CBCT‐based synthetic CT image generation using a diffusion model for CBCT‐guided lung radiotherapy

• Published in: Medical physics (Lancaster) Vol. 51; no. 11; pp. 8168 - 8178
• Main Authors: Chen, Xiaoqian, Qiu, Richard L. J., Peng, Junbo, Shelton, Joseph W., Chang, Chih‐Wei, Yang, Xiaofeng, Kesarwala, Aparna H.
• Format: Journal Article
• Language: English
• Published: United States 01.11.2024
• Subjects: Algorithms; CBCT; Cone-Beam Computed Tomography - methods; Diffusion; diffusion model; Humans; Image Processing, Computer-Assisted - methods; image synthesis; Lung - diagnostic imaging; Lung - radiation effects; lung cancer; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - radiotherapy; Radiotherapy, Image-Guided - methods; synthetic CT; lung cancer; synthetic CT; diffusion model; image synthesis; CBCT
• ISSN: 0094-2405; 2473-4209; 2473-4209
• DOI: 10.1002/mp.17328

Background Although cone beam computed tomography (CBCT) has lower resolution compared to planning CTs (pCT), its lower dose, higher high‐contrast resolution, and shorter scanning time support its widespread use in clinical applications, especially in ensuring accurate patient positioning during the image‐guided radiation therapy (IGRT) process. Purpose While CBCT is critical to IGRT, CBCT image quality can be compromised by severe stripe and scattering artifacts. Tumor movement secondary to respiratory motion also decreases CBCT resolution. In order to improve the image quality of CBCT, we propose a Lung Diffusion Model (L‐DM) framework. Methods Our proposed algorithm is based on a conditional diffusion model trained on pCT and deformed CBCT (dCBCT) image pairs to synthesize lung CT images from dCBCT images and benefit CBCT‐based radiotherapy. dCBCT images were used as the constraint for the L‐DM. The image quality and Hounsfield unit (HU) values of the synthetic CTs (sCT) images generated by the proposed L‐DM were compared to three selected mainstream generation models. Results We verified our model in both an institutional lung cancer dataset and a selected public dataset. Our L‐DM showed significant improvement in the four metrics of mean absolute error (MAE), peak signal‐to‐noise ratio (PSNR), normalized cross‐correlation (NCC), and structural similarity index measure (SSIM). In our institutional dataset, our proposed L‐DM decreased the MAE from 101.47 to 37.87 HU and increased the PSNR from 24.97 to 29.89 dB, the NCC from 0.81 to 0.97, and the SSIM from 0.80 to 0.93. In the public dataset, our proposed L‐DM decreased the MAE from 173.65 to 58.95 HU, while increasing the PSNR, NCC, and SSIM from 13.07 to 24.05 dB, 0.68 to 0.94, and 0.41 to 0.88, respectively. Conclusions The proposed L‐DM significantly improved sCT image quality compared to the pre‐correction CBCT and three mainstream generative models. Our model can benefit CBCT‐based IGRT and other potential clinical applications as it increases the HU accuracy and decreases the artifacts from input CBCT images.