Visual enhancement of Cone‐beam CT by use of CycleGAN

• Published in: Medical physics (Lancaster) 2020-03, Vol.47 (3), p.998-1010
• Main Authors: Kida, Satoshi, Kaji, Shizuo, Nawa, Kanabu, Imae, Toshikazu, Nakamoto, Takahiro, Ozaki, Sho, Ohta, Takeshi, Nozawa, Yuki, Nakagawa, Keiichi
• Format: Article
• Language: English
• Subjects: CBCT; Cone-Beam Computed Tomography; Deep Learning; deep neural networks; generative adversarial networks; Humans; image correction; Image Processing, Computer-Assisted - methods; planning CT
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1002/mp.13963

Purpose Cone‐beam computed tomography (CBCT) offers advantages over conventional fan‐beam CT in that it requires a shorter time and less exposure to obtain images. However, CBCT images suffer from low soft‐tissue contrast, noise, and artifacts compared to conventional fan‐beam CT images. Therefore, it is essential to improve the image quality of CBCT. Methods In this paper, we propose a synthetic approach to translate CBCT images with deep neural networks. Our method requires only unpaired and unaligned CBCT images and planning fan‐beam CT (PlanCT) images for training. The CBCT images and PlanCT images may be obtained from other patients as long as they are acquired with the same scanner settings. Once trained, three‐dimensionally reconstructed CBCT images can be directly translated into high‐quality PlanCT‐like images. Results We demonstrate the effectiveness of our method with images obtained from 20 prostate patients, and provide a statistical and visual comparison. The image quality of the translated images shows substantial improvement in voxel values, spatial uniformity, and artifact suppression compared to those of the original CBCT. The anatomical structures of the original CBCT images were also well preserved in the translated images. Conclusions Our method produces visually PlanCT‐like images from CBCT images while preserving anatomical structures.