Streamlining the Histopathologic Workflow in Diabetic Kidney Disease with Artificial Intelligence

Christos Matsoukas, Tajana Tešan Tomić, Pernilla Tonelius, Esther Nuñez‐Durán, Lihuan Liang, Annika Wernerson, Johan Mölne, Robert Menzies, Anna Granqvist, Pernille Hansen, Kevin Smith, Magnus SöderbergJournal of the American Society of Nephrology 2025 · DOI

Abstract

In this study, we accelerated and enhanced pathology readouts in a real-life pharmaceutical industry setting. We show that AI-assisted scoring reduced pathologists' workload and expedited study assessments. Self-supervised learning captured intrinsic properties of kidney morphology without expert annotation and reduced expert bias and translational discrepancies, greatly facilitating translational activities in drug development for patients with diabetic kidney disease.
BibTeX
@article{matsoukas2025streamlining,
  author = {Christos Matsoukas and Tajana Tešan Tomić and Pernilla Tonelius and Esther Nuñez‐Durán and Lihuan Liang and Annika Wernerson and Johan Mölne and Robert Menzies and Anna Granqvist and Pernille Hansen and Kevin Smith and Magnus Söderberg},
  title = {{Streamlining the Histopathologic Workflow in Diabetic Kidney Disease with Artificial Intelligence}},
  journal = {Journal of the American Society of Nephrology},
  year = {2025},
  doi = {10.1681/asn.0000000923},
}

Loading related content...

Figure