high-resolution of hard tissue even in small voxel size, but the process is associated with radiation exposure and poor soft tissue imaging. Thus, we synthesized a CBCT image from the magnetic resonance imaging (MRI), using deep learning and to assess its clinical accuracy. We collected patients who underwent both CBCT and MRI simultaneously in our institution (Seoul). MRI data were registered with CBCT data, and both data were prepared into 512 slices of axial, sagittal, and coronal sections. A deep learning-based synthesis model was trained and the output data were evaluated by comparing the original and synthetic CBCT (syCBCT). According to expert evaluation, syCBCT images showed better performance in terms of artifacts and noise criteria but had poor resolution compared to the original CBCT images. In syCBCT, hard tissue showed better clarity with significantly different MAE and SSIM. This study result would be a basis for replacing CBCT with non-radiation imaging that would be helpful for patients planning to undergo both MRI and CBCT.