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

Highlights What are the main findings? Combining domain-generalized pre-training with test-time adaptation substantially enhances segmentation accuracy for medical images in out-of-domain scenarios. Generalizing image descriptors and intensity augmentation during training and adaptation outperformed complex existing methods in several scenarios. What is the implication of the main finding? We provide a powerful tool to achieve high segmentation accuracy out-of-domain, even without access to source data. Our efficient method is applicable to many top public 2D and 3D segmentation models trained on large, private datasets. Abstract Applying pre-trained medical deep learning segmentation models to out-of-domain images often yields predictions of insufficient quality. In this study, we propose using a robust generalizing descriptor, along with augmentation, to enable domain-generalized pre-training and test-time adaptation, thereby achieving high-quality segmentation in unseen domains. In this study, five different publicly available datasets, including 3D CT and MRI images, are used to evaluate segmentation performance in out-of-domain scenarios. The settings include abdominal, spine, and cardiac imaging. Domain-generalized pre-training on source data is used to obtain the best initial performance in the target domain. We introduce a combination of the generalizing SSC descriptor and GIN intensity augmentation for optimal generalization. Segmentation results are subsequently optimized at test time, where we propose adapting the pre-trained models for every unseen scan using a consistency scheme with the augmentation–descriptor combination. The proposed generalized pre-training and subsequent test-time adaptation improve model performance significantly in CT to MRI cross-domain prediction for abdominal (+46.2 and +28.2 Dice), spine (+72.9), and cardiac (+14.2 and +55.7 Dice) scenarios (p < 0.001). Our method enables the optimal, independent use of source and target data, successfully bridging domain gaps with a compact and efficient methodology.