Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information
This addresses the problem of model failure on unseen medical datasets from different centers and vendors, though it is incremental as it builds on existing style transfer methods.
The authors tackled domain generalization in multi-vendor cardiac image segmentation by using random style transfer for domain augmentation, achieving promising performance on unseen data from the M&Ms challenge2020 with 40 subjects.
Deep learning (DL)-based models have demonstrated good performance in medical image segmentation. However, the models trained on a known dataset often fail when performed on an unseen dataset collected from different centers, vendors and disease populations. In this work, we present a random style transfer network to tackle the domain generalization problem for multi-vendor and center cardiac image segmentation. Style transfer is used to generate training data with a wider distribution/ heterogeneity, namely domain augmentation. As the target domain could be unknown, we randomly generate a modality vector for the target modality in the style transfer stage, to simulate the domain shift for unknown domains. The model can be trained in a semi-supervised manner by simultaneously optimizing a supervised segmentation and an unsupervised style translation objective. Besides, the framework incorporates the spatial information and shape prior of the target by introducing two regularization terms. We evaluated the proposed framework on 40 subjects from the M\&Ms challenge2020, and obtained promising performance in the segmentation for data from unknown vendors and centers.