Performance evaluation of a deep learning model for automatic detection and localization of idiopathic osteosclerosis on dental panoramic radiographs

dc.authorscopusid 57194135354
dc.authorscopusid 56246508200
dc.authorscopusid 57867839600
dc.contributor.author Tassoker, Melek
dc.contributor.author Ozic, Muhammet Usame
dc.contributor.author Yuce, Fatma
dc.date.accessioned 2024-05-25T11:37:40Z
dc.date.available 2024-05-25T11:37:40Z
dc.date.issued 2024
dc.department Okan University en_US
dc.department-temp [Tassoker, Melek] Necmettin Erbakan Univ, Fac Dent, Dept Oral & Maxillofacial Radiol, Baglarbasi St, TR-42090 Meram, Konya, Turkiye; [Ozic, Muhammet Usame] Pamukkale Univ, Fac Technol, Dept Biomed Engn, Denizli, Turkiye; [Yuce, Fatma] Istanbul Okan Univ, Fac Dent, Dept Oral & Maxillofacial Radiol, Istanbul, Turkiye en_US
dc.description.abstract Idiopathic osteosclerosis (IO) are focal radiopacities of unknown etiology observed in the jaws. These radiopacities are incidentally detected on dental panoramic radiographs taken for other reasons. In this study, we investigated the performance of a deep learning model in detecting IO using a small dataset of dental panoramic radiographs with varying contrasts and features. Two radiologists collected 175 IO-diagnosed dental panoramic radiographs from the dental school database. The dataset size is limited due to the rarity of IO, with its incidence in the Turkish population reported as 2.7% in studies. To overcome this limitation, data augmentation was performed by horizontally flipping the images, resulting in an augmented dataset of 350 panoramic radiographs. The images were annotated by two radiologists and divided into approximately 70% for training (245 radiographs), 15% for validation (53 radiographs), and 15% for testing (52 radiographs). The study employing the YOLOv5 deep learning model evaluated the results using precision, recall, F1-score, mAP (mean Average Precision), and average inference time score metrics. The training and testing processes were conducted on the Google Colab Pro virtual machine. The test process's performance criteria were obtained with a precision value of 0.981, a recall value of 0.929, an F1-score value of 0.954, and an average inference time of 25.4 ms. Although radiographs diagnosed with IO have a small dataset and exhibit different contrasts and features, it has been observed that the deep learning model provides high detection speed, accuracy, and localization results. The automatic identification of IO lesions using artificial intelligence algorithms, with high success rates, can contribute to the clinical workflow of dentists by preventing unnecessary biopsy procedure. en_US
dc.identifier.citationcount 0
dc.identifier.doi 10.1038/s41598-024-55109-2
dc.identifier.issn 2045-2322
dc.identifier.issue 1 en_US
dc.identifier.pmid 38396289
dc.identifier.scopus 2-s2.0-85185696707
dc.identifier.scopusquality Q1
dc.identifier.uri https://doi.org/10.1038/s41598-024-55109-2
dc.identifier.uri https://hdl.handle.net/20.500.14517/1205
dc.identifier.volume 14 en_US
dc.identifier.wos WOS:001176953400016
dc.identifier.wosquality Q2
dc.language.iso en
dc.publisher Nature Portfolio 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 3
dc.subject Deep learning en_US
dc.subject Dense bone island en_US
dc.subject Idiopathic osteosclerosis en_US
dc.subject Panoramic radiography en_US
dc.subject YOLOv5 en_US
dc.title Performance evaluation of a deep learning model for automatic detection and localization of idiopathic osteosclerosis on dental panoramic radiographs en_US
dc.type Article en_US
dc.wos.citedbyCount 1

Files