HHMI Janelia Research Campus

Generalist cell segmentation model combining SAM's ViT-L backbone with Cellpose flow fields. First model to surpass average human annotators on the Cellpose benchmark.

Generalist cell segmentation framework with a super-generalist cyto3 model and one-click image restoration networks optimized for downstream segmentation quality.

Human-in-the-loop cell segmentation framework enabling custom model training from as few as 100-200 corrected annotations.

Generalist deep learning algorithm for cell and nucleus instance segmentation using simulated diffusion flows, without per-dataset retraining.