Saved in:
Bibliographic Details
Main Authors: Jaheen, Ahmed, Hassan, Islam, Abouserie, Mohanad, Rehab, Abdelaty, Elasfar, Adham, Elmasry, Knzy, El-Dawlatly, Mostafa, Eldawlatly, Seif
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.10173
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912733931241472
author Jaheen, Ahmed
Hassan, Islam
Abouserie, Mohanad
Rehab, Abdelaty
Elasfar, Adham
Elmasry, Knzy
El-Dawlatly, Mostafa
Eldawlatly, Seif
author_facet Jaheen, Ahmed
Hassan, Islam
Abouserie, Mohanad
Rehab, Abdelaty
Elasfar, Adham
Elmasry, Knzy
El-Dawlatly, Mostafa
Eldawlatly, Seif
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10173
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CephRes-MHNet: A Multi-Head Residual Network for Accurate and Robust Cephalometric Landmark Detection
Jaheen, Ahmed
Hassan, Islam
Abouserie, Mohanad
Rehab, Abdelaty
Elasfar, Adham
Elmasry, Knzy
El-Dawlatly, Mostafa
Eldawlatly, Seif
Computer Vision and Pattern Recognition
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.
title CephRes-MHNet: A Multi-Head Residual Network for Accurate and Robust Cephalometric Landmark Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.10173