Localization of Craniomaxillofacial Landmarks on CBCT Images Using 3D Mask R-CNN and Local Dependency Learning

Yankun Lang, Chunfeng Lian, Deqiang Xiao, Hannah Deng, Kim Han Thung, Peng Yuan, Jaime Gateno, Tianshu Kuang, David M. Alfi, Li Wang, Dinggang Shen, James J. Xia, Pew Thian Yap

Research output: Contribution to journalArticlepeer-review

Abstract

Cephalometric analysis relies on accurate detection of craniomaxillofacial (CMF) landmarks from cone-beam computed tomography (CBCT) images. However, due to the complexity of CMF bony structures, it is difficult to localize landmarks efficiently and accurately. In this paper, we propose a deep learning framework to tackle this challenge by jointly digitalizing 105 CMF landmarks on CBCT images. By explicitly learning the local geometrical relationships between the landmarks, our approach extends Mask R-CNN for end-to-end prediction of landmark locations. Specifically, we first apply a detection network on a down-sampled 3D image to leverage global contextual information to predict the approximate locations of the landmarks. We subsequently leverage local information provided by higher-resolution image patches to refine the landmark locations. On patients with varying non-syndromic jaw deformities, our method achieves an average detection accuracy of 1.38±0.95mm, outperforming a related state-of-the-art method.

Original languageEnglish (US)
Pages (from-to)1
Number of pages1
JournalIEEE Transactions on Medical Imaging
DOIs
StateAccepted/In press - 2022

Keywords

  • Biomedical imaging
  • Craniomaxilloficial (CMF) landmark localization
  • Deep learning
  • Feature extraction
  • Location awareness
  • Mask R-CNN
  • Proposals
  • Surgery
  • Task analysis
  • Three-dimensional displays

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Localization of Craniomaxillofacial Landmarks on CBCT Images Using 3D Mask R-CNN and Local Dependency Learning'. Together they form a unique fingerprint.

Cite this