HHMI Janelia Research Campus

Generalist cell segmentation model pairing SAM's ViT-L encoder with Cellpose flow fields, outperforming average human annotators on its benchmark.

Generalist cell segmentation pairing the cyto3 super-generalist model with one-click networks that denoise, deblur, and upsample microscopy images.

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.