Automation of generative adversarial network-based synthetic data-augmentation for maximizing the diagnostic performance with paranasal imaging

Abstract

Thus far, there have been no reported specific rules for systematically determining the appropriate augmented sample size to optimize model performance when conducting data augmentation. In this paper, we report on the feasibility of synthetic data augmentation using generative adversarial networks (GAN) by proposing an automation pipeline to find the optimal multiple of data augmentation to achieve the best deep learning-based diagnostic performance in a limited dataset. We used Waters’ view radiographs for patients diagnosed with chronic sinusitis to demonstrate the method developed herein. We demonstrate that our approach produces significantly better diagnostic performance parameters than models trained using conventional data augmentation. The deep learning method proposed in this study could be implemented to assist radiologists in improving their diagnosis. Researchers and industry workers could overcome the lack of training data by employing our proposed automation pipeline approach in GAN-based synthetic data augmentation. This is anticipated to provide new means to overcome the shortage of graphic data for algorithm training.

Generative Adversarial Networks (GANs) in the Field of Head and Neck Surgery: Current Evidence and Prospects for the Future—A Systematic Review

“…Some studies are not limited in using only one type of imaging data. The study conducted by Kong et al, 2022 [ 26 ] exploits both CT and paranasal RX scans, the study conducted by Andlauer et al, 2021 [ 27 ] crosses both 2D images and postoperative 3D simulated images obtained from processing CT scans, and the study conducted by Chen et al [ 28 ] analyzes both CT and MRI scans.…”

“…The study conducted by Kong et al, 2022 [ 26 ] also demonstrated how GANs are an effective source of data that can be exploited to train artificial intelligence models to perform the job for which they were created. Through a particular type of GAN, synthetic data were generated to train a deep learning model created to diagnose the presence of sinus pathology by studying panoramic RX images and CT scans.…”

An interpretable framework to identify responsive subgroups from clinical trials regarding treatment effects: Application to treatment of intracerebral hemorrhage

“…Also, as discussed in another study that utilized the synthetic data augmentation procedures, the phenomenon is possibly caused by the model’s mode collapse issue. [ 39 ] Currently, no study discussed the synthetic method for downstream tasks of causal effects estimation, leaving us with an unanswered question of which characteristics of the synthetic data will affect the evaluation metrics for causal models. Further exploration is necessary to fully understand the nuances of synthetic data augmentation in the context of RCTs and answer causal questions.…”

Transfer Learning-Based Classification of Maxillary Sinus Using Generative Adversarial Networks

“…Most importantly, GANs also have an application in diagnosis of sinus-related conditions. For example, Kong et al [36] introduced a novel automation pipeline utilizing generative adversarial networks (GANs) for synthetic data augmentation, aiming to determine an optimal multiple for improving deep learning-based diagnostic performance with limited datasets. The study demonstrates superior diagnostic performance compared to conventional data augmentation using Waters' view radiographs of patients with chronic sinusitis.…”