Orthognathic surgical planning using graph CNN with dual embedding module: External validations with multi-hospital datasets

In Hwan Kim, Jun Sik Kim, Jiheon Jeong, Jae Woo Park, Kanggil Park, Jin Hyoung Cho, Mihee Hong, Kyung Hwa Kang, Minji Kim, Su Jung Kim, Yoon Ji Kim, Sang Jin Sung, Young Ho Kim, Sung Hoon Lim, Seung Hak Baek, Namkug Kim

Research output: Contribution to journalArticlepeer-review


Background and objective: Despite recent development of AI, prediction of the surgical movement in the maxilla and mandible by OGS might be more difficult than that of tooth movement by orthodontic treatment. To evaluate the prediction accuracy of the surgical movement using pairs of pre-(T0) and post-surgical (T1) lateral cephalograms (lat-ceph) of orthognathic surgery (OGS) patients and dual embedding module-graph convolution neural network (DEM-GCNN) model. Methods: 599 pairs from 3 institutions were used as training, internal validation, and internal test sets and 201 pairs from other 6 institutions were used as external test set. DEM-GCNN model (IEM, learning the lat-ceph images; LTEM, learning the landmarks) was developed to predict the amount and direction of surgical movement of ANS and PNS in the maxilla and B-point and Md1crown in the mandible. The distance between T1 landmark coordinates actually moved by OGS (ground truth) and predicted by DEM-GCNN model and pre-existed CNN-based Model-C (learning the lat-ceph images) was compared. Results: In both internal and external tests, DEM-GCNN did not exhibit significant difference from ground truth in all landmarks (ANS, PNS, B-point, Md1crown, all P > 0.05). When the accumulated successful detection rate for each landmark was compared, DEM-GCNN showed higher values than Model-C in both the internal and external tests. In violin plots exhibiting the error distribution of the prediction results, both internal and external tests showed that DEM-GCNN had significant performance improvement in PNS, ANS, B-point, Md1crown than Model-C. DEM-GCNN showed significantly lower prediction error values than Model-C (one-jaw surgery, B-point, Md1crown, all P < 0.005; two-jaw surgery, PNS, ANS, all P < 0.05; B point, Md1crown, all P < 0.005). Conclusion: We developed a robust OGS planning model with maximized generalizability despite diverse qualities of lat-cephs from 9 institutions.

Original languageEnglish
Article number107853
JournalComputer Methods and Programs in Biomedicine
StatePublished - Dec 2023

Bibliographical note

Publisher Copyright:
© 2023 Elsevier B.V.


  • Cephalometry
  • Deep learning
  • Dual embedding module
  • Graph convolution neural network
  • Maxillofacial surgery
  • Multicenter study
  • Orthognathic surgery
  • Surgical prediction


Dive into the research topics of 'Orthognathic surgical planning using graph CNN with dual embedding module: External validations with multi-hospital datasets'. Together they form a unique fingerprint.

Cite this