Vision Transformers with direct coordinate prediction achieve superior performance in Cephalometric Landmark Detection

Direct coordinate prediction avoids memory-intensive heatmap prediction

General-purpose architectures show better generalization than highly specialized approaches

Demonstrated 2 mm improvement in mean radial error compared to state-of-the-art methods

Cephalometric Landmark Detection (CLD), i.e. annotating interest points in lateral X-ray images, is the crucial first step of every orthodontic therapy. While CLD has immense potential for automation using Deep Learning methods, carefully crafted contemporary approaches using convolutional neural networks and heatmap prediction do not qualify for large-scale clinical application due to insufficient performance. We propose a novel approach using Vision Transformers (ViTs) with direct coordinate prediction, avoiding the memory-intensive heatmap prediction common in previous work. Through extensive ablation studies comparing our method against contemporary CNN architectures (ConvNext V2) and heatmap-based approaches (Segformer), we demonstrate that ViTs with coordinate prediction achieve superior performance with more than 2 mm improvement in mean radial error compared to state-of-the-art CLD methods. Our results show that while non-adapted CNN architectures perform poorly on the given task, contemporary approaches may be too tailored to specific datasets, failing to generalize to different and especially sparse datasets. We conclude that using general-purpose Vision Transformers with direct coordinate prediction shows great promise for future research on CLD and medical computer vision.

Cephalometric landmark detection

Vision transformers

Medical imaging

Deep learning

Orthodontics

Computer vision

© 2025 The Authors. Published by Elsevier Ltd on behalf of European Association for Cranio-Maxillo-Facial Surgery.