Search

The application of deep learning for automated segmentation (delineation of boundaries) of histologic primitives (structures) from whole slide images can facilitate the establishment of novel protocols for kidney biopsy assessment. Here, we developed and validated deep learning networks for the segmentation of histologic structures on kidney biopsies and nephrectomies. For development, we examined 125 biopsies for Minimal Change Disease collected across 29 NEPTUNE enrolling centers along with 459 whole slide images stained with Hematoxylin & Eosin (125), Periodic Acid Schiff (125), Silver (102), and Trichrome (107) divided into training, validation and testing sets (ratio 6:1:3). Histologic structures were manually segmented (30048 total annotations) by five nephropathologists. Twenty deep learning models were trained with optimal digital magnification across the structures and stains. Periodic Acid Schiff-stained whole slide images yielded the best concordance between pathologists and deep learning segmentation across all structures (F-scores: 0.93 for glomerular tufts, 0.94 for glomerular tuft plus Bowman's capsule, 0.91 for proximal tubules, 0.93 for distal tubular segments, 0.81 for peritubular capillaries, and 0.85 for arteries and afferent arterioles). Optimal digital magnifications were 5X for glomerular tuft/tuft plus Bowman's capsule, 10X for proximal/distal tubule, arteries and afferent arterioles, and 40X for peritubular capillaries. Silver stained whole slide images yielded the worst deep learning performance. Thus, this largest study to date adapted deep learning for the segmentation of kidney histologic structures across multiple stains and pathology laboratories. All data used for training and testing and a detailed online tutorial will be publicly available.

Autosomal-recessive polycystic kidney disease (ARPKD; MIM 263200) is a severe, typically early-onset form of cystic disease that primarily involves the kidneys and biliary tract. Phenotypic expression and age at presentation can be quite variable. 1 The incidence of ARPKD is 1 in 20000livebirths, 2 anditspleotropicmanifestationsarepotentially life-threatening. Optimal care requires proper surveillance to limit morbidity and mortality, knowledgeable approaches to diagnosis and treatment, and informed strategies to optimize quality of life. Clinical management therefore isideallydirected by multidisciplinary care teams consisting of perinatologists, neonatologists, nephrologists, hepatologists, geneticists, and behavioral specialists to coordinate patient care from the perinatal period to adulthood. In May 2013, an international team of 25 multidisciplinary specialists from the United States, Canada, Germany, and the United Kingdom convened in Washington, DC, to review the literature published from 1990 to 2013 and to develop recommendations for diagnosis, surveillance, and clinical management. Identification of the gene PKHD1, and the significant advances in perinatal care, imaging, medical management, and behavioral therapies during the past decade provide the foundational elements to define diagnostic criteria and establish clinical management guidelines as the first steps towards standardizing the clinical care for patients with ARPKD. The key issues discussed included recommendations regarding perinatal interventions, diagnostic criteria, genetic testing, management of renal and biliary-associated morbidities, and behavioral assessment. The meeting was funded by the National Institutes of Health and an educational grant from the Polycystic Kidney Disease Foundation. Here we summarize the discussions and provide an updated set of diagnostic, surveillance, and management recommendations for optimizing the pediatric care of patients with ARPKD. Specialist care of ARPKD-related complications, including dialysis, transplantation, and management of severe portal hypertension (HTN), will be addressed in a subsequent report. Given the paucity of information regarding targeted therapies in ARPKD, this topic was not addressed in this conference.

The Nephrotic Syndrome Study Network (NEPTUNE) is a North American multicenter collaborative consortium established to develop a translational research infrastructure for nephrotic syndrome. This includes a longitudinal observational cohort study, a pilot and ancillary study program, a training program, and a patient contact registry. NEPTUNE will enroll 450 adults and children with minimal change disease, focal segmental glomerulosclerosis, and membranous nephropathy for detailed clinical, histopathological, and molecular phenotyping at the time of clinically indicated renal biopsy. Initial visits will include an extensive clinical history, physical examination, collection of urine, blood and renal tissue samples, and assessments of quality of life and patient-reported outcomes. Follow-up history, physical measures, urine and blood samples, and questionnaires will be obtained every 4 months in the first year and biannually, thereafter. Molecular profiles and gene expression data will be linked to phenotypic, genetic, and digitalized histological data for comprehensive analyses using systems biology approaches. Analytical strategies were designed to transform descriptive information to mechanistic disease classification for nephrotic syndrome and to identify clinical, histological, and genomic disease predictors. Thus, understanding the complexity of the disease pathogenesis will guide further investigation for targeted therapeutic strategies.

Autosomal dominant polycystic kidney disease (ADPKD) and autosomal recessive polycystic kidney disease (ARPKD) are important inherited kidney diseases with distinct clinical features and genetics. Although these diseases have classically been considered "adult" (ADPKD) or "infantile/pediatric" (ARPKD), it is now clear that both diseases can present in children and adults. ADPKD and ARPKD also share important pathophysiologic features, including cilia dysfunction. ADPKD is a systemic disease involving cysts in the kidneys and abdominal organs as well as abnormalities in the heart and vasculature. Although it typically presents in adults, ADPKD has been diagnosed in fetuses, infants, children, and adolescents. The majority of children diagnosed with ADPKD are asymptomatic. Those with symptoms typically present with hypertension or gross hematuria. Routine screening for renal cysts in asymptomatic children who have a parent with ADPKD is generally not recommended. ARPKD is a disorder confined to the kidneys (polycystic kidneys) and liver (a developmental biliary lesion called congenital hepatic fibrosis). Although most children with ARPKD present in infancy with large, echogenic kidneys, a subset present later in childhood and even adulthood, primarily with complications related to the liver disease. As more patients with ARPKD survive to adulthood, these liver complications are likely to become more prevalent.