Detection of periodontal bone loss and periodontitis from 2D dental radiographs via machine learning and deep learning: systematic review employing APPRAISE-AI and meta-analysis
Erkennung von parodontalem Knochenverlust und Parodontitis aus 2D-Zahnröntgenbildern mittels Machine Learning und Deep Learning: systematische Übersicht mit Metaanalyse
Dentomaxillofacial Radiology · 01.02.2025 · 54 (2) · 89-108
DOI: 10.1093/dmfr/twae070 ↗Auf einen Blick
Die Übersichtsarbeit zeigt: Deep-Learning-Modelle zur Beurteilung von alveolärem Knochenverlust auf Dentalröntgenbildern erzielten insgesamt gute Leistungswerte. Die Qualität der eingeschlossenen Arbeiten war überwiegend mittel.
Fragestellung
Wie gut erkennen KI-Modelle auf Panoramaschicht- und periapikalen Dentalröntgenbildern alveolären Knochenverlust und Parodontitis?
Methode
Systematische Übersicht; Suche in 5 Datenbanken von Januar 1990 bis Januar 2024; Qualitätsbewertung mit APPRAISE-AI; Metaanalyse mit metaprop in R V3.6.1.
Ergebnisse
30 Artikel wurden eingeschlossen, 10 für die Metaanalyse. Sensitivität 87 % (95 %-KI 80–93 %), Spezifität 76 % (95 %-KI 69–81 %), Genauigkeit 84 % (95 %-KI 75–91 %).
Einschränkungen
Die Leistung variierte zwischen den Modellen; Transparenz und Berichtsstandards der KI-Studien waren unzureichend.
Schlussfolgerung der Autor:innen
Deep Learning ist bei der Bewertung parodontaler Knochenlevel vielversprechend, mit Leistungsunterschieden zwischen den Modellen. Die Berichterstattung und Transparenz der KI-Studien sollten verbessert werden.
Kernaussagen
- 30 Artikel eingeschlossen, 10 in der Metaanalyse
- Sensitivität 87 % und Spezifität 76 %
- Qualität meist intermediär; keine Arbeit mit sehr hoher Qualität
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 05.12.2024. Verfasst von Yahia H Khubrani und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Dentistry, Cardiff University, The Annexe, University Dental Hospital, Heath Park, Cardiff CF14 4XY, United Kingdom. Hauptthemen laut MEDLINE: Alveolar Bone Loss, Deep Learning, Periodontitis, Machine Learning. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jazan University, Saudi Arabia Cultural Bureau.
Abstract (Originalsprache)
Objectives
Periodontitis is a serious periodontal infection that damages the soft tissues and bone around teeth and is linked to systemic conditions. Accurate diagnosis and staging, complemented by radiographic evaluation, are vital. This systematic review (PROSPERO ID: CRD42023480552) explores artificial intelligence (AI) applications in assessing alveolar bone loss and periodontitis on dental panoramic and periapical radiographs Methods Five databases (Medline, Embase, Scopus, Web of Science, and Cochrane’s Library) were searched from January 1990 to January 2024. Keywords related to “artificial intelligence”, “Periodontal bone loss/Periodontitis”, and “Dental radiographs” were used. Risk of bias and quality assessment of included papers were performed according to the APPRAISE-AI Tool for Quantitative Evaluation of AI Studies for Clinical Decision Support. Meta analysis was carried out via the “metaprop” command in R V3.6.1.
Results
Thirty articles were included in the review, where 10 papers were eligible for meta-analysis. Based on quality scores from the APPRAISE-AI critical appraisal tool of the 30 papers, 1 (3.3%) were of very low quality (score < 40), 3 (10.0%) were of low quality (40 ≤ score < 50), 19 (63.3%) were of intermediate quality (50 ≤ score < 60), and 7 (23.3%) were of high quality (60 ≤ score < 80). No papers were of very high quality (score ≥ 80). Meta-analysis indicated that model performance was generally good, eg, sensitivity 87% (95% CI, 80%-93%), specificity 76% (95% CI, 69%-81%), and accuracy 84% (95% CI, 75%-91%).
Conclusion
Deep learning shows much promise in evaluating periodontal bone levels, although there was some variation in performance. AI studies can lack transparency and reporting standards could be improved. Our systematic review critically assesses the application of deep learning models in detecting alveolar bone loss on dental radiographs using the APPRAISE-AI tool, highlighting their efficacy and identifying areas for improvement, thus advancing the practice of clinical radiology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Dentistry, Cardiff University, The Annexe, University Dental Hospital, Heath Park, Cardiff CF14 4XY, United Kingdom.
- School of Dentistry, Jazan University, Jazan 82817, Saudi Arabia.
- School of Computer Science and Informatics, Cardiff University, Cardiff CF24 4AG, United Kingdom.
- Cardiff University Brain Research Imaging Centre, School of Psychology, Cardiff University, Cardiff CF24 4HQ, United Kingdom.
- Department of Clinical Radiology, University Hospital of Wales, Cardiff CF14 4XW, United Kingdom.
ORCID-Profile: Yahia H Khubrani, David Thomas, Paddy J Slator, Richard D White, Damian J J Farnell
Förderung
- Jazan University
- Saudi Arabia Cultural Bureau
Zitieren
APA
Khubrani, Y. H., Thomas, D., Slator, P. J., White, R. D., & Farnell, D. J. J. (2025). Detection of periodontal bone loss and periodontitis from 2D dental radiographs via machine learning and deep learning: systematic review employing APPRAISE-AI and meta-analysis. Dentomaxillofacial Radiology, 54(2), 89-108. https://doi.org/10.1093/dmfr/twae070
Vancouver
Khubrani YH, Thomas D, Slator PJ, White RD, Farnell DJJ. Detection of periodontal bone loss and periodontitis from 2D dental radiographs via machine learning and deep learning: systematic review employing APPRAISE-AI and meta-analysis. Dentomaxillofacial Radiology. 2025;54(2):89-108. doi:10.1093/dmfr/twae070
BibTeX
@article{Khubrani2025,
author = {Khubrani, Yahia H and Thomas, David and Slator, Paddy J and White, Richard D and Farnell, Damian J J},
title = {Detection of periodontal bone loss and periodontitis from 2D dental radiographs via machine learning and deep learning: systematic review employing APPRAISE-AI and meta-analysis},
journal = {Dentomaxillofacial Radiology},
year = {2025},
volume = {54},
number = {2},
pages = {89--108},
doi = {10.1093/dmfr/twae070}
}
EUVIMED