Assessment of Cell Nuclei AI Foundation Models in Kidney Pathology
This addresses the generalizability issue in cell nuclei segmentation for kidney pathology, providing a large-scale benchmark but is incremental as it assesses existing models without introducing new methods.
The study evaluated three state-of-the-art cell nuclei foundation models (Cellpose, StarDist, and CellViT) on a diverse dataset of 2,542 kidney whole slide images, finding that CellViT performed best but all models showed a persistent performance gap in kidney pathology segmentation.
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.