Accurate and robust cephalometric image analysis plays an essential role in orthodontic diagnosis, treatment assessment and surgical planning. This paper proposes a novel landmark localization method for cephalometric analysis using multiscale image patch-based graph convolutional networks. In detail, image patches with the same size are hierarchically sampled from the Gaussian pyramid to well preserve multiscale context information. We combine local appearance and shape information into spatialized features with an attention module to enrich node representations in graph. The spatial relationships of landmarks are built with the incorporation of three-layer graph convolutional networks, and multiple landmarks are simultaneously updated and moved toward the targets in a cascaded coarse-to-fine process. Quantitative results obtained on publicly available cephalometric X-ray images have exhibited superior performance compared with other state-of-the-art methods in terms of mean radial error and successful detection rate within various precision ranges. Our approach performs significantly better especially in the clinically accepted range of 2 mm and this makes it suitable in cephalometric analysis and orthognathic surgery.

Accurate and robust anatomical landmark localization is a mandatory and crucial step in deformation diagnosis and treatment planning for patients with craniomaxillofacial (CMF) malformations. In this paper, we propose a trainable end-to-end cephalometric landmark localization framework on Cone-beam computed tomography (CBCT) scans, referred to as CMF-Net, which combines the appearance with transformers, geometric constraint, and adaptive wing (AWing) loss. More precisely: (1) we decompose the localization task into two branches: the appearance branch integrates transformers for identifying the exact positions of candidates, while the geometric constraint branch at low resolution allows the implicit spatial relationships to be effectively learned on the reduced training data. (2) We use the AWing loss to leverage the difference between the pixel values of the target heatmaps and the automatic prediction heatmaps. We verify our CMF-Net by identifying the 24 most relevant clinical landmarks on 150 dental CBCT scans with complicated scenarios collected from real-world clinics. Comprehensive experiments show that it performs better than the state-of-the-art deep learning methods, with an average localization error of 1.108 mm (the clinically acceptable precision range being 1.5 mm) and a correct landmark detection rate equal to 79.28%. Our CMF-Net is time-efficient and able to locate skull landmarks with high accuracy and significant robustness. This approach could be applied in 3D cephalometric measurement, analysis, and surgical planning.

Objective . Cephalometric alandmark localization is of great clinical significance in diagnosing and treating patients with dental-maxillofacial deformities. Domain shifts across clinical centers significantly hinder model generalizability, causing existing methods to struggle with accurate and robust anatomical landmark localization due to insufficient alignment of high-level semantic features across domains. We aim to improve the cross-domain generalizability of cephalometric landmark detection by aligning semantic features and enhancing output resolution under an unsupervised domain adaptation (UDA) setting. Approach . In this paper, we propose bi-Level alignment with super-resolution head, an effective framework for precise and robust anatomical landmark detection under UDA. Specifically, we employ adaptive instance normalization to generate target-style images while preserving original anatomical spatial structure at the input level. At the output level, a Mean–Teacher framework leverages high-quality pseudo-labels from the teacher model to guide the student model’s learning. Additionally, a lightweight super-resolution head enables the generation of high-resolution heatmaps from the multi-scale feature maps and the low-resolution heatmaps, reducing quantization errors with low computational cost. Results . The proposed method achieved a mean localization error of 1.64 mm, a successful detection rate of 72.68% within the clinically acceptable threshold of 2 mm, and an average classification accuracy of 81.81% for anatomical types. Significance . Extensive experiments on public cephalometric datasets demonstrate superiority over state-of-the-art UDA methods, highlighting its potential for clinical applications in cephalometric analysis and orthodontic surgery planning.