J Clin Med. 2020 Feb 1;9(2). pii: E392. doi: 10.3390/jcm9020392.
Evaluation of Transfer Learning with Deep Convolutional Neural Networks for Screening Osteoporosis in Dental Panoramic Radiographs.
Lee KS1,2,3, Jung SK4, Ryu JJ5, Shin SW6,7, Choi J1,8.
Author information
1Department of Biomedical Engineering, College of Medicine, Seoul National University, Seoul 03080, Korea.
2Department of Clinical Dentistry, College of Medicine, Korea University, Seoul 02841, Korea.
3Department of Prosthodontics, Korea University An-san Hospital, Gyung-gi do 15355, Korea.
4Department of Orthodontics, Korea University Ansan Hospital, Gyung-gi do 15355, Korea.
5Department of Prosthodontics Korea University Anam Hospital, Seoul 02841, Korea.
6Department of Advanced Prosthodontics, Graduate School of Clinical Dentistry, Korea University, Seoul 02841, Korea.
7Institute of Clinical Dental Research, Korea University, Seoul 02841, Korea.
8Institute of Medical & Biological Engineering, Medical Research Center, Seoul 03080, Korea.
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.
KEYWORDS:
artificial intelligence; convolutional neural networks; dental panoramic radiographs; osteoporosis screening
PMID: 32024114 DOI: 10.3390/jcm9020392
