PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 10, 2026IET Computer Vision0 citationsOpen Access

Cephalometric Landmark Detection Using a Multi‐Scale Cross‐Attention Model

View Full Paper
SXShuli XingHLHao LiangGMguojun mao

Key Points

  • The study aims to improve automatic detection of cephalometric landmarks using a novel model.
  • Developed a multi-scale cross-attention model for feature extraction.
  • Reduced computational complexity related to global attention.
  • Generated multiple outputs for each landmark position prediction.
  • Tested model performance with varying Gaussian kernel sizes.
  • Achieved competitive accuracy in landmark detection without pretrained processes.
  • Demonstrated significance of Gaussian kernel size on model effectiveness.
  • Outperformed conventional manual annotation methods in time and cost efficiency.

Abstract

ABSTRACT The annotation of cephalometric landmarks plays a critical role in craniofacial diagnosis and treatment. Compared to conventional manual methods, deep learning‐based automated approaches significantly reduce both time requirements and labour costs. Most current deep learning models primarily rely on convolutional neural networks, but these models exhibit limitations in capturing long‐range dependencies between pixels. Transformer‐based models can effectively address this issue; however, they exhibit poor inductive bias when applied to small‐scale image datasets and are computationally expensive to train on high‐resolution images. In this paper, we propose a novel feature extraction module that reduces the quadratic complexity of computing global attention while enhancing the diversity of global features. Moreover, we extend the range of the original heatmap values and generate multiple outputs for each landmark position prediction. We integrate these components into a simple U‐shaped model, and it achieves competitive detection accuracy without using any pretrained or additional processes compared to several recent methods. In addition, our experiments reveal that the Gaussian kernel size is a critical factor affecting model performance, a parameter that has not been extensively explored in the existing literature.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Xing et al. (2026) studied this question.

synapsesocial.com/papers/69af95a470916d39fea4d69chttps://doi.org/10.1049/cvi2.70056
Ask AI
Helpful
Bookmark
Share
View Full Paper