Tag: medical image segmentation

Researchers have developed MDG-Net, a retinal vessel segmentation network that abandons traditional skip connections in favor of a multilevel decoder ...

Vietnamese researchers have trained a 3D U-Net to reconstruct facial soft tissue directly from skull geometry, achieving millimeter-level accuracy while ...

Researchers in China have developed REF-VMUNetUp, a Mamba-based network with rotary position embeddings and dynamic upsampling that improves multi-organ segmentation ...

Researchers have developed a unified scoring method that combines multiple accuracy metrics with model confidence to provide a more clinically ...

Researchers in China have developed NAHFormer, a transformer-based segmentation framework using neighborhood attention and hierarchical feature fusion that outperforms state-of-the-art ...

Medical images rarely look the same twice. A retinal scan captured on one clinic's fundus camera can differ dramatically, in ...