Training medical AI algorithms requires large volumes of accurately labeled datasets, which are difficult to obtain in the real world. Synthetic images generated from deep generative models can help alleviate the data scarcity problem, but their effectiveness relies on their fidelity to real-world images. Typically, researchers select synthesis models based on image quality measurements, prioritizing synthetic images that appear realistic. However, our empirical analysis shows that high-fidelity and visually appealing synthetic images are not necessarily superior. In fact, we present a case where low-fidelity synthetic images outperformed their high-fidelity counterparts in downstream tasks. Our findings highlight the importance of comprehensive analysis before incorporating synthetic data into real-world applications. We hope our results will raise awareness among the research community of the value of low-fidelity synthetic images in medical AI algorithm training.
View on arXiv