Evaluation of Transfer Learning with Deep Convolutional Neural Networks for Screening Osteoporosis in Dental Panoramic Radiographs
- Authors
- Lee, Ki-Sun; Jung, Seok-Ki; Ryu, Jae Jun; Shin, Sang Wan; Choi, Jinwook
- Issue Date
- Feb-2020
- Publisher
- MDPI
- Keywords
- osteoporosis screening; artificial intelligence; convolutional neural networks; dental panoramic radiographs
- Citation
- Journal of Clinical Medicine, v.9, no.2
- Indexed
- SCIE
SCOPUS
- Journal Title
- Journal of Clinical Medicine
- Volume
- 9
- Number
- 2
- URI
- https://scholarworks.korea.ac.kr/kumedicine/handle/2020.sw.kumedicine/1076
- DOI
- 10.3390/jcm9020392
- ISSN
- 2077-0383
2077-0383
- Abstract
- Dental panoramic radiographs (DPRs) provide information required to potentially evaluate bone density changes through a textural and morphological feature analysis on a mandible. This study aims to evaluate the discriminating performance of deep convolutional neural networks (CNNs), employed with various transfer learning strategies, on the classification of specific features of osteoporosis in DPRs. For objective labeling, we collected a dataset containing 680 images from different patients who underwent both skeletal bone mineral density and digital panoramic radiographic examinations at the Korea University Ansan Hospital between 2009 and 2018. Four study groups were used to evaluate the impact of various transfer learning strategies on deep CNN models as follows: a basic CNN model with three convolutional layers (CNN3), visual geometry group deep CNN model (VGG-16), transfer learning model from VGG-16 (VGG-16_TF), and fine-tuning with the transfer learning model (VGG-16_TF_FT). The best performing model achieved an overall area under the receiver operating characteristic of 0.858. In this study, transfer learning and fine-tuning improved the performance of a deep CNN for screening osteoporosis in DPR images. In addition, using the gradient-weighted class activation mapping technique, a visual interpretation of the best performing deep CNN model indicated that the model relied on image features in the lower left and right border of the mandibular. This result suggests that deep learning-based assessment of DPR images could be useful and reliable in the automated screening of osteoporosis patients.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 2. Clinical Science > Department of Dentistry > 1. Journal Articles
- 2. Clinical Science > Department of Orthodontics > 1. Journal Articles
- 2. Clinical Science > Department of Prosthodontics > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.