Search papers, labs, and topics across Lattice.
3
0
3
VCDP transforms semi-supervised medical image segmentation by aligning voxel embeddings with both global organ identities and local anatomical variations, leading to superior performance on challenging segmentation tasks.
SHTA achieves significant improvements in segmentation accuracy by ensuring semantic consistency in challenging regions, all without increasing inference costs.
Class imbalance in medical image segmentation is no longer a bottleneck: SCDL learns structured class-conditional feature distributions to segment minority structures with state-of-the-art accuracy.
