CephRes-MHNet: A Multi-Head Residual Network for Accurate and Robust Cephalometric Landmark Detection

Accurate localization of cephalometric landmarks from 2D lateral skull X-rays is vital for orthodontic diagnosis and treatment. Manual annotation is time-consuming and error-prone, whereas automated approaches often struggle with low contrast and anatomical complexity. This paper introduces CephRes-MHNet, a multi-head residual convolutional network for robust and efficient cephalometric landmark detection. The architecture integrates residual encoding, dual-attention mechanisms, and multi-head decoders to enhance contextual reasoning and anatomical precision. Trained on the Aariz Cephalometric dataset of 1,000 radiographs, CephResMHNet achieved a mean radial error (MRE) of 1.23 mm and a success detection rate (SDR) @ 2.0 mm of 85.5 %, outperforming all evaluated models. In particular, it exceeded the strongest baseline, the attention-driven AFPF-Net (MRE$=1.25 ~\text{mm}$, SDR @$2.0 ~\text{mm}= 84.1 \%$), while using less than 25 % of its parameters. These results demonstrate that CephRes-MHNet attains state-of-the-art accuracy through architectural efficiency, providing a practical solution for real-world orthodontic analysis.