How Good Are Synthetic Medical Images? An Empirical Study with Lung Ultrasound

TL;DR

This study evaluates the effectiveness of synthetic lung ultrasound images generated by generative models for training deep learning models, demonstrating that synthetic data can enhance performance and protect patient privacy.

Contribution

It introduces a comprehensive framework for using synthetic medical images in model training, including data augmentation, privacy protection, and new performance metrics.

Findings

Synthetic data improves model performance when combined with real data.

Models trained solely on synthetic data perform comparably to real data-trained models.

Adversarial methods can effectively protect patient privacy in medical imaging.

Abstract

Acquiring large quantities of data and annotations is known to be effective for developing high-performing deep learning models, but is difficult and expensive to do in the healthcare context. Adding synthetic training data using generative models offers a low-cost method to deal effectively with the data scarcity challenge, and can also address data imbalance and patient privacy issues. In this study, we propose a comprehensive framework that fits seamlessly into model development workflows for medical image analysis. We demonstrate, with datasets of varying size, (i) the benefits of generative models as a data augmentation method; (ii) how adversarial methods can protect patient privacy via data substitution; (iii) novel performance metrics for these use cases by testing models on real holdout data. We show that training with both synthetic and real data outperforms training with real data alone, and that models trained solely with synthetic data approach their real-only counterparts. Code is available at https://github.com/Global-Health-Labs/US-DCGAN.