Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report

Evi M. C. Huijben, Maarten L. Terpstra, Arthur Jr Galapon, Suraj Pai, Adrian Thummerer, Peter Koopmans, Manya Afonso, Maureen A. J. M. van Eijnatten, Oliver J. Gurney-Champion, Zeli Chen, Yiwen Zhang, Kaiyi Zheng, Chuanpu Li, Haowen Pang, Chuyang Ye, Runqi Wang, Tao Song, Fuxin Fan, Jingna Qiu, Yixing Huang et al. (39 additional authors not shown)

Abstract: Highlights•SynthRAD2023 is the first large multi-center CT synthesis challenge for radiotherapy.•SynthRAD offers benchmark datasets and methods to evaluate image synthesis.•The challenge focused on MRI- or CBCT-to-CT synthesis for pelvis and brain.•Large participation was obtained, with 22 (MRI-to-CT) and 17 (CBCT-to-CT) teams.•Top-performing teams achieved excellent image similarity and dose accuracy.