Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations

Abstract

Realistic image generation is valuable in dental medicine, but still challenging for generative adversarial networks (GANs), which require large amounts of data to overcome the training instability. Thus, we generated lateral cephalogram X-ray images using a deep-learning-based progressive growing GAN (PGGAN). The quality of generated images was evaluated by three methods. First, signal-to-noise ratios of real/synthesized images, evaluated at the posterior arch region of the first cervical vertebra, showed no statistically significant difference (t-test, p = 0.211). Second, the results of an image Turing test, conducted by non-orthodontists and orthodontists for 100 randomly chosen images, indicated that they had difficulty in distinguishing whether the image was real or synthesized. Third, cephalometric tracing with 42 landmark points detection, performed on real and synthesized images by two expert orthodontists, showed consistency with mean difference of 2.08 ± 1.02 mm. Furthermore, convolutional neural network-based classification tasks were used to classify skeletal patterns using a real dataset with class imbalance and a dataset balanced with synthesized images. The classification accuracy for the latter case was increased by 1.5%/3.3% at internal/external test sets, respectively. Thus, the cephalometric images generated by PGGAN are sufficiently realistic and have potential to application in various fields of dental medicine.

Cephalometric analysis performance discrepancy between orthodontists and an artificial intelligence model using lateral cephalometric radiographs

“…Therefore, cephalometric analysis is an indispensable tool for orthodontic diagnosis, treatment planning, evaluating growth changes, and assessing orthodontic treatment results 1 . However, the process of manually determining the cephalometric landmarks for a cephalometric analysis can be time‐consuming 1–4 . Nonetheless, manual landmark identification is still considered the gold standard for performing cephalometric analysis.…”

“…A cephalometric analysis consists of identifying anatomical skeletal, dental, and soft tissue landmarks from which planes, angles, or distances between them are measured providing important information for the orthodontic diagnosis and treatment plan elaboration 1,2 . Therefore, cephalometric analysis is an indispensable tool for orthodontic diagnosis, treatment planning, evaluating growth changes, and assessing orthodontic treatment results 1 . However, the process of manually determining the cephalometric landmarks for a cephalometric analysis can be time‐consuming 1–4 .…”

Evaluating the performance of generative adversarial network-synthesized periapical images in classifying C-shaped root canals

“…Previous research on GANs in dentistry has primarily concentrated on artifact reduction or super-resolution 22 – 28 , modality change 29 – 31 , or 3D prosthesis creation 32 – 39 . Although some studies have employed GANs for image generation in dentistry using intraoral photographs 40 or lateral cephalograms 41 , there have been no reported studies examining the potential of GANs for 2D radiographic imagery with limited datasets. Therefore, the aim of this study was to evaluate the quality of GAN-synthesized periapical images and evaluate the performance in diagnosing C-shaped canal anatomies.…”

A Self-attention Guided Multi-scale Gradient GAN for Diversified X-ray Image Synthesis

“…State-of-the-art GANs such as ProGAN [12], StyleGAN [13], and MSG-GAN [14] have been used for biomedical image synthesis. These GAN architectures have demonstrated significant performance in generating diverse images [15].…”