Please use this identifier to cite or link to this item:
https://hdl.handle.net/11499/54857
Title: | Fully Automated Detection of Osteoporosis Stage on Panoramic Radiographs Using YOLOv5 Deep Learning Model and Designing a Graphical User Interface | Authors: | Öziç, M.Ü. Tassoker, M. Yuce, F. |
Keywords: | Automatic detection Deep learning Osteoporosis Panoramic radiographs YOLOv5 Computer operating systems Decision support systems Deep learning Deterioration Diagnosis Diseases Image segmentation Learning algorithms Learning systems Automated detection Automatic Detection Deep learning Fully automated Learning models Osteoporosis Panoramic radiograph Performance criterion Test data YOLOv5 Graphical user interfaces |
Publisher: | Springer Science and Business Media Deutschland GmbH | Abstract: | Purpose: Osteoporosis 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. Methods: Eight 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. Results: Two 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). Conclusion: The 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. © 2023, Taiwanese Society of Biomedical Engineering. | URI: | https://doi.org/10.1007/s40846-023-00831-x https://hdl.handle.net/11499/54857 |
ISSN: | 1609-0985 |
Appears in Collections: | Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection Teknoloji Fakültesi Koleksiyonu WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection |
Show full item record
CORE Recommender
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.