TSynD Targeted Synthetic Data Generation for Enhanced Medical Image Classification

Abstract

Deep learning in medical applications usually faces the problem of limited training data that does not represent most of the relevant distribution. This is due to the fact that, both, the acquisition process of the data is difficult and the labeling of medical data is costly. The former is caused by the complex and expensive nature of medical sensors and strict data privacy laws. The latter is due to the high wages of medical professionals. To overcome this issue common strategies include data augmentation or the use of generative models. Both strategies however have in common that they extend the training distribution in a rather untargeted way. We presented the TSynD approach that allows for a more targeted creation of images.