Evaluation of Transfer Learning with Deep Convolutional Neural Networks for Screening Osteoporosis in Dental Panoramic Radiographs

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.

Deep Convolutional Neural Networks Based Analysis of Cephalometric Radiographs for Differential Diagnosis of Orthognathic Surgery Indications

“…In this study, Grad-CAM was used to determine whether the deep learning AI model considered and evaluated the correct region. Grad-CAM is a generalized version of CAM that can be applied to AI models without global average pooling [29,30]. The highlighted CAM gives us insight into what it is seeing and evaluating why it failed.…”

“…We also used the gradient-weighted class activation mapping (Grad-CAM) technique to see where the AI was interested [29,30]. By expressing difference in color, it was possible to know which area received the greatest judgment by the AI model.…”

Deep Neural Networks for Dental Implant System Classification

“…In transfer learning, an existing learned model is used as a feature extractor without changing the weight data, while in fine tuning, an existing learned model is used as a feature extractor by relearning some of the weight data. These methods are powerful methods for training deep CNNs without overfitting, even when the target dataset is smaller than the base dataset [20].…”

Comprehensive Serum Glycopeptide Spectra Analysis Combined with Artificial Intelligence (CSGSA-AI) to Diagnose Early-Stage Ovarian Cancer

“…Oh et al [25] used CNN to learn 695 brain images of Alzheimer's disease patients acquired by magnetic resonance imaging (MRI) to distinguish it from normal brain and achieved 87% accuracy. Since preparing a large number of clinical specimens is difficult, this transfer learning technology is meaningful to accelerate clinical studies using AI [28]. Moreover, since the development of CNN is outstanding among general deep learning technologies, some scientists have attempted to convert numerical (non-image) data into images and let CNN learn the images.…”