LEMON: a foundation model for nuclear morphology in Computational Pathology

TL;DR

LEMON is a self-supervised foundation model trained on millions of cell images, enabling scalable and robust single-cell morphological analysis in computational pathology.

Contribution

It introduces a novel self-supervised model for single-cell image representation learning, addressing a gap in current pathology analysis methods.

Findings

LEMON achieves strong performance on five benchmark datasets.

Supports large-scale single-cell analyses across diverse tissues and cancer types.

Model weights are publicly available at the provided URL.

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 scalable single-cell image representation learning. Trained on millions of cell images from diverse tissues and cancer types, LEMON learns robust and versatile morphological representations that support large-scale single-cell analyses in pathology. We evaluate LEMON on five benchmark datasets across a range of prediction tasks and show that it provides strong performance, highlighting its potential as a new paradigm for cell-level computational pathology. Model weights are available at https://huggingface.co/aliceblondel/LEMON.