Accuracy of auto-identification of the posteroanterior cephalometric landmarks using cascade convolution neural network algorithm and cephalometric images of different quality from nationwide multiple centers

• Published in: American journal of orthodontics and dentofacial orthopedics 2022-04, Vol.161 (4), p.e361-e371
• Main Authors: Gil, Soo-Min, Kim, Inhwan, Cho, Jin-Hyoung, Hong, Mihee, Kim, Minji, Kim, Su-Jung, Kim, Yoon-Ji, Kim, Young Ho, Lim, Sung-Hoon, Sung, Sang Jin, Baek, Seung-Hak, Kim, Namkug, Kang, Kyung-Hwa
• Format: Article
• Language: English
• Subjects: Algorithms; Anatomic Landmarks; Cephalometry - methods; Humans; Neural Networks, Computer; Radiography; Reproducibility of Results
• ISSN: 0889-5406; 1097-6752
• DOI: 10.1016/j.ajodo.2021.11.011

The purpose of this study was to evaluate the accuracy of auto-identification of the posteroanterior (PA) cephalometric landmarks using the cascade convolution neural network (CNN) algorithm and PA cephalogram images of a different quality from nationwide multiple centers nationwide. Of the 2798 PA cephalograms from 9 university hospitals, 2418 images (2075 training set and 343 validation set) were used to train the CNN algorithm for auto-identification of 16 PA cephalometric landmarks. Subsequently, 99 pretreatment images from the remaining 380 test set images were used to evaluate the accuracy of auto-identification of the CNN algorithm by comparing with the identification by a human examiner (gold standard) using V-Ceph 8.0 (Ostem, Seoul, South Korea). Pretreatment images were used to eliminate the effects of orthodontic bracket, tube and wire, surgical plate, and surgical screws. Paired t test was performed to compare the x- and y-coordinates of each landmark. The point-to-point error and the successful detection rate (range, within 2.0 mm) were calculated. The number of landmarks without a significant difference between the location identified by the human examiner and by auto-identification by the CNN algorithm were 8 on the x-coordinate and 5 on the y-coordinate, respectively. The mean point-to-point error was 1.52 mm. The low point-to-point error (2.0 mm) was observed at the maxillary right first molar root apex (2.18 mm). The mean successful detection rate of auto-identification was 83.3%. Cascade CNN algorithm for auto-identification of PA cephalometric landmarks showed a possibility of an effective alternative to manual identification. •Cascade CNN algorithm showed clinically acceptable accuracy for auto-identification of PA cephalometric landmarks.•This study was the first to investigate the accuracy of auto-identification of PA cephalometric landmarks using the cascade CNN algorithm.•This study is the first to use PA cephalogram images of different qualities from 9 nationwide multicenters.•Cascaded CNN algorithm for auto-identification of PA cephalometric landmarks showed a possibility of an effective alternative to manual identification.