EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Automatic deep learning detection of overhanging restorations in bitewing radiographs

Guldane Magat iD, Ali Altındag, Fatma Pertek Hatipoglu, Omer Hatipoglu, İbrahim Sevki Bayrakdar, Ozer Celik, Kaan Orhan iD

Dentomaxillofacial Radiology · 01.10.2024 · 53 (7) · 468-477

DOI: 10.1093/dmfr/twae036 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 18.07.2024. Verfasst von Guldane Magat und 6 weiteren Autor:innen. Beteiligte Einrichtung: Necmettin Erbakan University Dentistry Faculty, Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Necmettin Erbakan University, K…. Hauptthemen laut MEDLINE: Deep Learning, Dental Restoration, Permanent, Radiography, Bitewing. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

This study aimed to assess the effectiveness of deep convolutional neural network (CNN) algorithms for the detecting and segmentation of overhanging dental restorations in bitewing radiographs.

Methods

A total of 1160 anonymized bitewing radiographs were used to progress the artificial intelligence (AI) system for the detection and segmentation of overhanging restorations. The data were then divided into three groups: 80% for training (930 images, 2399 labels), 10% for validation (115 images, 273 labels), and 10% for testing (115 images, 306 labels). A CNN model known as You Only Look Once (YOLOv5) was trained to detect overhanging restorations in bitewing radiographs. After utilizing the remaining 115 radiographs to evaluate the efficacy of the proposed CNN model, the accuracy, sensitivity, precision, F1 score, and area under the receiver operating characteristic curve (AUC) were computed.

Results

The model demonstrated a precision of 90.9%, a sensitivity of 85.3%, and an F1 score of 88.0%. Furthermore, the model achieved an AUC of 0.859 on the receiver operating characteristic (ROC) curve. The mean average precision (mAP) at an intersection over a union (IoU) threshold of 0.5 was notably high at 0.87.

Conclusions

The findings suggest that deep CNN algorithms are highly effective in the detection and diagnosis of overhanging dental restorations in bitewing radiographs. The high levels of precision, sensitivity, and F1 score, along with the significant AUC and mAP values, underscore the potential of these advanced deep learning techniques in revolutionizing dental diagnostic procedures.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningDental Restoration, PermanentRadiography, BitewingHumansAlgorithmsNeural Networks, ComputerSensitivity and Specificity

Stichwörter der Autor:innen

artificial intelligencebitewingdeep learningoverhanging restoration

Autor:innen und Institutionen

  • Necmettin Erbakan University Dentistry Faculty, Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Necmettin Erbakan University, Konya, Meram, Turkey, 42090, Turkey.
  • Department of Endodontics, Nigde Omer Halisdemir University, Nigde, 51240, Turkey.
  • Department of Restorative Dentistry, Nigde Omer Halisdemir University, Nigde, 51240, Turkey.
  • Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University, Eskisehir, 26040, Turkey.
  • Department of Mathematics-Computer, Eskisehir Osmangazi University Faculty of Science, Eskisehir, 26040, Turkey.
  • CranioCatch Company, Eskisehir, 26040, Turkey.

ORCID-Profile: Guldane Magat, Kaan Orhan

Zitieren

APA

Magat, G., Altındag, A., Pertek Hatipoglu, F., Hatipoglu, O., Bayrakdar, İ. S., Celik, O., & Orhan, K. (2024). Automatic deep learning detection of overhanging restorations in bitewing radiographs. Dentomaxillofacial Radiology, 53(7), 468-477. https://doi.org/10.1093/dmfr/twae036

Vancouver

Magat G, Altındag A, Pertek Hatipoglu F, Hatipoglu O, Bayrakdar İS, Celik O, et al. Automatic deep learning detection of overhanging restorations in bitewing radiographs. Dentomaxillofacial Radiology. 2024;53(7):468-477. doi:10.1093/dmfr/twae036

BibTeX
@article{Magat2024,
  author = {Magat, Guldane and Altındag, Ali and Pertek Hatipoglu, Fatma and Hatipoglu, Omer and Bayrakdar, İbrahim Sevki and Celik, Ozer and Orhan, Kaan},
  title = {Automatic deep learning detection of overhanging restorations in bitewing radiographs},
  journal = {Dentomaxillofacial Radiology},
  year = {2024},
  volume = {53},
  number = {7},
  pages = {468--477},
  doi = {10.1093/dmfr/twae036}
}
Kostenlos starten →