One Sequence to Segment Them All: Efficient Data Augmentation for CT and MRI Cross-Domain 3D Spine Segmentation

ArXi:2605.03098v1 Announce Type: new Deep learning-based medical image segmentation is increasingly used to clinical diagnosis and develop new treatment strategies. However, model performance remains limited by the scarcity of high-quality annotated data and insufficient generalization across imaging protocols. This limitation is particularly evident in MRI and CT, where models are typically trained on a single acquisition sequence and exhibit reduced robustness when applied to unseen sequences or contrasts.