Fully Automated Detection of Osteoporosis Stage on Panoramic Radiographs Using YOLOv5 Deep Learning Model and Designing a Graphical User Interface

Basit Öğe Kaydı
dc.contributor.authorOzic, Muhammet Usame
dc.contributor.authorTassoker, Melek
dc.contributor.authorYuce, Fatma
dc.date.accessioned2024-02-23T14:00:11Z
dc.date.available2024-02-23T14:00:11Z
dc.date.issued2023
dc.departmentNEÜen_US
dc.description.abstractPurposeOsteoporosis is a systemic disease that causes fracture risk and bone fragility due to decreased bone mineral density and deterioration of bone microarchitecture. Deep learning-based image analysis technologies have effectively been used as a decision support system in diagnosing disease. This study proposes a deep learning-based approach that automatically performs osteoporosis localization and stage estimation on panoramic radiographs with different contrasts.MethodsEight hundred forty-six panoramic radiographs were collected from the hospital database and pre-processed. Two radiologists annotated the images according to the Mandibular Cortical Index, considering the cortical region extending from the distal to the antegonial area of the foramen mentale. The data were trained and validated using the YOLOv5 deep learning algorithm in the Linux-based COLAB Pro cloud environment. The Weights and Bias platform was integrated into COLAB, and the training process was monitored instantly. Using the model weights obtained, the test data that the system had not seen before were analyzed. Using the non-maximum suppression technique on the test data, the bounding boxes of the regions that could be osteoporosis were automatically drawn. Finally, a graphical user interface was developed with the PyQT5 library.ResultsTwo radiologists analyzed the data, and the performance criteria were calculated. The performance criteria of the test data were obtained as follows: an average precision of 0.994, a recall of 0.993, an F1-score of 0.993, and an inference time of 14.3 ms (0.0143 s).ConclusionThe proposed method showed that deep learning could successfully perform automatic localization and staging of osteoporosis on panoramic radiographs without region-of-interest cropping and complex pre-processing methods.en_US
dc.description.sponsorshipThis study was presented as an abstract at the 26th Turkish Dental Association International Dentistry Congress (TDB) in Istanbul, Turkey, from September 8 to 11, 2022.en_US
dc.description.sponsorshipThis study was presented as an abstract at the 26th Turkish Dental Association International Dentistry Congress (TDB) in Istanbul, Turkey, from September 8 to 11, 2022.en_US
dc.identifier.doi10.1007/s40846-023-00831-x
dc.identifier.endpage731en_US
dc.identifier.issn1609-0985
dc.identifier.issn2199-4757
dc.identifier.issue6en_US
dc.identifier.scopus2-s2.0-85174923301en_US
dc.identifier.scopusqualityQ3en_US
dc.identifier.startpage715en_US
dc.identifier.urihttps://doi.org/10.1007/s40846-023-00831-x
dc.identifier.urihttps://hdl.handle.net/20.500.12452/11492
dc.identifier.volume43en_US
dc.identifier.wosWOS:001090747600002en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Heidelbergen_US
dc.relation.ispartofJournal Of Medical And Biological Engineeringen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAutomatic Detectionen_US
dc.subjectDeep Learningen_US
dc.subjectOsteoporosisen_US
dc.subjectPanoramic Radiographsen_US
dc.subjectYolov5en_US
dc.titleFully Automated Detection of Osteoporosis Stage on Panoramic Radiographs Using YOLOv5 Deep Learning Model and Designing a Graphical User Interfaceen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu