Cephalometric analysis is a fundamental examination which is routinely used in fields of orthodontics and orthognathics [1]. Many analysis methods have been proposed for cephalometric analysis, such as Ricketts analysis [2], Downs analysis [3] and Steiner analysis [4]. The key operation during the analysis is marking craniofacial landmarks from lateral cephalograms, since they serve as the datum of the succeeding qualitative assessment of angles and distances which provide diagnosis information of the craniofacial condition of a patient and affect treatment planning decision. Due to the X-ray imaging quality of the skull and the individual variations of anatomical types, it is not easy to reliably locate the landmarks in lateral cephalograms with high precision. Reliable landmark annotations often require experienced doctors, and even for seasoned orthodontists, manually identifying these landmarks can be a time-consuming process [5]. Hence, fully automatic and accurate landmark localization has been a long-standing area with a great deal of need. In the past two decades, many cephalometric landmark detection methods have been proposed and massive progress has been achieved continuously especially in the era of deep learning. However, most of the existing studies only contain single-center/single-vendor data, or few landmarks, which makes it unclear that if the performance obtained on these datasets can generalize well on more diverse datasets. Our challenge, named CLDetection2023, aims to provide a comprehensive benchmark for cephalometric landmark detection methods. The main topic of this challenge is finding automatic algorithms to accurately localize the cephalometric landmarks in lateral X-ray images. It will provide the largest and most diverse cephalometric landmark detection dataset by extending the existing benchmark datasets with more landmark annotations, including ISBI 2015 Challenge [6] and PKU cephalogram dataset [7]. Specifically, our dataset, includes 600 X-ray images from 3 medical centers with multi-center, multi-vendor, and more-landmarks. We annotated a total of 38 craniofacial landmarks for all cases, which can support almost all cephalometric analysis methods, which is a feature that previous public datasets do not have. This challenge will provide a unique opportunity for participants from different backgrounds (e.g. academia, industry, and government, etc.) to compare their algorithms in an impartial way. [1] Proffit W R, Fields Jr H W, Sarver D M. Contemporary orthodontics[M]. Elsevier Health Sciences, 2006. [2] Ricketts R M. Orthodontic Diagnosis and Planning: --Their roles in preventive and rehabilitative dentistry[M]. Rocky Mountain/Orthodontics, 1982. [3] Downs W B. Variations in facial relationships: their significance in treatment and prognosis[J]. American journal of orthodontics, 1948, 34(10): 812-840. [4] Steiner C C. Cephalometrics for you and me[J]. American journal of orthodontics, 1953, 39(10): 729-755. [5] Durão A P R, Morosolli A, Pittayapat P, et al. Cephalometric landmark variability among orthodontists and dentomaxillofacial radiologists: a comparative study[J]. Imaging science in dentistry, 2015, 45(4): 213-220. [6] Wang C W, Huang C T, Lee J H, et al. A benchmark for comparison of dental radiography analysis algorithms[J]. Medical image analysis, 2016, 31: 63-76. [7] Zeng M, Yan Z, Liu S, et al. Cascaded convolutional networks for automatic cephalometric landmark detection[J]. Medical Image Analysis, 2021, 68: 101904. [8] Li W, Lu Y, Zheng K, et al. Structured landmark detection via topology-adapting deep graph learning[C] //European Conference on Computer Vision. Springer, Cham, 2020: 266-283. [9] Zhong Z, Li J, Zhang Z, et al. An attention-guided deep regression model for landmark detection in cephalograms[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2019: 540-548. [10] Proffit W R, Fields Jr H W, Sarver D M. Contemporary orthodontics[M]. Elsevier Health Sciences, 2006.