Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Optimising for the Unknown: Domain Alignment for Cephalometric Landmark Detection

Julian Wyatt, Irina Voiculescu

TL;DR

This work proposes a domain alignment strategy with a regional facial extraction module and an X-ray artefact augmentation procedure for CL-Detection MICCAI Challenge, ranked as the best in MRE and third in the 2mm SDR on the online validation leaderboard.

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.

Optimising for the Unknown: Domain Alignment for Cephalometric Landmark Detection

TL;DR

This work proposes a domain alignment strategy with a regional facial extraction module and an X-ray artefact augmentation procedure for CL-Detection MICCAI Challenge, ranked as the best in MRE and third in the 2mm SDR on the online validation leaderboard.

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.
Paper Structure (12 sections, 4 figures, 2 tables)

This paper contains 12 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. RCNN regional facial extraction
  4. Landmark heatmap regression
  5. Experiments
  6. Dataset
  7. Implementation details
  8. Augmentations and X-ray artefact simulation
  9. Results and discussion
  10. Limitations & future work
  11. Conclusion
  12. Acknowledgements.

Figures (4)

  • Figure 1: Abstraction of the RCNN regional face extraction module.
  • Figure 2: ConvNeXt V2 MLP feature pyramid prediction architecture.
  • Figure 3: Ablation studies trained with the nano encoder. (a) Impact of RCNN padding around landmarks for bounding box generation during training from 16-128 pixels. Models are trained on patients 1-400 and evaluated on 401-600. Here, y is a deterministic image pad and crop method and z is a standard pad to aspect ratio and resize. (b) Effect of varying the frequency of X-ray artefact simulation on model performance (Fold 1). (c) Influence of the number of hottest heatmap values averaged to determine the final coordinates (Fold 1).
  • Figure 4: Qualitative results for four cases: the worst overall SDR for the tiny encoder ( 062.bmp), the worst for the baseline ( 194.bmp), and two hand-picked failure cases ( 447.bmp & 535.bmp). Blue dots represent predictions within $2mm$, red dots are outside $2mm$, and green dots are ground truth, with yellow lines connecting predictions to ground truth. The top-left number indicates the MRE for each image, and all images are cropped to square to highlight landmarks rather than by the RCNN module.