Can Generative Adversarial Networks help to overcome the limited data problem in segmentation?

Abstract

PurposeFor image translational tasks, the application of deep learning methods showed that Generative Adversarial Network (GAN) architectures outperform the traditional U-Net networks, when using the same training data size. This study investigates whether this performance boost can also be expected for segmentation tasks with small training dataset size. Materials/MethodsTwo models were trained on varying training dataset sizes ranging from 1—100 patients: a) U-Net and b) U-Net with patch discriminator (conditional GAN). The performance of both models to segment the male pelvis on CT-data was evaluated (Dice similarity coefficient, Hausdorff) with respect to training data size. ResultsNo significant differences were observed between the U-Net and cGAN when the models were trained with the same training sizes up to 100 patients. The training dataset size had a significant impact on the models’ performances, with vast improvements when increasing dataset sizes from 1 to 20 patients. ConclusionWhen introducing GANs for the segmentation task no significant performance boost was observed in our experiments, even in segmentation models developed on small datasets.