Deep learning-based histopathologic segmentation of peritubular capillaries in kidney transplant biopsies
Despite satisfactory performance of the DL-model developed in this study, we observed that prominent interstitial inflammation and fibrosis, where PTCs become less recognizable, and the presence of structures mimicking PTCs (e.g. atrophic tubules), posed the largest challenges for the model. Our model is novel as it was trained on a set of transplant biopsies with morphological abnormalities, requiring only PAS-stained kidney biopsies and confirmation of ground truth with the use of CD34 immunohistochemistry. Next steps include incorporation of inflammatory cell segmentation, which may enhance accuracy, reproducibility and quantitative scoring of peritubular capillaritis to guide pathologists in routine diagnostics.
Authors
- Nicolas Kozakowski (ORCID: https://orcid.org/0000-0001-9180-620X)
- Meyke Hermsen (ORCID: https://orcid.org/0000-0002-2531-7077)
- Željko Kikić (ORCID: https://orcid.org/0000-0002-0093-5389)
- Jesper Kers (ORCID: https://orcid.org/0000-0002-2418-5279)
- Luuk B. Hilbrands (ORCID: https://orcid.org/0000-0002-4935-9765)
- Dominique van Midden (ORCID: https://orcid.org/0000-0002-6607-8092)
- Linda Studer
- Jeroen van der Laak (ORCID: https://orcid.org/0000-0001-7982-0754)
- Eric J. Steenbergen
Institutions
- Radboud University Nijmegen (NL)
- Leiden University Medical Center (NL)
- Radboud University Medical Center (NL)
- Radboud Institute for Molecular Life Sciences (NL)
- Medical University of Vienna (AT)
Publication Details
- Journal
- Computers in Biology and Medicine
- Published
- 2025-05-24
- DOI
- https://doi.org/10.1016/j.compbiomed.2025.110395
- Citations
- 2
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- Nierstichting
- Medizinische Universität Wien