EUVIMEDEUVIMED entdecken
Crossref

Artificial intelligence-assisted grading for tear trough deformity

Kevin Yu-Ting Chen, Shin-Shi Tzeng, Hung-Chang Chen

Journal of Plastic, Reconstructive & Aesthetic Surgery · 2024

DOI: 10.1016/j.bjps.2024.07.048 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Plastic, Reconstructive & Aesthetic Surgery, 2024. Verfasst von Kevin Yu-Ting Chen und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plastic and Reconstructive Surgery, New Taipei Municipal Tucheng Hospital, New Taipei City, Taiwan; Department of Plastic and Reconstru…. Hauptthemen laut MEDLINE: Artificial Intelligence, Photography, Smartphone. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 19 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Various classification systems for tear trough deformity (TTD) have been published; however, their complexity can pose challenges in clinical use, especially for less experienced surgeons. It is believed that artificial intelligence (AI) technology can address some of these challenges by reducing inadvertent errors and improving the accuracy of medical practice. In this study, we aimed to establish a reliable and precise digital image grading model for TTD using smartphone-based photography enhanced using AI deep learning technology. This model is designed to aid and guide surgeons, particularly those who are less experienced or from younger generations, during clinical examinations and in making decisions regarding further surgical interventions. MATERIALS AND METHODS: A total of 504 patients and 983 photos were included in the study. We adopted the Barton's grading system for TTD. All photos were taken using the same smartphone and processed and analyzed using the medical AI assistant (MAIA™) software. The photos were then randomly divided into two groups to establish training and testing models. RESULTS: The confusion matrix for the training model demonstrated a sensitivity of 56%, specificity of 87.3%, F1 score of 0.57, and an area under the curve (AUROC) of 0.85. For the testing group, the sensitivity was 49.3%, specificity was 85%, F1 score was 0.49, and AUROC was 0.83. Representative heatmaps were also generated. CONCLUSION: Our study is the first to demonstrate that tear trough deformities can be easily categorized using a built-in smartphone camera in conjunction with an AI deep learning program. This approach can reduce errors during clinical patient evaluations, particularly for less experienced practitioners.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligencePhotographySmartphoneHumansFemaleMaleAdultMiddle AgedDeep LearningEyelidsSensitivity and Specificity

Stichwörter der Autor:innen

Artificial intelligenceDeep learningGrading systemSmartphoneTear trough deformity

Autor:innen und Institutionen

  • Department of Plastic and Reconstructive Surgery, New Taipei Municipal Tucheng Hospital, New Taipei City, Taiwan; Department of Plastic and Reconstructive Surgery, Chang Gung Memorial Hospital, Chang Gung University Col…
  • Department of Plastic and Reconstructive Surgery, Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Taoyuan, Taiwan.
  • ELYSEE Aesthetics Medical Center, Taipei City, Taiwan. Electronic address: Firepigtw@gmail.com.

Zitieren

APA

Chen, K. Y., Tzeng, S. S., & Chen, H. C. (2024). Artificial intelligence-assisted grading for tear trough deformity. Journal of Plastic, Reconstructive & Aesthetic Surgery. https://doi.org/10.1016/j.bjps.2024.07.048

Vancouver

Chen KY, Tzeng SS, Chen HC. Artificial intelligence-assisted grading for tear trough deformity. Journal of Plastic, Reconstructive & Aesthetic Surgery. 2024. doi:10.1016/j.bjps.2024.07.048

BibTeX
@article{Chen2024,
  author = {Chen, Kevin Yu-Ting and Tzeng, Shin-Shi and Chen, Hung-Chang},
  title = {Artificial intelligence-assisted grading for tear trough deformity},
  journal = {Journal of Plastic, Reconstructive & Aesthetic Surgery},
  year = {2024},
  doi = {10.1016/j.bjps.2024.07.048}
}
Kostenlos starten →