Abstract: The currently existing deep learning models are still unable to accurately and reliably locate anatomical landmark points on 2D cephalometric X-ray images. To address this issue,  proposes a localization model  for cephalometric measurement based on appearance token and landmark token. Firstly, fixed-size image patches of different resolutions are sampled from the original image and input into a feature extraction network to extract multi-scale features. Then, these features are converted into appearance tokens through linear projection and, together with landmark tokens, input into a relational reasoning layer. This allows the landmark tokens to learn the intrinsic relationships between the appearance tokens and the land-marks in the interence layer. Finally, through multiple iterative inferences, the model moves the initial points from coarse to fine in a cascaded manner towards the target. Compared with advanced baseline models, the proposed model demonstrates superior localization performance on public cephalometric X-ray images.

Key words: cascaded manner, cephalometric measurement, landmark localization, relational inference