Significance Statement: Nephropathologic analyses provide important outcomes-related data in the animal model studies that are essential to understanding kidney disease pathophysiology. In this work, the authors used a deep learning technique, the convolutional neural network, as a multiclass histology segmentation tool to evaluate kidney disease in animal models. This enabled a rapid, automated, high-performance segmentation of digital whole-slide images of periodic acid–Schiff–stained kidney tissues, allowing high-throughput quantitative and comparative analyses in multiple murine disease models and other species. The convolutional neural network also performed well in evaluating patient samples, providing a translational bridge between preclinical and clinical research. Extracted quantitative morphologic features closely correlated with standard morphometric measurements. Deep learning–based segmentation in experimental renal pathology is a promising step toward reproducible, unbiased, and high-throughput quantitative digital nephropathology. Background: Nephropathologic analyses provide important outcomes-related data in experiments with the animal models that are essential for understanding kidney disease pathophysiology. Precision medicine increases the demand for quantitative, unbiased, reproducible, and efficient histopathologic analyses, which will require novel high-throughput tools. A deep learning technique, the convolutional neural network, is increasingly applied in pathology because of its high performance in tasks like histology segmentation. Methods: We investigated use of a convolutional neural network architecture for accurate segmentation of periodic acid–Schiff-stained kidney tissue from healthy mice and five murine disease models and from other species used in preclinical research. We trained the convolutional neural network to segment six major renal structures: glomerular tuft, glomerulus including Bowman’s capsule, tubules, arteries, arterial lumina, and veins. To achieve high accuracy, we performed a large number of expert-based annotations, 72,722 in total. Results: Multiclass segmentation performance was very high in all disease models. The convolutional neural network allowed high-throughput and large-scale, quantitative and comparative analyses of various models. In disease models, computational feature extraction revealed interstitial expansion, tubular dilation and atrophy, and glomerular size variability. Validation showed a high correlation of findings with current standard morphometric analysis. The convolutional neural network also showed high performance in other species used in research—including rats, pigs, bears, and marmosets—as well as in humans, providing a translational bridge between preclinical and clinical studies. Conclusions: We developed a deep learning algorithm for accurate multiclass segmentation of digital whole-slide images of periodic acid–Schiff-stained kidneys from various species and renal disease models. This enables reproducible quantitative histopathologic analyses in preclinical models that also might be applicable to clinical studies.

The common marmoset (Callithrix jacchus, C. j.) is an established primate model in biomedical research and for human-related diseases. Monitoring of cardiovascular parameters including blood pressure (BP) is important for the health surveillance of these experimental animals and the quantification of diseases or pharmaceutical substances influencing BP. Measurement guidelines for C. j. do not exist yet; therefore, the present study was carried out to establish a practicable protocol based on recommendations of the American College of Veterinary Internal Medicine (ACVIM). Furthermore, BP data of 49 marmosets (13.8–202.4 months of age) were obtained via high-definition oscillometry to further knowledge of physiological parameters and gender-related differences in this primate. The thighs proved to be the most suitable measurement localization, since systolic values were less variable (left 4.03 ± 2.90%, right 5.96 ± 2.77%) compared with the tail (12.7 ± 6.96%). BP values were similar in the morning and in the afternoon (P > 0.05). Data were highly reproducible within and between several sessions on three consecutive days (P > 0.05) as well as over the course of 20 months (P > 0.05). Furthermore, the measurement time for females was significantly shorter than for males (5:14 ± 1:59 min versus 6:50 ± 1:58 min, P = 0.007). Measurement recommendations for the common marmoset were successfully established. Standardized values enabled a reliable comparison of BP parameters, e.g. for cardiovascular, toxicological or metabolic research.

Cardiovascular complications are the main cause of morbidity and mortality from diabetes. Herein, vascular inflammation is a major pathological manifestation. We previously characterized the cardiac microvascular inflammatory phenotype in diabetic patients and highlighted micro-RNA 92a (miR-92a) as a driver of endothelial dysfunction. In this article, we further dissect the molecular underlying of these findings by addressing anti-inflammatory Krüppel-like factors 2 and 4 (KLF2 and KLF4). We show that KLF2 dysregulation in diabetes correlates with greater monocyte adhesion as well as migratory defects in cardiac microvascular endothelial cells. We also describe, for the first time, a role for myocyte enhancer factor 2D (MEF2D) in cardiac microvascular dysfunction in diabetes. We show that both KLFs 2 and 4, as well as MEF2D, are dysregulated in human and porcine models of diabetes. Furthermore, we prove a direct interaction between miR-92a and all three targets. Altogether, our data strongly qualify miR-92a as a potential therapeutic target for diabetes-associated cardiovascular disease.