<ul><li>DG-TTA: Out-of-domain Medical Image Segmentation through Augmentation and Descriptor-driven Domain Generalization and Test-Time Adaptation</li><li>Researchers propose using a powerful generalizing descriptor and augmentation to enable domain-generalized pre-training and test-time adaptation for high-quality segmentation in unseen domains.</li><li>The method was evaluated on five different publicly available datasets, including 3D CT and MRI images, in abdominal, spine, and cardiac imaging scenarios.</li><li>Results show significant improvements in cross-domain prediction for abdominal, spine, and cardiac scenarios, with increased Dice similarity scores ranging from 14.2% to 72.9%.</li></ul>

DG-TTA: Out-of-domain Medical Image Segmentation through Augmentation and Descriptor-driven Domain Generalization and Test-Time Adaptation

Discover more