EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Assessment of Deep Convolutional Neural Network Models for the Classification of Benign Fibro‐Osseous Lesions of the Jaws

Paniti Achararit iD, Chawan Manaspon iD, Chavin Jongwannasiri, Kraisorn Sappayatosok, Thanaphum Osathanon iD, Ekarat Phattarataratip

Clinical and Experimental Dental Research · 2025

DOI: 10.1002/cre2.70244 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinical and Experimental Dental Research, 2025. Verfasst von Paniti Achararit und 5 weiteren Autor:innen. Beteiligte Einrichtung: Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy, Bangkok, Thailand. Hauptthemen laut MEDLINE: Neural Networks, Computer, Fibroma, Ossifying, Fibrous Dysplasia of Bone, Jaw Neoplasms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This study was funded by the Faculty Research Grant (DRF66007), Faculty of Dentistry, Chulalongkorn University..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Benign fibro‐osseous lesions (BFOL) constitute a group of pathologic entities with marked overlapping histopathologic features but are diverse in nature and clinical behaviors. Accurate diagnoses of BFOLs necessitate clinical‐pathological correlations, which are paramount for their appropriate management. Recent research indicates the potential utility of artificial intelligence in diagnostic pathology. Here, we aimed to assess the performance of the deep convolutional neural network (DCNN) models for BFOL classification and investigate its impact on the diagnostic performance of oral pathologists. Material and Methods Microscopic slides from 68 patients diagnosed with cemento‐ossifying fibroma (COF), fibrous dysplasia (FD), and cemento‐osseous dysplasia (COD) were collected. The image patches from each slide were processed, augmented, and used to train and validate the five pre‐trained DCNN models for BFOL classification. The best‐performing model was selected to evaluate its diagnostic performance on the testing data set, compared with experienced oral pathologists.

Results

The InceptionV3 model showed the highest and most balanced overall performance in BFOL classification. It demonstrated the highest accuracy (96.7%) in classifying COF, followed by COD (83.3%), and FD (80.0%), respectively. The model accuracy in identifying COF was greater than the average performance of pathologists (90.0%). However, pathologists performed better in classifying COD (87.2%) and FD (95.0%). With DCNN assistance, pathologists significantly improved the accuracy, sensitivity, and specificity in distinguishing BFOLs while reducing the average diagnosis time.

Conclusions

The DCNN model has the potential to be developed as an auxiliary tool, assisting pathologists in diagnosing BFOLs. Through ongoing refinements, artificial intelligence assistance can aid pathologists in enhancing the accuracy and efficiency of BFOL diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerFibroma, OssifyingFibrous Dysplasia of BoneJaw NeoplasmsCementomaDeep LearningHumansMaleFemaleJawConvolutional Neural Networks

Stichwörter der Autor:innen

cemento‐osseous dysplasiacemento‐ossifying fibromaconvolutional neural networkdeep learningdiagnosisfibrous dysplasiafibro‐osseous lesions

Autor:innen und Institutionen

  • Princess Srisavangavadhana College of Medicine, Chulabhorn Royal Academy, Bangkok, Thailand.
  • Biomedical Engineering Institute, Chiang Mai University, Chiang Mai, Thailand.
  • College of Dental Medicine, Rangsit University, Pathum Thani, Thailand.
  • Center of Excellence for Dental Stem Cell Biology, Department of Anatomy, Faculty of Dentistry, Chulalongkorn University, Bangkok, Thailand.
  • Department of Oral Pathology, Faculty of Dentistry, Chulalongkorn University, Bangkok, Thailand.

ORCID-Profile: Paniti Achararit, Chawan Manaspon, Thanaphum Osathanon

Förderung

  • This study was funded by the Faculty Research Grant (DRF66007), Faculty of Dentistry, Chulalongkorn University.

Zitieren

APA

Achararit, P., Manaspon, C., Jongwannasiri, C., Sappayatosok, K., Osathanon, T., & Phattarataratip, E. (2025). Assessment of Deep Convolutional Neural Network Models for the Classification of Benign Fibro‐Osseous Lesions of the Jaws. Clinical and Experimental Dental Research. https://doi.org/10.1002/cre2.70244

Vancouver

Achararit P, Manaspon C, Jongwannasiri C, Sappayatosok K, Osathanon T, Phattarataratip E. Assessment of Deep Convolutional Neural Network Models for the Classification of Benign Fibro‐Osseous Lesions of the Jaws. Clinical and Experimental Dental Research. 2025. doi:10.1002/cre2.70244

BibTeX
@article{Achararit2025,
  author = {Achararit, Paniti and Manaspon, Chawan and Jongwannasiri, Chavin and Sappayatosok, Kraisorn and Osathanon, Thanaphum and Phattarataratip, Ekarat},
  title = {Assessment of Deep Convolutional Neural Network Models for the Classification of Benign Fibro‐Osseous Lesions of the Jaws},
  journal = {Clinical and Experimental Dental Research},
  year = {2025},
  doi = {10.1002/cre2.70244}
}
Kostenlos starten →