EUVIMEDEUVIMED entdecken
Open Access

Streamlining the Histopathologic Workflow in Diabetic Kidney Disease with Artificial Intelligence

Christos Matsoukas iD, Tajana Tesan Tomic, Pernilla Tonelius, Esther Nuñez-Duran, Lihuan Liang, Annika Wernerson, Johan Mölne, Robert I Menzies, Anna B Granqvist, Pernille B L Hansen, Kevin Smith, Magnus Söderberg iD

Journal of the American Society of Nephrology · 2025

DOI: 10.1681/asn.0000000923 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Society of Nephrology, 2025. Verfasst von Christos Matsoukas und 11 weiteren Autor:innen. Beteiligte Einrichtung: Pathology, Clinical Pharmacology and Safety Sciences, R&D AstraZeneca, Gothenburg, Sweden. Hauptthemen laut MEDLINE: Diabetic Nephropathies, Artificial Intelligence, Workflow. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Wallenberg AI, Autonomous Systems and Software Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Key Points Artificial intelligence models effectively generalized across studies and animal models and reduced translational gaps when applied to human biopsies. Artificial intelligence assistance reduced study evaluation turnaround times by up to 90% versus manual whole slide imaging scoring, matching expert-level performance. Self-supervised learning captured diabetic kidney disease–relevant features and mitigated expert-specific bias.

Background

Assessment of pathology end points in animal models of diabetic kidney disease is time-consuming and prone to expert bias. In addition, the sparsity of human kidney biopsy data hinders the development of translational models from animals to humans.

Methods

We developed an artificial intelligence (AI)–driven workflow to streamline histopathologic assessments in animal models of diabetic nephropathy. Our approach ( 1 ) detected glomeruli in whole slide images, ( 2 ) enabled fast expert scoring through an annotation tool, and ( 3 ) automated scoring. By leveraging unlabeled preclinical data for self-supervised learning, we enhanced AI scoring performance, reduced expert bias, and enabled the translation of AI scoring from animal models to human biopsies. To translate AI models from preclinical studies to human biopsies, we introduced a method that adjusted the feature extractor to human-specific features during inference without the need for annotated examples.

Results

Our annotation tool streamlined glomerular scoring, reducing turnaround time by 80%. Supervised AI models outperformed expert agreement and further reduced turnaround time by 90%, demonstrating generalization across studies involving both the same and different animal models. Without supervision, the self-supervised model achieved a κ value of 0.78, effectively identifying glomerular changes without guidance. Incorporating self-supervised learning into supervised training improved performance to κ=0.84 and reduced bias compared with individual experts ( P < 0.001). Our translational approach achieved a κ value of 0.63 on human glomeruli, although the model was trained exclusively on mouse glomeruli scores, reducing the translational gap by 45%.

Conclusions

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetic NephropathiesArtificial IntelligenceWorkflowAnimalsHumansMiceBiopsyDisease Models, AnimalKidney GlomerulusSupervised Machine Learning

Stichwörter der Autor:innen

CKDdiabetic kidney diseaseglomerular diseasesglomerulus

Autor:innen und Institutionen

  • Pathology, Clinical Pharmacology and Safety Sciences, R&D AstraZeneca, Gothenburg, Sweden.
  • KTH Royal Institute of Technology, Stockholm, Sweden.
  • Science for Life Laboratory, Stockholm, Sweden.
  • Bioscience Technology, Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM), BioPharmaceuticals R&D, AstraZeneca, Gothenburg, Sweden.
  • Bioscience Renal, Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM), BioPharmaceuticals R&D, AstraZeneca, Gothenburg, Sweden.
  • Bioscience Renal, Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM), BioPharmaceuticals R&D, AstraZeneca, Cambridge, United Kingdom.

ORCID-Profile: Christos Matsoukas, Magnus Söderberg

Förderung

  • Wallenberg AI, Autonomous Systems and Software Program

Zitieren

APA

Matsoukas, C., Tomic, T. T., Tonelius, P., Nuñez-Duran, E., Liang, L., Wernerson, A., Mölne, J., Menzies, R. I., Granqvist, A. B., Hansen, P. B. L., Smith, K., & Söderberg, M. (2025). Streamlining the Histopathologic Workflow in Diabetic Kidney Disease with Artificial Intelligence. Journal of the American Society of Nephrology. https://doi.org/10.1681/asn.0000000923

Vancouver

Matsoukas C, Tomic TT, Tonelius P, Nuñez-Duran E, Liang L, Wernerson A, et al. Streamlining the Histopathologic Workflow in Diabetic Kidney Disease with Artificial Intelligence. Journal of the American Society of Nephrology. 2025. doi:10.1681/asn.0000000923

BibTeX
@article{Matsoukas2025,
  author = {Matsoukas, Christos and Tomic, Tajana Tesan and Tonelius, Pernilla and Nuñez-Duran, Esther and Liang, Lihuan and Wernerson, Annika and Mölne, Johan and Menzies, Robert I and Granqvist, Anna B and Hansen, Pernille B L and Smith, Kevin and Söderberg, Magnus},
  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}
}
Kostenlos starten →