How Good Are Synthetic Medical Images? An Empirical Study with Lung Ultrasound
This work addresses data scarcity, imbalance, and privacy issues in healthcare AI, offering a practical solution for medical image analysis, though it is incremental in applying existing generative methods to this domain.
The study tackled the challenge of data scarcity in medical image analysis by proposing a framework that integrates synthetic images from generative models into training workflows, showing that combining synthetic and real data outperforms using real data alone and that models trained only on synthetic data approach the performance of those trained on real data.
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.