rewire.it
Paper-reported evidence

Evaluating cell AI foundation models in kidney pathology with human-in-the-loop enrichment

2025 · Peer-reviewed · PMC archival version PMC12644679.1

Paper-reported results. The values below come from this source, not an independent rewire.it run.

Open primary paper →DOI: 10.1038/s43856-025-01205-x

Primary full text verified using Europe PMC XML; venue: Communications Medicine; PMC ID: PMC12644679.

2 verified numerical rows · source checked 2026-09-15

Paper-reportedAuthor's model

Cellpose + easy 100%

Kidney histopathology cell segmentation

Reported score
0.7529
Metric
F1 score
Dataset / split
Kidney pathology images

Fine-tuned Cellpose with all easy samples selected in the paper.

Table 2, Cellpose Easy 100% row, F1 score columnVerify at source →
Paper-reportedIndependent paper evaluation

Cellpose baseline

Kidney histopathology cell segmentation

Reported score
0.6748
Metric
F1 score
Dataset / split
Kidney pathology images

Cellpose segmentation before human-in-the-loop fine-tuning.

Table 2, Cellpose baseline row, F1 score columnVerify at source →