From Diagnosis to Decision‐Making: AI‐Driven Triage of Oral Mucosal Lesions Detected on Intraoral Photographs
Julia Schwärzler,
Ekaterina Tolstaya,
Antonin Tichy,
Tami Yap,
Michael McCullough,
Yoana Malenova,
David Steybe,
Sven Otto,
Sebastian Paris,
Falk Schwendicke Australian Dental Journal
· Wiley
· 2026-10-16
· DOI: 10.1111/adj.70079
Аннотация
ABSTRACT Background Managing oral mucosal lesions in general dental practice is challenging, as visually similar conditions may require very different treatments. We developed an AI‐based triage system connecting intraoral image analysis with guideline‐based treatment recommendations, tested it externally, and compared its performance with clinicians' recommendations. Methods YOLOv8 and YOLOv11 were trained on 4079 intraoral photographs to classify 11 oral mucosal lesion types. These were mapped into five treatment tiers defined by urgency and management aim: T1 specialist referral for malignant and high‐risk lesions, T2 interdisciplinary referral for specialist‐led non‐cancer management, T3 risk‐adapted surveillance, T4 dental treatment with reassessment, and T5 no treatment. Model performance was compared with two general dentists and four specialists on an internal test set. YOLOv11 was additionally tested on an external dataset. Results YOLOv11 outperformed YOLOv8 in macro‐averaged precision, recall, and F1 score, achieving 0.72, 0.74, and 0.73 respectively. However, 25% of T1 high‐risk cases were under‐triaged. YOLOv11 significantly outperformed all clinicians, whose F1 scores ranged from 0.33 to 0.69. External performance decreased markedly (F1 score: 0.58), consistent with domain shift. Conclusion Guideline‐oriented AI triage is feasible but requires multicentre training for improved generalizability, as well as safety‐focused optimization, and prospective user evaluation before clinical use.
Julia Schwärzler, Ekaterina Tolstaya, Antonin Tichy, Tami Yap, Michael McCullough, Yoana Malenova et al. From Diagnosis to Decision‐Making: AI‐Driven Triage of Oral Mucosal Lesions Detected on Intraoral Photographs. // Australian Dental Journal. – 2026. – DOI: 10.1111/adj.70079. – URL: https://onlinelibrary.wiley.com/doi/10.1111/adj.70079?af=R
Julia Schwärzler, Ekaterina Tolstaya, Antonin Tichy, Tami Yap, Michael McCullough, Yoana Malenova, David Steybe, Sven Otto, Sebastian Paris, & Falk Schwendicke (2026). From Diagnosis to Decision‐Making: AI‐Driven Triage of Oral Mucosal Lesions Detected on Intraoral Photographs. Australian Dental Journal. https://doi.org/10.1111/adj.70079
Julia Schwärzler, et al. “From Diagnosis to Decision‐Making: AI‐Driven Triage of Oral Mucosal Lesions Detected on Intraoral Photographs.” Australian Dental Journal, 2026. doi:10.1111/adj.70079.
@article{Schwrzler2026,
title = {From Diagnosis to Decision‐Making: AI‐Driven Triage of Oral Mucosal Lesions Detected on Intraoral Photographs},
author = {Schwärzler, Julia and Tolstaya, Ekaterina and Tichy, Antonin and Yap, Tami and McCullough, Michael and Malenova, Yoana and Steybe, David and Otto, Sven and Paris, Sebastian and Schwendicke, Falk},
journal = {Australian Dental Journal},
year = {2026},
doi = {10.1111/adj.70079},
url = {https://onlinelibrary.wiley.com/doi/10.1111/adj.70079?af=R}
}
Abstract The rotational path removable partial denture (RPRPD) design is a viable treatment approach for the esthetic and functional rehabilitation of Kennedy's Classification III and IV partially edentulous patients. The purpose of...
BDJ Open, Published online: 19 November 2026; doi:10.1038/s41405-026-00443-y Design and validation of a questionnaire to measure the knowledge and performance of dentists regarding dental considerations in patients receiving bisphosphonate
ABSTRACT Background Temporomandibular joint osteoarthritis (TMJOA) is characterized by progressive cartilage degeneration and inflammatory catabolism, but the mechanisms linking inflammatory stress to extracellular signalling remain...