Releases weights for LEMON, a foundation model for single-cell nuclear morphology trained on millions of pathology images.
March 30, 2026
Original Paper
LEMON: a foundation model for nuclear morphology in Computational Pathology
arXiv · 2603.25802
The Takeaway
While patch-level pathology models are common, single-cell foundation models are rare. This democratizes high-performance cell-level representations for cancer research and precision medicine.
From the abstract
Computational pathology relies on effective representation learning to support cancer research and precision medicine. Although self-supervised learning has driven major progress at the patch and whole-slide image levels, representation learning at the single-cell level remains comparatively underexplored, despite its importance for characterizing cell types and cellular phenotypes. We introduce LEMON (Learning Embeddings from Morphology Of Nuclei), a self-supervised foundation model for scalabl