A radiologist opens a whole spine MRI of a patient with suspected metastatic disease. There are twenty five vertebral bodies and two dozen discs to outline, from the sacrum up to the first cervical vertebra, plus the spinal cord. A…
TEAMS Mamba Snake Traces Organ Contours With Text Prompts Read More »
A dermatologist looking at a high frequency ultrasound scan of skin can read the layers the way a geologist reads rock strata. There is the bright epidermis at the surface, a dark band beneath it that clinicians call the subepidermal…
Physics Guided Synthetic Ultrasound for Skin Segmentation Read More »
Medical image segmentation is the task of coloring in a scan, drawing a precise outline around every organ or lesion so that a clinician can measure it, track it over time, or plan around it. Done by hand it is…
G2RA-Net: Graph Slices Sharpen Medical Image Segmentation Read More »
Teaching a model to outline a skin lesion or a polyp usually means paying experts to trace thousands of images by hand, which is slow and expensive. The obvious shortcut is to label a few and let the model learn…
SAUF-Net Separates Lesion Shape From Its Appearance Read More »
A sweeping new survey from UT Southwestern and UPenn maps the full landscape of SAM/SAM2-based Video Object Segmentation and Tracking — covering how models remember the past, understand the present, and predict the future of any moving object.
Segment Anything for Video: How SAM2 Is Reshaping Object Tracking and Segmentation Read More »
Ziyang Wang at Oxford and Chao Ma introduce Weak-Mamba-UNet: the first weakly-supervised framework that runs CNN, Vision Transformer, and Visual Mamba together under scribble supervision, letting each architecture’s strengths cover the others’ blind spots. On MRI cardiac segmentation, it achieves…
Researchers at Ruijin Hospital and the Chinese Academy of Sciences found a smarter way to use the Segment Anything Model in medical imaging: not as the deployed model, but as a teacher that never shows up at inference time —…
IERE: SAM-Powered Cross-Domain Medical Image Segmentation Without Inference Cost Read More »
Researchers at University of Nottingham Ningbo built a hybrid model that beats every state-of-the-art method across eight medical image datasets — not by stacking more layers or adding heavier attention, but by finally making CNN and Transformer encoders talk to…
Most medical segmentation systems are trained to find one thing. A polyp. An organ. A lesion. Nobody explicitly teaches the network what the tissue around that target actually looks like. The model learns foreground boundaries entirely from positive examples, so…
PraNet-V2 Fixes Medical Segmentation By Modeling Background Read More »
Researchers at Chongqing University of Technology built a u-shaped encoder-decoder that fuses dynamic sparse attention from BiFormer with a redesigned channel-spatial skip connection — outperforming TransUNet by 4.49% DSC and Swin-Unet by 3.34% DSC on the Synapse multi-organ benchmark while…
BRAU-Net++: U-Shaped Hybrid CNN-Transformer Network for Medical Image Segmentation Read More »