Optimising for the Unknown: Domain Alignment for Cephalometric Landmark Detection

Julian Wyatt, Irina Voiculescu
10/6/2024
cs.CV

Official code: Julian-Wyatt/OptimisingfortheUnknown (8 stars, last commit 2024-10-05).

Abstract

Cephalometric Landmark Detection is the process of identifying key areas for cephalometry. Each landmark is a single GT point labelled by a clinician. A machine learning model predicts the probability locus of a landmark represented by a heatmap. This work, for the 2024 CL-Detection MICCAI Challenge, proposes a domain alignment strategy with a regional facial extraction module and an X-ray artefact augmentation procedure. The challenge ranks our method's results as the best in MRE of 1.186mm and third in the 2mm SDR of 82.04% on the online validation leaderboard. The code is available at https://github.com/Julian-Wyatt/OptimisingfortheUnknown.

View on arXivView PDF

Code Implementations(1)

Julian-Wyatt/OptimisingfortheUnknownOfficial100%

MICCAI Cephalometric Landmark Detection Challenge Submission with paper titled Optimising for the Unknown.

80Shell, PythonSep 29, 20242 years ago

Similar Papers

Deep Learning Techniques for Automatic Lateral X-ray Cephalometric Landmark Detection: Is the Problem Solved?

86% match2024

PAL-Net: A Point-Wise CNN with Patch-Attention for 3D Facial Landmark Localization

83% match1 repo82025

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

83% match2025

Cephalometric Landmark Detection across Ages with Prototypical Network

82% match1 repo262024

nnLandmark: A Self-Configuring Method for 3D Medical Landmark Detection

82% match1 repo412025

Self-CephaloNet: A Two-stage Novel Framework using Operational Neural Network for Cephalometric Analysis

82% match2025

Cite this paper

@article{wyatt2024optimising,
  title  = {Optimising for the Unknown: Domain Alignment for Cephalometric Landmark Detection},
  author = {Julian Wyatt and Irina Voiculescu},
  year   = {2024},
  eprint = {2410.04445},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.04445v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.04445.svg)](https://codeofpaper.com/paper/2410.04445)

Discussion