IEEE International Symposium on Computer-Based Medical Systems (CBMS) ·
Beyond Heatmaps: Self-Evolving Graph Neural Fields for Robust Cephalometric Landmark Detection
Published · Conference · Biomedical AI
One model locates craniofacial landmarks across different annotation protocols.
Abstract
Automated cephalometric landmark detection still constitutes a critical component of orthodontic diagnosis and treatment planning. Nevertheless, the current state of the art in heatmap regression and coordinate prediction is challenged by the presence of low-contrast images, highly variable anatomy, and the need to model complex spatial dependencies between landmarks. To overcome these difficulties, we propose Self-Evolving Graph Neural Fields (SE-GNF), a new framework that combines implicit neural models with graph-based spatial reasoning to support accurate, continuous, and sub-pixel landmark localization. SE-GNF consists of three main components: a neural-field module that maps sampled coordinates to smooth spatial representations, a Graph Attention Network encoder that encodes anatomical dependencies between craniofacial structures, and a cross-attention-based detector with learnable landmark-specific queries. Unlike discrete heatmap-based methods, SE-GNF provides differentiable coordinate predictions while maintaining anatomical relationships. The method generalizes to different cephalometric protocols without requiring any changes to the architecture. Experimentally, SE-GNF achieves mean radial errors of 0.98 mm (Test1) and 1.27 mm (Test2) on the ISBI 2015 challenge dataset (19 landmarks) and 0.70 mm on the ISBI 2023 challenge dataset (29 landmarks), thus providing a clinically sufficient level of precision for orthodontic landmark detection and treatment planning.
Findings
- Reports mean radial errors of 0.98 mm and 1.27 mm on ISBI 2015 Test1 and Test2.
- Reports 0.70 mm on ISBI 2023, covering a different 29-landmark protocol.
Sources and citation
View BibTeX citation
@inproceedings{neural-fields-2026,
title = {{Beyond Heatmaps: Self-Evolving Graph Neural Fields for Robust Cephalometric Landmark Detection}},
author = {Appana Saketh Krishna Rao and Kushal and BHVSP Subrahmanyam and Acchugatla Sravanthi and Neeraj Choudhary},
booktitle = {IEEE International Symposium on Computer-Based Medical Systems (CBMS)},
year = {2026},
pages = {1130--1135},
publisher = {IEEE},
url = {https://ieeexplore.ieee.org/abstract/document/11718174/}
}