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.

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.

EGF-related growth factors in the pathogenesis of murine ARPKD. Background Epidermal growth factor (EGF), transforming growth factor-α (TGF-α) and their receptor, EGFR, play key roles in polycystic kidney disease (PKD) pathogenesis. Renal expression of two related growth factors, amphiregulin and heparin-binding EGF, has not been examined previously in PKD. The aims of this study of murine autosomal-recessive polycystic kidney disease (ARPKD) were ( 1 ) to characterize amphiregulin and heparin-binding EGF expression in cystic versus normal kidneys and cells; and ( 2 ) to identify the functional effects of abnormal EGF-related growth factor expression. Methods Amphiregulin and heparin-binding-EGF expression were examined by immunohistology and Western blot of kidneys and conditionally-immortalized collecting tubule cells obtained from cystic bpk mice (a murine model of ARPKD) and normal littermates. EGF, TGF-α, amphiregulin, and heparin-binding EGF in vitro effects on cystic and control collecting tubule cells were assessed by cell proliferation, cyst fluid mitogenicity, and EGFR activation. Results By immunohistology, amphiregulin and heparin-binding EGF localized to apical and basolateral surfaces of proximal tubule cysts > normal proximal tubules. In cystic collecting tubules, heparin-binding EGF (but not amphiregulin) localized to both apical and basolateral surfaces; whereas in normal collecting tubules, amphiregulin and heparin-binding EGF localized to the basolateral surface only. Increased amphiregulin and heparin-binding EGF expression by Western blot was seen in cystic vs. normal kidneys and increased heparin-binding EGF (but not amphiregulin) expression was present in cystic collecting tubule cell lines vs. controls. EGF, TGF-α, amphiregulin, and heparin-binding EGF were all mitogenic to cystic > control collecting tubule cells. Immunoprecipitation of EGF and TGF-α reduced cyst fluid mitogenicity by almost 80%, whereas heparin-binding EGF and amphiregulin immunoprecipitations had minimal effects. Differential receptor activation was also seen: Heparin-binding EGF markedly activated EGFR (>EGF = TGF-α > amphiregulin), with a greater effect seen in cystic vs. control collecting tubule cells. Conclusion Multiple EGF-related growth factors are abnormally expressed in murine ARPKD and may have differential roles in disease pathogenesis. In particular, newly identified abnormalities in heparin-binding EGF expression in cystic kidneys and cells may have important implications for disease pathogenesis.

A novel inhibitor of tumor necrosis factor-α converting enzyme ameliorates polycystic kidney disease. Background Transforming growth factor-α (TGF-α) expression is abnormal in polycystic kidney disease. We previously demonstrated that blockade of the epidermal growth factor receptor (EGFR), the receptor for TGF-α, significantly slowed disease progression in the bpk murine model of autosomal-recessive kidney disease (ARPKD). In the present study, kidney TGF-α expression in this model is characterized, and the therapeutic potential of inhibiting TGF-α in ARPKD is examined using a novel inhibitor of tumor necrosis factor-α converting enzyme (TACE), the metalloproteinase that cleaves membrane-bound TGF-α to release the secreted ligand. Methods Immunohistochemistry (IH) and Western analysis were performed on kidneys from cystic bpk mice and noncystic littermates at postnatal days 7, 14, and 21. Bpk mice and normal controls were treated with WTACE2, a competitive inhibitor of TACE, from day 7 until day 21, and the effects on kidney histology and renal function were assessed. Results Increased TGF-α expression by IH was demonstrated in the proximal tubules (PT) at postnatal day 7 and collecting tubules (CT) by day 21. A parallel increase in kidney TGF-α expression was demonstrated by Western analysis. Treatment of cystic bpk mice with WTACE2 resulted in a 43% reduction in kidney weight to body weight ratio (11.2 vs. 19.7%), improved cystic index (3.2 vs. 4.8), reduced cystic CT to PT ratio (1.2 vs. 8), and a greater than 30% reduction in BUN and serum creatinine. Conclusions These findings support the pathophysiological role of the TGF-α/EGFR axis in murine ARPKD and demonstrate that inhibition of TGF-α secretion has therapeutic potential in PKD.