Cell nuclei instance segmentation is a crucial task in digital kidney pathology. Traditional automatic segmentation methods often lack generalizability when applied to unseen datasets. Recently, the success of foundation models (FMs) has provided a more generalizable solution, potentially enabling the segmentation of any cell type. In this study, we perform a large-scale evaluation of three widely used state-of-the-art (SOTA) cell nuclei foundation models (Cellpose, StarDist, and CellViT). Specifically, we created a highly diverse evaluation dataset consisting of 2,542 kidney whole slide images (WSIs) collected from both human and rodent sources, encompassing various tissue types, sizes, and staining methods. To our knowledge, this is the largest-scale evaluation of its kind to date. Our quantitative analysis of the prediction distribution reveals a persistent performance gap in kidney pathology. Among the evaluated models, CellViT demonstrated superior performance in segmenting nuclei in kidney pathology. However, none of the foundation models are perfect; a performance gap remains in general nuclei segmentation for kidney pathology.
@article{arxiv.2408.06381,
title = {Assessment of Cell Nuclei AI Foundation Models in Kidney Pathology},
author = {Junlin Guo and Siqi Lu and Can Cui and Ruining Deng and Tianyuan Yao and Zhewen Tao and Yizhe Lin and Marilyn Lionts and Quan Liu and Juming Xiong and Yu Wang and Shilin Zhao and Catie Chang and Mitchell Wilkes and Mengmeng Yin and Haichun Yang and Yuankai Huo},
journal= {arXiv preprint arXiv:2408.06381},
year = {2025}
}