Synthetic Data Generation Through Image Translation for Improving Out-of-domain MRI Lesion Segmentation

One of the key limitations in machine learning models is poor performance on data that is out of the domain of the training distribution. This is especially true for image analysis in magnetic resonance (MR) imaging, as variations in hardware and software create non-standard intensities, contrasts, and noise distributions across scanners. Recently, image translation models have been proposed to augment data across domains to create synthetic data points. In this thesis, the objective was to investigate the application an unsupervised image translation model to augment MR images from a source dataset to a target dataset to create synthetic data for training segmentation models. Specifically, the objective was to observe if training on these synthetic data points can approach the performance of a model trained directly on the target distribution. Three configurations of augmentation between datasets consisting of translation between images, between scanner vendors, and from labels to images. It was found that the segmentation models trained on synthetic data from labels to images configuration yielded the closest performance to the segmentation model trained directly on the target dataset. The Dice coefficient score per each target vendor (GE, Siemens, Philips) for training on synthetic data was 0.63, 0.64, and 0.58, compared to training directly on target dataset was 0.65, 0.72, and 0.61.