Machine learning for automated identification of anatomical landmarks in ultrasound periodontal imaging
Dentomaxillofacial Radiology · 2025
DOI: 10.1093/dmfr/twaf001 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, 2025. Verfasst von Baiyan Qi und 7 weiteren Autor:innen. Beteiligte Einrichtung: Aiiso Yufeng Li Family Department of Chemical and Nano Engineering, University of California San Diego, La Jolla, CA 92093, United States. Hauptthemen laut MEDLINE: Machine Learning, Anatomic Landmarks, Gingival Recession. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDCR NIH HHS, NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Objectives
To identify landmarks in ultrasound periodontal images and automate the image-based measurements of gingival recession (iGR), gingival height (iGH), and alveolar bone level (iABL) using machine learning.
Methods
We imaged 184 teeth from 29 human subjects. The dataset included 1580 frames for training and validating the U-Net convolutional neural network machine learning model, and 250 frames from new teeth that were not used in training for testing the generalization performance. The predicted landmarks, including the tooth, gingiva, bone, gingival margin (GM), cementoenamel junction (CEJ), and alveolar bone crest (ABC), were compared to manual annotations. We further demonstrated automated measurements of the clinical metrics iGR, iGH, and iABL.
Results
Over 98% of predicted GM, CEJ, and ABC distances are within 200 µm of the manual annotation. Bland-Altman analysis revealed biases (bias of machine learning vs ground truth) of −0.1 µm, −37.6 µm, and −40.9 µm, with 95% limits of agreement of [−281.3, 281.0] µm, [−203.1, 127.9] µm, and [−297.6, 215.8] µm for iGR, iGH, and iABL, respectively, when compared to manual annotations. On the test dataset, the biases were 167.5 µm, 40.1 µm, and 78.7 µm with 95% CIs of [−1175 to 1510] µm, [−910.3 to 990.4] µm, and [−1954 to 1796] µm for iGR, iGH, and iABL, respectively.
Conclusions
The proposed machine learning model demonstrates robust prediction performance, with the potential to enhance the efficiency of clinical periodontal diagnosis by automating landmark identification and clinical metrics measurements.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Aiiso Yufeng Li Family Department of Chemical and Nano Engineering, University of California San Diego, La Jolla, CA 92093, United States.
- Herman Ostrow School of Dentistry, University of Southern California, Los Angeles, CA 90089, United States.
- Shu Chien-Gene Lay Department of Bioengineering, University of California San Diego, La Jolla, CA 92093, United States.
- Material Science and Engineering Program, University of California San Diego, La Jolla, CA 92093, United States.
- Department of Radiology, University of California San Diego, La Jolla, CA 92093, United States.
ORCID-Profile: Jesse V Jokerst
Förderung
- NIDCR NIH HHS
- NIH HHS
- National Institutes of Health
Zitieren
APA
Qi, B., Sasi, L., Khan, S., Luo, J., Chen, C., Rahmani, K., Jahed, Z., & Jokerst, J. V. (2025). Machine learning for automated identification of anatomical landmarks in ultrasound periodontal imaging. Dentomaxillofacial Radiology. https://doi.org/10.1093/dmfr/twaf001
Vancouver
Qi B, Sasi L, Khan S, Luo J, Chen C, Rahmani K, et al. Machine learning for automated identification of anatomical landmarks in ultrasound periodontal imaging. Dentomaxillofacial Radiology. 2025. doi:10.1093/dmfr/twaf001
BibTeX
@article{Qi2025,
author = {Qi, Baiyan and Sasi, Lekshmi and Khan, Suhel and Luo, Jordan and Chen, Casey and Rahmani, Keivan and Jahed, Zeinab and Jokerst, Jesse V},
title = {Machine learning for automated identification of anatomical landmarks in ultrasound periodontal imaging},
journal = {Dentomaxillofacial Radiology},
year = {2025},
doi = {10.1093/dmfr/twaf001}
}
EUVIMED