BackgroundPathologists use visual classification of glomerular lesions to assess samples from patients with diabetic nephropathy (DN). The results may vary among pathologists. Digital algorithms may reduce this variability and provide more consistent image structure interpretation.MethodsWe developed a digital pipeline to classify renal biopsies from patients with DN. We combined traditional image analysis with modern machine learning to efficiently capture important structures, minimize manual effort and supervision, and enforce biologic prior information onto our model. To computationally quantify glomerular structure despite its complexity, we simplified it to three components consisting of nuclei, capillary lumina and Bowman spaces; and Periodic Acid-Schiff positive structures. We detected glomerular boundaries and nuclei from whole slide images using convolutional neural networks, and the remaining glomerular structures using an unsupervised technique developed expressly for this purpose. We defined a set of digital features which quantify the structural progression of DN, and a recurrent network architecture which processes these features into a classification.ResultsOur digital classification agreed with a senior pathologist whose classifications were used as ground truth with moderate Cohen’s kappa κ = 0.55 and 95% confidence interval [0.50, 0.60]. Two other renal pathologists agreed with the digital classification with κ1 = 0.68, 95% interval [0.50, 0.86] and κ2 = 0.48, 95% interval [0.32, 0.64]. Our results suggest computational approaches are comparable to human visual classification methods, and can offer improved precision in clinical decision workflows. We detected glomerular boundaries from whole slide images with 0.93±0.04 balanced accuracy, glomerular nuclei with 0.94 sensitivity and 0.93 specificity, and glomerular structural components with 0.95 sensitivity and 0.99 specificity.ConclusionsComputationally derived, histologic image features hold significant diagnostic information that may augment clinical diagnostics.

Neural networks promise to bring robust, quantitative analysis to medical fields, but adoption is limited by the technicalities of training these networks. To address this translation gap between medical researchers and neural networks in the field of pathology, we have created an intuitive interface which utilizes the commonly used whole slide image (WSI) viewer, Aperio ImageScope (Leica Biosystems Imaging, Inc.), for the annotation and display of neural network predictions on WSIs. Leveraging this, we propose the use of a human-in-the-loop strategy to reduce the burden of WSI annotation. We track network performance improvements as a function of iteration and quantify the use of this pipeline for the segmentation of renal histologic findings on WSIs. More specifically, we present network performance when applied to segmentation of renal micro compartments, and demonstrate multi-class segmentation in human and mouse renal tissue slides. Finally, to show the adaptability of this technique to other medical imaging fields, we demonstrate its ability to iteratively segment human prostate glands from radiology imaging data.

The modern Western diet is rich in advanced glycation end products (AGEs). We have previously shown an association between dietary AGEs and markers of inflammation and oxidative stress in a population of end stage renal disease (ESRD) patients undergoing peritoneal dialysis (PD). In the current pilot study we explored the effects of dietary AGEs on the gut bacterial microbiota composition in similar patients. AGEs play an important role in the development and progression of cardiovascular (CVD) disease. Plasma concentrations of different bacterial products have been shown to predict the risk of incident major adverse CVD events independently of traditional CVD risk factors, and experimental animal models indicates a possible role AGEs might have on the gut microbiota population. In this pilot randomized open label controlled trial, twenty PD patients habitually consuming a high AGE diet were recruited and randomized into either continuing the same diet (HAGE, n = 10) or a one-month dietary AGE restriction (LAGE, n = 10). Blood and stool samples were collected at baseline and after intervention. Variable regions V3-V4 of 16s rDNA were sequenced and taxa was identified on the phyla, genus, and species levels. Dietary AGE restriction resulted in a significant decrease in serum Nε-(carboxymethyl) lysine (CML) and methylglyoxal-derivatives (MG). At baseline, our total cohort exhibited a lower relative abundance of Bacteroides and Alistipes genus and a higher abundance of Prevotella genus when compared to the published data of healthy population. Dietary AGE restriction altered the bacterial gut microbiota with a significant reduction in Prevotella copri and Bifidobacterium animalis relative abundance and increased Alistipes indistinctus, Clostridium citroniae, Clostridium hathewayi, and Ruminococcus gauvreauii relative abundance. We show in this pilot study significant microbiota differences in peritoneal dialysis patients’ population, as well as the effects of dietary AGEs on gut microbiota, which might play a role in the increased cardiovascular events in this population and warrants further studies.

BackgroundThe progression of chronic kidney disease (CKD) remains one of the main challenges in clinical nephrology. Therefore, identifying the pathophysiological mechanisms and the independent preventable risk factors helps in decreasing the number of patients suffering end stage renal disease and slowing its progression.MethodsSmoking data was analyzed in patients with CKD throughout 2005-2009. One hundred and ninety-eight patients who had recently been diagnosed with stage three CKD or higher according to the National Kidney Foundation (NKF) 2002 Classification were studied. The control group was randomly selected and then matched with the case subjects using a computerized randomization technique. The relative risk was estimated by computing odds ratio (OR) by using multinomial logistic regression in SPSS ® for Windows between the two groups.ResultsSmoking significantly increases the risk of CKD (OR = 1.6, p = 0.009, 95% CI = 1.12-2.29). When compared to nonsmokers, current smokers have an increased risk of having CKD (OR = 1.63 p = 0.02, 95% CI = 1.08-2.45), while former smokers did not have a statistically significant difference. The risk increased with high cumulative quantity (OR among smokers with > 30 pack-years was 2.6, p = 0.00, 95% CI = 1.53-4.41). Smoking increased the risk of CKD the most for those classified as hypertensive nephropathy (OR = 2.85, p = 0.01, 95% CI = 1.27-6.39) and diabetic nephropathy (2.24, p = 0.005, 95% CI = 1.27-3.96). No statistically significant difference in risk was found for glomerulonephritis patients or any other causes.ConclusionThis study suggests that heavy cigarette smoking increases the risk of CKD overall and particularly for CKD classified as hypertensive nephropathy and diabetic nephropathy.