EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

3D evaluation model of facial aesthetics based on multi‐input 3D convolution neural networks for orthognathic surgery

Qingchuan Ma, Etsuko Kobayashi, Siao Jin, Ken Masamune, Hideyuki Suenaga iD

The International Journal of Medical Robotics and Computer Assisted Surgery · 2024

DOI: 10.1002/rcs.2651 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Medical Robotics and Computer Assisted Surgery, 2024. Verfasst von Qingchuan Ma und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral-Maxillofacial Surgery and Orthodontics, The University of Tokyo Hospital, Tokyo, Japan. Hauptthemen laut MEDLINE: Neural Networks, Computer, Imaging, Three-Dimensional, Face, Esthetics. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, Japan Agency for Medical Research and Development, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Quantitative evaluation of facial aesthetics is an important but also time‐consuming procedure in orthognathic surgery, while existing 2D beauty‐scoring models are mainly used for entertainment with less clinical impact.

Methods

A deep‐learning‐based 3D evaluation model DeepBeauty3D was designed and trained using 133 patients' CT images. The customised image preprocessing module extracted the skeleton, soft tissue, and personal physical information from raw DICOM data, and the predicting network module employed 3‐input‐2‐output convolution neural networks (CNN) to receive the aforementioned data and output aesthetic scores automatically.

Results

Experiment results showed that this model predicted the skeleton and soft tissue score with 0.231 ± 0.218 (4.62%) and 0.100 ± 0.344 (2.00%) accuracy in 11.203 ± 2.824 s from raw CT images.

Conclusion

This study provided an end‐to‐end solution using real clinical data based on 3D CNN to quantitatively evaluate facial aesthetics by considering three anatomical factors simultaneously, showing promising potential in reducing workload and bridging the surgeon‐patient aesthetics perspective gap.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerImaging, Three-DimensionalFaceEstheticsOrthognathic Surgical ProceduresTomography, X-Ray ComputedHumansFemaleMaleDeep LearningAdultOrthognathic SurgeryImage Processing, Computer-AssistedYoung AdultAlgorithms

Stichwörter der Autor:innen

convolution neural networksfacial aestheticsgolden ratioorthognathic surgeryvisual perception

Autor:innen und Institutionen

  • Department of Oral-Maxillofacial Surgery and Orthodontics, The University of Tokyo Hospital, Tokyo, Japan.
  • School of Engineering Medicine, Beihang University, Beijing, China.
  • Department of Precision Engineering, The University of Tokyo, Tokyo, Japan.
  • Institute of Advanced BioMedical Engineering and Science, Tokyo Women's Medical University, Tokyo, Japan.

ORCID-Profile: Hideyuki Suenaga

Förderung

  • Japan Society for the Promotion of Science
  • Japan Agency for Medical Research and Development
  • National Natural Science Foundation of China

Zitieren

APA

Ma, Q., Kobayashi, E., Jin, S., Masamune, K., & Suenaga, H. (2024). 3D evaluation model of facial aesthetics based on multi‐input 3D convolution neural networks for orthognathic surgery. The International Journal of Medical Robotics and Computer Assisted Surgery. https://doi.org/10.1002/rcs.2651

Vancouver

Ma Q, Kobayashi E, Jin S, Masamune K, Suenaga H. 3D evaluation model of facial aesthetics based on multi‐input 3D convolution neural networks for orthognathic surgery. The International Journal of Medical Robotics and Computer Assisted Surgery. 2024. doi:10.1002/rcs.2651

BibTeX
@article{Ma2024,
  author = {Ma, Qingchuan and Kobayashi, Etsuko and Jin, Siao and Masamune, Ken and Suenaga, Hideyuki},
  title = {3D evaluation model of facial aesthetics based on multi‐input 3D convolution neural networks for orthognathic surgery},
  journal = {The International Journal of Medical Robotics and Computer Assisted Surgery},
  year = {2024},
  doi = {10.1002/rcs.2651}
}
Kostenlos starten →