Cascaded convolutional networks for automatic cephalometric landmark detection.

Journal: Medical image analysis
Published Date:

Abstract

Cephalometric analysis is a fundamental examination which is widely used in orthodontic diagnosis and treatment planning. Its key step is to detect the anatomical landmarks in lateral cephalograms, which is time-consuming in traditional manual way. To solve this problem, we propose a novel approach with a cascaded three-stage convolutional neural networks to predict cephalometric landmarks automatically. In the first stage, high-level features of the craniofacial structures are extracted to locate the lateral face area which helps to overcome the appearance variations. Next, we process the aligned face area to estimate the locations of all landmarks simultaneously. At the last stage, each landmark is refined through a dedicated network using high-resolution image data around the initial position to achieve more accurate result. We evaluate the proposed method on several anatomical landmark datasets and the experimental results show that our method achieved competitive performance compared with the other methods.

Authors

  • Minmin Zeng
    Fourth Clinical Division, School and Hospital of Stomatology, Peking University, Beijing, China. Electronic address: bdzengmw@163.com.
  • Zhenlei Yan
    Ling. AI, Beijing, China.
  • Shuai Liu
    Graduate School of Chinese Academy of Traditional Chinese Medicine, Beijing, China.
  • Yanheng Zhou
    Department of orthodontics, School and Hospital of Stomatology, Peking University, Beijing, China.
  • Lixin Qiu
    Fourth Clinical Division, School and Hospital of Stomatology, Peking University, Beijing, China.