Targeted data augmentations let single-sequence 3D spine segmentation models generalize to seven unseen CT and MRI datasets with 155% average Dice gain and almost no in-domain loss.
ResearchGate preprint (2025), https://www.researchgate.net/publication/389881289_TotalSpineSeg_Robust_ Spine_Segmentation_with_Landmark-Based_Labeling_in_MRI
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
One Sequence to Segment Them All: Efficient Data Augmentation for CT and MRI Cross-Domain 3D Spine Segmentation
Targeted data augmentations let single-sequence 3D spine segmentation models generalize to seven unseen CT and MRI datasets with 155% average Dice gain and almost no in-domain loss.