Streamlining the Histopathologic Workflow in Diabetic Kidney Disease with Artificial Intelligence
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.
Authors
- Christos Matsoukas (ORCID: https://orcid.org/0000-0003-1401-3497)
- Johan Mölne (ORCID: https://orcid.org/0000-0001-6241-7117)
- Pernille Hansen (ORCID: https://orcid.org/0000-0003-0661-1665)
- Tajana Tešan Tomić
- Annika Wernerson (ORCID: https://orcid.org/0000-0003-2792-0010)
- Anna Granqvist
- Esther Nuñez‐Durán
- Kevin Smith (ORCID: https://orcid.org/0000-0002-6163-191X)
- Robert Menzies (ORCID: https://orcid.org/0000-0003-3833-5765)
- Pernilla Tonelius
- Lihuan Liang
- Magnus Söderberg (ORCID: https://orcid.org/0000-0003-0946-5202)
Institutions
- Science for Life Laboratory (SE)
- Sahlgrenska University Hospital (SE)
- Karolinska Institutet (SE)
- AstraZeneca (South Korea) (KR)
- Ribocon (Germany) (DE)
- AstraZeneca (Finland) (FI)
- AstraZeneca (Sweden) (SE)
- KTH Royal Institute of Technology (SE)
- University of Gothenburg (SE)
Publication Details
- Journal
- Journal of the American Society of Nephrology
- Published
- 2025-11-12
- DOI
- https://doi.org/10.1681/asn.0000000923
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00