A semi-supervised learning approach for automated 3D cephalometric landmark identification using computed tomography
Open Access
- 28 September 2022
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (9) , e0275114
Abstract
Identification of 3D cephalometric landmarks that serve as proxy to the shape of human skull is the fundamental step in cephalometric analysis. Since manual landmarking from 3D computed tomography (CT) images is a cumbersome task even for the trained experts, automatic 3D landmark detection system is in a great need. Recently, automatic landmarking of 2D cephalograms using deep learning (DL) has achieved great success, but 3D landmarking for more than 80 landmarks has not yet reached a satisfactory level, because of the factors hindering machine learning such as the high dimensionality of the input data and limited amount of training data due to the ethical restrictions on the use of medical data. This paper presents a semi-supervised DL method for 3D landmarking that takes advantage of anonymized landmark dataset with paired CT data being removed. The proposed method first detects a small number of easy-to-find reference landmarks, then uses them to provide a rough estimation of the all landmarks by utilizing the low dimensional representation learned by variational autoencoder (VAE). The anonymized landmark dataset is used for training the VAE. Finally, coarse-to-fine detection is applied to the small bounding box provided by rough estimation, using separate strategies suitable for the mandible and the cranium. For mandibular landmarks, patch-based 3D CNN is applied to the segmented image of the mandible (separated from the maxilla), in order to capture 3D morphological features of mandible associated with the landmarks. We detect 6 landmarks around the condyle all at once rather than one by one, because they are closely related to each other. For cranial landmarks, we again use the VAE-based latent representation for more accurate annotation. In our experiment, the proposed method achieved a mean detection error of 2.88 mm for 90 landmarks using only 15 paired training data.Keywords
Funding Information
- Korea Health Industry Development Institute (HI20C0127)
- Korea Health Industry Development Institute (HI20C0127)
- Korea Health Industry Development Institute (HI20C0127)
This publication has 17 references indexed in Scilit:
- Fully Automatic System for Accurate Localisation and Analysis of Cephalometric Landmarks in Lateral CephalogramsScientific Reports, 2016
- Computer-aided cephalometric landmark annotation for CBCT dataInternational Journal of Computer Assisted Radiology and Surgery, 2016
- A new mandible-specific landmark reference system for three-dimensional cephalometry using cone-beam computed tomographyEuropean Journal of Orthodontics, 2015
- Three-dimensional architectural and structural analysis—a transition in concept and design from Delaire's cephalometric analysisInternational Journal of Oral and Maxillofacial Surgery, 2014
- Three‐dimensional cephalometric analysis in orthodontics: a systematic reviewOrthodontics & Craniofacial Research, 2013
- Empirical beam hardening correction (EBHC) for CTMedical Physics, 2010
- A comparison of two-dimensional radiography and three-dimensional computed tomography in angular cephalometric measurementsDentomaxillofacial Radiology, 2010
- Comparison between traditional 2-dimensional cephalometry and a 3-dimensional approach on human dry skullsAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2004
- Efficient component labeling of images of arbitrary dimension represented by linear bintreesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1988
- Cephalometric analysis as a tool for treatment planning and evaluationEuropean Journal of Orthodontics, 1981