Loading…
Native 3D CT foundation model extending DINO self-distillation to a hierarchical Swin backbone, pretrained on 11,000 unlabeled radiology volumes.
Multi-sequence MRI foundation model pretrained on 336,476 volumetric scans, ranking first on 41 of 44 downstream clinical benchmarks.
3D MRI organ segmentation foundation model built on Swin-UNETR and trained on the UKBOB whole-body dataset covering 72 organs and skeletal structures.
Swin transformer foundation model for fluorescence microscopy image restoration, unifying denoising, super-resolution, and volumetric reconstruction.
Self-supervised pretraining framework for 3D medical image encoders that learns anatomy by predicting where a sub-volume sits within a CT scan.