The evaluation of kidney biopsies performed by expert pathologists is a crucial process for assessing if a kidney is eligible for transplantation. In this evaluation process, an important step consists of the quantification of global glomerulosclerosis, which is the ratio between sclerotic glomeruli and the overall number of glomeruli. Since there is a shortage of organs available for transplantation, a quick and accurate assessment of global glomerulosclerosis is essential for retaining the largest number of eligible kidneys. In the present paper, the authors introduce a Computer-Aided Diagnosis (CAD) system to assess global glomerulosclerosis. The proposed tool is based on Convolutional Neural Networks (CNNs). In particular, the authors considered approaches based on Semantic Segmentation networks, such as SegNet and DeepLab v3+. The dataset has been provided by the Department of Emergency and Organ Transplantations (DETO) of Bari University Hospital, and it is composed of 26 kidney biopsies coming from 19 donors. The dataset contains 2344 non-sclerotic glomeruli and 428 sclerotic glomeruli. The proposed model consents to achieve promising results in the task of automatically detecting and classifying glomeruli, thus easing the burden of pathologists. We get high performance both at pixel-level, achieving mean F-score higher than 0.81, and Weighted Intersection over Union (IoU) higher than 0.97 for both SegNet and Deeplab v3+ approaches, and at object detection level, achieving 0.924 as best F-score for non-sclerotic glomeruli and 0.730 as best F-score for sclerotic glomeruli.

Background/Aims: Cardiovascular disease is the most frequent cause of morbidity and mortality in autosomal dominant polycystic kidney disease (ADPKD) patients, often before the onset of renal failure, and the pathogenetic mechanism is not yet well elucidated. The aim of the study was to identify early and noninvasive markers of cardiovascular risk in young ADPKD patients, in the early stages of disease. Methods: A total of 26 patients with ADPKD and 24 control group, matched for age and sex, were enrolled, and we have assessed inflammatory indexes, mineral metabolism, metabolic state and markers of atherosclerosis and endothelial dysfunction (carotid intima media thickness (IMT), ankle brachial index (ABI), flow mediated dilation (FMD), renal resistive index (RRI), left ventricular mass index (LVMI)) and cardiopulmonary exercise testing (CPET), maximal O₂ uptake (V’O₂max), and O₂ uptake at lactic acid threshold (V’O₂@LT). Results: The ADPKD patients compared to control group, showed a significant higher mean value of LVMI, RRI, homocysteine (Hcy), Homeostasis Model Assessment-insulin resistance (HOMA-IR), serum uric acid (SUA), Cardiac-troponinT (cTnT) and intact parathyroid hormone (iPTH) (p<0.001, p<0.001, p<0.001, p<0.001, p<0.001, p=0.007, p=0.019; respectively), and a lower value of FMD and 25-hydroxyvitaminD (25-OH-VitD) (p<0.001, p<0.001) with reduced parameters of exercise tolerance, as V’O₂max, V’O₂max/Kg and V’O₂max (% predicted) (p<0.001, p<0.001, p=0.018; respectively), and metabolic response indexes (V’O₂@LT, V’O₂ @LT%, V’O₂@LT/Kg,) (p<0.001, p=0.14, p<0.001; respectively). Moreover, inflammatory indexes were significantly higher in ADPKD patients, and we found a positive correlation between HOMA-IR and C-reactive protein (CRP) (r=0.507, p=0.008), and a negative correlation between HOMA-IR and 25-OH-VitD (r=-0.585, p=0.002). Conclusion: In our study, ADPKD patients, in the early stages of disease, showed a greater insulin resistance, endothelial dysfunction, inflammation and mineral metabolism disorders, respect to control group. Moreover, these patients presented reduced tolerance to stress, and decreased anaerobic threshold to CPET. Our results indicate a major and early cardiovascular risk in ADPKD patients. Therefore early and noninvasive markers of cardiovascular risk and CPET should be carried out, in ADPKD patients, in the early stages of disease, despite the cost implication.

Background Computer-aided diagnosis (CAD) systems based on medical images could support physicians in the decision-making process. During the last decades, researchers have proposed CAD systems in several medical domains achieving promising results. CAD systems play an important role in digital pathology supporting pathologists in analyzing biopsy slides by means of standardized and objective workflows. In the proposed work, we designed and tested a novel CAD system module based on image processing techniques and machine learning, whose objective was to classify the condition affecting renal corpuscles (glomeruli) between sclerotic and non-sclerotic. Such discrimination is useful for the biopsy slides evaluation performed by pathologists. Results We collected 26 digital slides taken from the kidneys of 19 donors with Periodic Acid-Schiff staining. Expert pathologists have conducted the slides preparation, digital acquisition and glomeruli annotations. Before setting the classifiers, we evaluated several feature extraction techniques from the annotated regions. Then, a feature reduction procedure followed by a shallow artificial neural network allowed discriminating between the glomeruli classes. We evaluated the workflow considering an independent dataset (i.e., processing images not used in the training procedure). Ten independent runs of the training algorithm, and evaluation, allowed achieving MCC and Accuracy of 0.95 (± 0.01) and 0.99 (standard deviation < 0.00), respectively. We also obtained good precision (0.9844 ± 0.0111) and recall (0.9310 ± 0.0153). Conclusions Results on the test set confirm that the proposed workflow is consistent and reliable for the investigated domain, and it can support the clinical practice of discriminating the two classes of glomeruli. Analyses on misclassifications show that the involved images are usually affected by staining artefacts or present partial sections due to slice preparation and staining processes. In clinical practice, however, pathologists discard images showing such artefacts.

Background Age- and height-adjusted total kidney volume is currently considered the best prognosticator in patients with autosomal dominant polycystic kidney disease. We tested the ratio of urinary epidermal growth factor and monocyte chemotactic peptide 1 for the prediction of the Mayo Clinic Imaging Classes. Methods Urinary epidermal growth factor and monocyte chemotactic peptide 1 levels were measured in two independent cohorts (discovery, n = 74 and validation set, n = 177) and healthy controls (n = 59) by immunological assay. Magnetic resonance imaging parameters were used for total kidney volume calculation and the Mayo Clinic Imaging Classification defined slow (1A–1B) and fast progressors (1C–1E). Microarray and quantitative gene expression analysis were used to test epidermal growth factor and monocyte chemotactic peptide 1 gene expression. Results Baseline ratio of urinary epidermal growth factor and monocyte chemotactic peptide 1 correlated with total kidney volume adjusted for height (r = − 0.6, p < 0.001), estimated glomerular filtration rate (r = 0.69 p < 0.001), discriminated between Mayo Clinic Imaging Classes (p < 0.001), and predicted the variation of estimated glomerular filtration rate at 10 years (r = − 0.51, p < 0.001). Conditional Inference Trees identified cut-off levels of the ratio of urinary epidermal growth factor and monocyte chemotactic peptide 1 for slow and fast progressors at > 132 (100% slow) and < 25.76 (89% and 86% fast, according to age), with 94% sensitivity and 66% specificity (p = 6.51E−16). Further, the ratio of urinary epidermal growth factor and monocyte chemotactic peptide 1 at baseline showed a positive correlation (p = 0.006, r = 0.36) with renal outcome (delta-estimated glomerular filtration rate per year, over a mean follow-up of 4.2 ± 1.2 years). Changes in the urinary epidermal growth factor and monocyte chemotactic peptide 1 were mirrored by gene expression levels in both human kidney cysts (epidermal growth factor: − 5.6-fold, fdr = 0.001; monocyte chemotactic peptide 1: 3.1-fold, fdr = 0.03) and Pkd1 knock-out mouse kidney (Egf: − 14.8-fold, fdr = 2.37E-20, Mcp1: 2.8-fold, fdr = 6.82E−15). Conclusion The ratio of urinary epidermal growth factor and monocyte chemotactic peptide 1 is a non-invasive pathophysiological biomarker that can be used for clinical risk stratification in autosomal dominant polycystic kidney disease.

No abstract