Comparison of five convolutional neural networks for predicting osteoporosis based on mandibular cortical index on panoramic radiographs

dc.authorscopusid 57194135354
dc.authorscopusid 56246508200
dc.authorscopusid 57867839600
dc.contributor.author Tassoker,M.
dc.contributor.author Öziç,M.Ü.
dc.contributor.author Yuce,F.
dc.date.accessioned 2024-05-25T12:34:27Z
dc.date.available 2024-05-25T12:34:27Z
dc.date.issued 2022
dc.department Okan University en_US
dc.department-temp Tassoker M., Department of Oral and Maxillofacial Radiology, Necmettin Erbakan University Faculty of Dentistry, Konya, Turkey; Öziç M.Ü., Department of Biomedical Engineering, Pamukkale University, Faculty of Technology, Denizli, Turkey; Yuce F., Department of Oral and Maxillofacial Radiology, Okan University, Istanbul, Turkey en_US
dc.description.abstract Objectives: The aim of the present study was to compare five convolutional neural networks for predicting osteoporosis based on mandibular cortical index (MCI) on panoramic radiographs. Methods: Panoramic radiographs of 744 female patients over 50 years of age were labeled as C1, C2, and C3 depending on the MCI. The data of the present study were reviewed in different categories including (C1, C2, C3), (C1, C2), (C1, C3), and (C1, (C2 +C3)) as two-class and three-class predictions. The data were separated randomly as 20% test data, and the remaining data were used for training and validation with fivefold cross-validation. AlexNET, GoogleNET, ResNET-50, SqueezeNET, and ShuffleNET deep-learning models were trained through the transfer learning method. The results were evaluated by performance criteria including accuracy, sensitivity, specificity, F1-score, AUC, and training duration. The Gradient-Weighted Class Activation Mapping (Grad-CAM) method was applied for visual interpretation of where deep-learning algorithms gather the feature from image regions. Results: The dataset (C1, C2, C3) has an accuracy rate of 81.14% with AlexNET; the dataset (C1, C2) has an accuracy rate of 88.94% with GoogleNET; the dataset (C1, C3) has an accuracy rate of 98.56% with AlexNET; and the dataset (C1,(C2+C3)) has an accuracy rate of 92.79% with GoogleNET. Conclusion: The highest accuracy was obtained in the differentiation of C3 and C1 where osseous structure characteristics change significantly. Since the C2 score represent the intermediate stage (osteopenia), structural characteristics of the bone present behaviors closer to C1 and C3 scores. Therefore, the data set including the C2 score provided relatively lower accuracy results. Dentomaxillofacial Radiology (2022) 51, 20220108. doi: 10.1259/dmfr.20220108 © 2022 The Authors. Published by the British Institute of Radiology. en_US
dc.identifier.citationcount 14
dc.identifier.doi 10.1259/DMFR.20220108
dc.identifier.issn 0250-832X
dc.identifier.issue 6 en_US
dc.identifier.pmid PubMed:35762349
dc.identifier.scopus 2-s2.0-85137009015
dc.identifier.scopusquality Q1
dc.identifier.uri https://doi.org/10.1259/DMFR.20220108
dc.identifier.uri https://hdl.handle.net/20.500.14517/2584
dc.identifier.volume 51 en_US
dc.identifier.wosquality Q2
dc.language.iso en
dc.publisher British Institute of Radiology en_US
dc.relation.ispartof Dentomaxillofacial Radiology en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.scopus.citedbyCount 17
dc.subject Artificial intelligence en_US
dc.subject Deep Learning en_US
dc.subject Osteoporosis en_US
dc.subject Panoramic Radiography en_US
dc.title Comparison of five convolutional neural networks for predicting osteoporosis based on mandibular cortical index on panoramic radiographs en_US
dc.type Article en_US

Files