Comparison of deep learning methods for the radiographic detection of patients with different periodontitis stages
Dentomaxillofacial Radiology · 2024
DOI: 10.1093/dmfr/twad003 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, 2024. Verfasst von Berceste Guler Ayyildiz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Dentistry, Department of Periodontology, Kutahya Health Sciences University, Kutahya, 43100, Turkey. Hauptthemen laut MEDLINE: Deep Learning, Alveolar Bone Loss. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Objectives
The objective of this study is to assess the accuracy of computer-assisted periodontal classification bone loss staging using deep learning (DL) methods on panoramic radiographs and to compare the performance of various models and layers.
Methods
Panoramic radiographs were diagnosed and classified into 3 groups, namely “healthy,” “Stage1/2,” and “Stage3/4,” and stored in separate folders. The feature extraction stage involved transferring and retraining the feature extraction layers and weights from 3 models, namely ResNet50, DenseNet121, and InceptionV3, which were proposed for classifying the ImageNet dataset, to 3 DL models designed for classifying periodontal bone loss. The features obtained from global average pooling (GAP), global max pooling (GMP), or flatten layers (FL) of convolutional neural network (CNN) models were used as input to the 8 different machine learning (ML) models. In addition, the features obtained from the GAP, GMP, or FL of the DL models were reduced using the minimum redundancy maximum relevance (mRMR) method and then classified again with 8 ML models.
Results
A total of 2533 panoramic radiographs, including 721 in the healthy group, 842 in the Stage1/2 group, and 970 in the Stage3/4 group, were included in the dataset. The average performance values of DenseNet121 + GAP-based and DenseNet121 + GAP + mRMR-based ML techniques on 10 subdatasets and ML models developed using 2 feature selection techniques outperformed CNN models.
Conclusions
The new DenseNet121 + GAP + mRMR-based support vector machine model developed in this study achieved higher performance in periodontal bone loss classification compared to other models in the literature by detecting effective features from raw images without the need for manual selection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Dentistry, Department of Periodontology, Kutahya Health Sciences University, Kutahya, 43100, Turkey.
- Faculty of Technology, Department of Software Engineering, Sivas Cumhuriyet University, Sivas, 58140, Turkey.
- Tavsanlõ Vocational School, Oral Health Department, Kutahya Health Sciences University, Kütahya, 43410, Turkey.
- Faculty of Engineering, Department of Computer Engineering, Kutahya Dumlupinar University, Kutahya, 43020, Turkey.
ORCID-Profile: Berceste Guler Ayyildiz, Busra Terzioglu
Zitieren
APA
Guler Ayyildiz, B., Karakis, R., Terzioglu, B., & Ozdemir, D. (2024). Comparison of deep learning methods for the radiographic detection of patients with different periodontitis stages. Dentomaxillofacial Radiology. https://doi.org/10.1093/dmfr/twad003
Vancouver
Guler Ayyildiz B, Karakis R, Terzioglu B, Ozdemir D. Comparison of deep learning methods for the radiographic detection of patients with different periodontitis stages. Dentomaxillofacial Radiology. 2024. doi:10.1093/dmfr/twad003
BibTeX
@article{GulerAyyildiz2024,
author = {Guler Ayyildiz, Berceste and Karakis, Rukiye and Terzioglu, Busra and Ozdemir, Durmus},
title = {Comparison of deep learning methods for the radiographic detection of patients with different periodontitis stages},
journal = {Dentomaxillofacial Radiology},
year = {2024},
doi = {10.1093/dmfr/twad003}
}
EUVIMED