EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advancements in diagnosing oral potentially malignant disorders: leveraging Vision transformers for multi-class detection

Shankeeth Vinayahalingam, Niels van Nistelrooij, René Rothweiler, Alessandro Tel, Tim Verhoeven, Daniel Tröltzsch, Marco Kesting, Stefaan Bergé, Tong Xi, Max Heiland, Tabea Flügge

Clinical Oral Investigations · 08.06.2024 · 28 (7)

DOI: 10.1007/s00784-024-05762-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinical Oral Investigations, online erschienen am 08.06.2024. Verfasst von Shankeeth Vinayahalingam und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral and Maxillofacial Surgery, Radboud University Medical Centre, Nijmegen, the Netherlands. Hauptthemen laut MEDLINE: Mouth Neoplasms, Precancerous Conditions, Lichen Planus, Oral, Leukoplakia, Oral. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Charité - Universitätsmedizin Berlin.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Diagnosing oral potentially malignant disorders (OPMD) is critical to prevent oral cancer. This study aims to automatically detect and classify the most common pre-malignant oral lesions, such as leukoplakia and oral lichen planus (OLP), and distinguish them from oral squamous cell carcinomas (OSCC) and healthy oral mucosa on clinical photographs using vision transformers.

Methods

4,161 photographs of healthy mucosa, leukoplakia, OLP, and OSCC were included. Findings were annotated pixel-wise and reviewed by three clinicians. The photographs were divided into 3,337 for training and validation and 824 for testing. The training and validation images were further divided into five folds with stratification. A Mask R-CNN with a Swin Transformer was trained five times with cross-validation, and the held-out test split was used to evaluate the model performance. The precision, F1-score, sensitivity, specificity, and accuracy were calculated. The area under the receiver operating characteristics curve (AUC) and the confusion matrix of the most effective model were presented.

Results

The detection of OSCC with the employed model yielded an F1 of 0.852 and AUC of 0.974. The detection of OLP had an F1 of 0.825 and AUC of 0.948. For leukoplakia the F1 was 0.796 and the AUC was 0.938.

Conclusions

OSCC were effectively detected with the employed model, whereas the detection of OLP and leukoplakia was moderately effective. Clinical relevance Oral cancer is often detected in advanced stages. The demonstrated technology may support the detection and observation of OPMD to lower the disease burden and identify malignant oral cavity lesions earlier.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Mouth NeoplasmsPrecancerous ConditionsLichen Planus, OralLeukoplakia, OralHumansSensitivity and SpecificityPhotographyDiagnosis, DifferentialCarcinoma, Squamous CellMaleFemalePhotography, DentalImage Interpretation, Computer-Assisted

Stichwörter der Autor:innen

Artificial IntelligenceDeep learningLeukoplakiaMalignant transformationOral lichen planusOral squamous cell carcinoma

Autor:innen und Institutionen

  • Department of Oral and Maxillofacial Surgery, Radboud University Medical Centre, Nijmegen, the Netherlands.
  • Department of Artificial Intelligence, Radboud University, Nijmegen, the Netherlands.
  • Department of Oral and Maxillofacial Surgery, Universitätsklinikum Münster, Münster, Germany.
  • Department of Oral and Maxillofacial Surgery, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt- Universität zu Berlin, Hindenburgdamm 30, 12203, Berlin, Germany.
  • Department of Oral and Maxillofacial Surgery, Translational Implantology, Medical Center, Faculty of Medicine, University of Freiburg, University of Freiburg, Freiburg, Germany.
  • Clinic of Maxillofacial Surgery, Head&Neck and Neuroscience Department, University Hospital of Udine, Udine, Italy.

Förderung

  • Charité - Universitätsmedizin Berlin

Zitieren

APA

Vinayahalingam, S., van Nistelrooij, N., Rothweiler, R., Tel, A., Verhoeven, T., Tröltzsch, D., Kesting, M., Bergé, S., Xi, T., Heiland, M., & Flügge, T. (2024). Advancements in diagnosing oral potentially malignant disorders: leveraging Vision transformers for multi-class detection. Clinical Oral Investigations, 28(7). https://doi.org/10.1007/s00784-024-05762-8

Vancouver

Vinayahalingam S, van Nistelrooij N, Rothweiler R, Tel A, Verhoeven T, Tröltzsch D, et al. Advancements in diagnosing oral potentially malignant disorders: leveraging Vision transformers for multi-class detection. Clinical Oral Investigations. 2024;28(7). doi:10.1007/s00784-024-05762-8

BibTeX
@article{Vinayahalingam2024,
  author = {Vinayahalingam, Shankeeth and van Nistelrooij, Niels and Rothweiler, René and Tel, Alessandro and Verhoeven, Tim and Tröltzsch, Daniel and Kesting, Marco and Bergé, Stefaan and Xi, Tong and Heiland, Max and Flügge, Tabea},
  title = {Advancements in diagnosing oral potentially malignant disorders: leveraging Vision transformers for multi-class detection},
  journal = {Clinical Oral Investigations},
  year = {2024},
  volume = {28},
  number = {7},
  doi = {10.1007/s00784-024-05762-8}
}
Kostenlos starten →