VoxForge: One Frozen 3D Encoder for MRI, CT and PET

Amazon AGI’s 388M-parameter ViT, trained on 235K commercial-use volumes, segments, classifies and registers scans without fine-tuning.
MedImgAnnotator: Batch Annotation for Large CT and MRI Cohorts

A Windows tool that queues folders of CT and MRI, pairs each scan with its predicted mask, and cuts the time spent per case.
SWIMSS: An Open MS Lesion Segmenter Trained on Seven Swiss Centres

A SwinUNETR trained on 1,385 people with MS from seven Swiss centres segments white matter lesions from FLAIR and MPRAGE, even on a CPU.
GRACE: Fixing Segmentation Masks With Retrieved Verified Cases

One refiner, trained once on CT, MRI and ultrasound, corrects a model’s mask using a verified case of the same organ from a library.
PathoDraw: One Zero-Shot Lesion Detector for Any Brain MRI

Trained only on synthetic lesions, one network flags stroke, glioma and white matter lesions on T1w, T2w or FLAIR brain MRI.
Scribble Once: Echo Cine Segmentation From One Scribbled Frame

Two scribbles on one frame per clip train a LoRA-adapted DINOv3 model to segment heart chambers across the whole echo sequence.
X-Strata: Separating Aneurysm and Vessel Layers in 2D Angiography

From two routine DSA cine runs, X-Strata recovers the full aneurysm sac, sorts crossing vessels in front or behind, and lifts both to 3D.
TinyUNet3D: 3D Segmentation in Under a Million Parameters

Glasgow distilled a 139M-parameter SegMamba-V2 into a 0.957M-parameter 3D U-Net. Distillation pays off mainly when labels are scarce.
Random Wavelet nnU-Net: Prostate Lesion Masks Across bpMRI Sites

An open nnU-Net trained on 1,579 bpMRI cases from five cohorts, with a wavelet augmentation that scrambles each sequence.
Awakening ImageCAS: Open Coronary Ostia and Centerlines for CCTA

Ostium labels for all 1000 ImageCAS scans, rooted centerline graphs with radii, and open localizers with sub-millimeter median error.