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

TL;DR

CephRes-MHNet is a novel multi-head residual network that significantly improves the accuracy and robustness of cephalometric landmark detection in X-ray images, outperforming existing models with fewer parameters.

Contribution

Introduces CephRes-MHNet, a multi-head residual convolutional network with dual-attention mechanisms for improved landmark detection accuracy and efficiency.

Findings

Achieved a mean radial error of 1.23 mm

Attained a success detection rate of 85.5% at 2.0 mm

Outperformed baseline models while using fewer parameters

Abstract

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, CephRes-MHNet 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 mm, SDR @ 2.0 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.