Roman David Buelow

The shortage of donor organs has led to an increased use of extended-criteria donors and donation after circulatory death for kidney transplantation, both of which are associated with graft injury. Although machine perfusion (MP) offers a preservation strategy, the most beneficial approach for kidneys with respect to effective graft preservation remains unclear. We compared oxygenated hypothermic (HMP) and normothermic machine perfusion (NMP) using a murine kidney perfusion model regarding intra-graft immune cell composition, viability, and inflammatory responses. NMP resulted in more severe tubular injury, accompanied by increased immune cell mobilization out of the graft. NMP increased early apoptosis among kidney-resident immune-cell populations, whereas endothelial cells showed increased late apoptosis after both strategies. Proximal tubular-cell apoptosis remained comparable to naïve tissue, and neither modality reduced reactive oxygen species levels. Both protocols induced antioxidant and hypoxia-responsive genes compared with static cold storage, while NMP elicited a stronger inflammatory response. Treatment with the senolytic ABT-263 demonstrated the model’s feasibility for investigating renal injury, cellular viability, and immune activation during MP.

Background: Activated parietal epithelial cells (PECs) and podocytes are key effector cells in the development of crescentic glomerulonephritis and focal segmental glomerulosclerosis (FSGS). Platelet-derived growth factor (PDGF)-C has been found to be important for tubulointerstitial fibrosis development, but its relevance for crescentic glomerulonephritis and FSGS was previously unknown. Methods: To address this, expression analyses for both PDGF-C and its receptor PDGFRα were carried out in mouse and human kidney tissues. To further elucidate a functional role of PDGF-C, the murine nephrotoxic nephritis model of crescentic glomerulonephritis was induced in a) Pdgfc -deficient mice, b) mice treated with a neutralizing PDGF-C antibody, and c) Pax8-cre::Pdgfc ^fl / ^fl mice with conditional Pdgfc deletion in kidney epithelial cells. We also subjected the collapsing FSGS model of the anti-Thy1.1 transgenic mouse to pharmacological PDGF-C inhibition. The studies were supplemented by PEC in vitro analyses. Results: Our data showed that PDGF-C was upregulated in PECs and expressed de novo in podocytes under disease conditions. It promoted the proliferation and activation of primary as well as conditionally immortalized PECs in vitro . In both the genetic and pharmacological PDGF-C intervention studies in murine crescentic glomerulonephritis and FSGS, significant improvements in glomerular crescent formation, glomerular sclerosis, renal inflammation and kidney function parameters were observed upon PDGF-C deficiency or antagonism. Mechanistically, transcription factor FOXM1 was identified as a mediator of disease-related PDGF-C expression in PECs. Conclusions: Our studies identified epithelial PDGF-C as a contributor to disease progression in crescentic glomerulonephritis and FSGS, acting in part through the activation of parietal epithelial cells.

Understanding pathological processes is crucial for the diagnosis, prediction and prognostication of kidney diseases. Although progress has been made in non-invasive diagnostic approaches, many pathological processes and diseases mainly manifest in the kidney tissue, necessitating comprehensive analyses of kidney samples. Cellular and molecular analyses of the kidney, including single-cell omics approaches, have identified novel disease mechanisms. However, these non-spatial methods lack information on cellular localization and tissue organization, which is crucial for understanding cell-cell interactions. Such information is particularly important for the kidney, which has many different cell types and intricate architecture. Developments in spatial omics technologies address this challenge by enabling the simultaneous analysis of molecular profiles and spatial context. Advances in three-dimensional imaging technologies, including non-destructive approaches, may provide additional layers of structural information. Integration of spatial omics technologies, such as transcriptomics, epigenomics and metabolomics, with imaging and computational pathology approaches, such as pathomics, has the potential to further advance understanding of the pathophysiology of kidney diseases. In the future, such approaches could become part of the diagnostic workflow in pathology. In the meantime, they hold great promise to aid the identification of diagnostic, prognostic and predictive biomarkers as well as novel therapeutic targets, and thereby facilitate drug discovery.

Introduction: Kidney biopsy reports contain rich information that is clinically actionable and useful for research. However, the narrative format hinders scalable reuse. We here investigated whether open-source large language models (LLMs) can extract relevant, standardized readouts from native kidney biopsy pathology reports. Methods: German free-text native kidney biopsy reports were parsed with three open-source LLMs (Llama3 70B, Llama3 8B, MedGemma) to generate structured JSON outputs covering relevant report elements (e.g., diagnosis, glomerular counts, histopathological patterns). Two independent observers manually curated the same report elements; disagreements between the two were resolved by an experienced nephropathologist to create the final ground truth. Performance was assessed using strict and soft matching and summarized accuracy. Inter-rated agreement was quantified using Cohen’s and Light’s Kappa with 95% confidence intervals via 1000-times bootstrapping. Results: Llama3 70B achieved the highest overall accuracy (93.3% strict, 97.1% soft), followed by MedGemma. These larger models showed near perfect performance for explicit and discrete variables and positivity of immunohistochemistry markers, while accuracy decreased for report elements requiring interpretation (e.g., primary diagnosis, interstitial inflammation in fibrosis vs. non-fibrotic cortex). Human raters showed strong agreement for the primary diagnosis (κ = 0.74, 95% CI 0.64-0.84). Adding Llama3 70B or MedGemma as a third rater increased overall agreement (0.82, 95% CI 0.74-0.89 and 0.78, 95% CI 0.69-0.85, respectively), whereas Llama3 8B reduced it. Conclusions: Open-source LLMs can accurately transform narrative nephropathology reports into a structured and machine-readable format, potentially supporting scalable retrospective cohort building. While some report elements can be extracted without supervision, interpretation-dependent elements should be supervised by a human observer. Lay Summary: Retrospective data collection from nephropathology reports is essential for building informative cohorts in computational nephropathology research, yet manual processing of narrative reports is time-consuming and limits scalability. In this study, we demonstrate that open-source large language models can reliably extract key diagnostic, quantitative, and descriptive data elements from kidney biopsy reports with high accuracy. While factual and clearly stated report elements can be extracted automatically, findings that require contextual or interpretative judgment still benefit from expert supervision. Overall, this approach substantially reduces manual effort and enables efficient generation of structured datasets from diagnostic routine, facilitating the development of kidney registries and future computational nephropathology research. In addition, such systems could be implemented into the routine diagnostic workflow, to directly transform narrative reports into structured data.

IgA nephropathy (IgAN) is a leading cause of kidney failure with diverse clinical presentations and treatment responses, particularly to corticosteroids, with conflicting evidence. Due to potentially severe side effects and heterogenous responses more individualized approaches are needed. We developed a causal machine learning framework for predicting individualized treatment effects of corticosteroids in IgAN by integrating clinical variables, histopathological scores, and deep learning-based biomarkers from digitized kidney biopsies (pathomics) of 1,022 patients from eight retrospective international cohorts. At the cohort-level, corticosteroids showed no significant effect on five-year kidney survival. However, the framework identified subpopulations with and without significant treatment benefit, improving progression-free kidney survival and also reducing overtreatment in low-benefit patients. Pathomics highlighted tubulointerstitial inflammation and glomerular tuft deformation as predictors of corticosteroid response. Our framework offers a blueprint for precision therapy in IgAN, supporting clinical decision-making in the era of emerging targeted treatments.

Deep learning (DL) holds great promise to improve medical diagnostics, including pathology. Current DL research mainly focuses on performance. DL implementation potentially leads to environmental consequences but approaches for assessment of both performance and carbon footprint are missing. Here, we explored an approach for developing DL for pathology, which considers both diagnostic performance and carbon footprint, calculated as CO₂ or equivalent emissions (CO₂eq). We evaluated various DL architectures used in computational pathology, including a large foundation model, across two diagnostic tasks of low and high complexity. We proposed a metric termed ‘environmentally sustainable performance’ (ESPer), which quantitatively integrates performance and operational CO₂eq during training and inference. While some DL models showed comparable diagnostic performance, ESPer enabled prioritizing those with less carbon footprint. We also investigated how data reduction approaches can improve the ESPer of individual models. This study provides an approach facilitating the development of environmentally friendly, sustainable medical AI.

Traditional histopathology, characterized by manual quantifications and assessments, faces challenges such as low-throughput and inter-observer variability that hinder the introduction of precision medicine in pathology diagnostics and research. The advent of digital pathology allowed the introduction of computational pathology, a discipline that leverages computational methods, especially based on deep learning (DL) techniques, to analyze histopathology specimens. A growing body of research shows impressive performances of DL-based models in pathology for a multitude of tasks, such as mutation prediction, large-scale pathomics analyses, or prognosis prediction. New approaches integrate multimodal data sources and increasingly rely on multi-purpose foundation models. This review provides an introductory overview of advancements in computational pathology and discusses their implications for the future of histopathology in research and diagnostics.

Background Prostate cancer (PCa) is among the most common cancers in men and its diagnosis requires the histopathological evaluation of biopsies by human experts. While several recent artificial intelligence-based (AI) approaches have reached human expert-level PCa grading, they often display significantly reduced performance on external datasets. This reduced performance can be caused by variations in sample preparation, for instance the staining protocol, section thickness, or scanner used. Another limiting factor of contemporary AI-based PCa grading is the prediction of ISUP grades, which leads to the perpetuation of human annotation errors. Methods We developed the prostate cancer aggressiveness index (PCAI), an AI-based PCa detection and grading framework that is trained on objective patient outcome, rather than subjective ISUP grades. We designed PCAI as a clinical application, containing algorithmic modules that offer robustness to data variation, medical interpretability, and a measure of prediction confidence. To train and evaluate PCAI, we generated a multicentric, retrospective, observational trial consisting of six cohorts with 25,591 patients, 83,864 images, and 5 years of median follow-up from 5 different centers and 3 countries. This includes a high-variance dataset of 8,157 patients and 28,236 images with variations in sample thickness, staining protocol, and scanner, allowing for the systematic evaluation and optimization of model robustness to data variation. The performance of PCAI was assessed on three external test cohorts from two countries, comprising 2,255 patients and 9,437 images. Findings Using our high-variance datasets, we show how differences in sample processing, particularly slide thickness and staining time, significantly reduce the performance of AI-based PCa grading by up to 6.2 percentage points in the concordance index (C-index). We show how a select set of algorithmic improvements, including domain adversarial training, conferred robustness to data variation, interpretability, and a measure of credibility to PCAI. These changes lead to significant prediction improvement across two biopsy cohorts and one TMA cohort, systematically exceeding expert ISUP grading in C-index and AUROC by up to 22 percentage points. Interpretation Data variation poses serious risks for AI-based histopathological PCa grading, even when models are trained on large datasets. Algorithmic improvements for model robustness, interpretability, credibility, and training on high-variance data as well as outcome-based severity prediction gives rise to robust models with above ISUP-level PCa grading performance.