Adapting to Unseen Vendor Domains for MRI Lesion Segmentation

TL;DR

This study explores using unsupervised image translation to generate synthetic MRI data for unseen vendor domains, improving lesion segmentation performance across different scanner types.

Contribution

It demonstrates that label-to-image translation effectively enhances segmentation accuracy on unseen MRI vendor domains, approaching the performance of models trained on real target data.

Findings

Synthetic data from label-to-image translation improved segmentation performance.

Dice scores for synthetic data closely matched real data across vendors.

Unsupervised image translation can mitigate domain shifts in MRI segmentation.

Abstract

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 paper, we investigate the application an unsupervised image translation model to augment MR images from a source dataset to a target dataset. Specifically, we want to evaluate how well these models can create synthetic data points representative of the target dataset through image translation, and to see if a segmentation model trained these synthetic data points would approach the performance of a model trained directly on the target dataset. We consider 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 coeffcient 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.