EUVIMEDEUVIMED entdecken
EvaluationsstudieOpen Access

Evaluation of automated photograph-cephalogram image integration using artificial intelligence models

Jun-Ho Moon, Min-Gyu Kim, Sung Joo Cho, Dong-Yub Ko, Hye-Won Hwang, Ji-Ae Park, Shin-Jae Lee

The Angle Orthodontist · 2024

DOI: 10.2319/010124-1.1 ↗

Kurz gefasst

Evaluationsstudie in der Zeitschrift The Angle Orthodontist, 2024. Verfasst von Jun-Ho Moon und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Cephalometry, Artificial Intelligence, Photography, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To develop and evaluate an automated method for combining a digital photograph with a lateral cephalogram. Materials and Methods A total of 985 digital photographs were collected and soft tissue landmarks were manually detected. Then 2500 lateral cephalograms were collected, and corresponding soft tissue landmarks were manually detected. Using the images and landmark identification information, two different artificial intelligence (AI) models—one for detecting soft tissue on photographs and the other for identifying soft tissue on cephalograms—were developed using different deep-learning algorithms. The digital photographs were rotated, scaled, and shifted to minimize the squared sum of distances between the soft tissue landmarks identified by the two different AI models. As a validation process, eight soft tissue landmarks were selected on digital photographs and lateral cephalometric radiographs from 100 additionally collected validation subjects. Paired t- tests were used to compare the accuracy of measures obtained between the automated and manual image integration methods.

Results

The validation results showed statistically significant differences between the automated and manual methods on the upper lip and soft tissue B point. Otherwise, no statistically significant difference was found.

Conclusions

Automated photograph-cephalogram image integration using AI models seemed to be as reliable as manual superimposition procedures.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CephalometryArtificial IntelligencePhotographyImage Processing, Computer-AssistedAnatomic LandmarksHumansAlgorithmsFemaleFaceMaleDeep LearningAdolescentReproducibility of Results

Stichwörter der Autor:innen

Artificial intelligenceDigital photographLateral cephalogramSoft-tissue landmark

Zitieren

APA

Moon, J. H., Kim, M. G., Cho, S. J., Ko, D. Y., Hwang, H. W., Park, J. A., & Lee, S. J. (2024). Evaluation of automated photograph-cephalogram image integration using artificial intelligence models. The Angle Orthodontist. https://doi.org/10.2319/010124-1.1

Vancouver

Moon JH, Kim MG, Cho SJ, Ko DY, Hwang HW, Park JA, et al. Evaluation of automated photograph-cephalogram image integration using artificial intelligence models. The Angle Orthodontist. 2024. doi:10.2319/010124-1.1

BibTeX
@article{Moon2024,
  author = {Moon, Jun-Ho and Kim, Min-Gyu and Cho, Sung Joo and Ko, Dong-Yub and Hwang, Hye-Won and Park, Ji-Ae and Lee, Shin-Jae},
  title = {Evaluation of automated photograph-cephalogram image integration using artificial intelligence models},
  journal = {The Angle Orthodontist},
  year = {2024},
  doi = {10.2319/010124-1.1}
}
Kostenlos starten →