Lieske, John

Kidney stones are a common urologic condition with a high amount of recurrence. Recurrence depends on a multitude of factors the incidence of precursors to kidney stones, plugs, and plaques. One method of characterising the stone precursors is endoscopic assessment, though it is manual and time‐consuming. Deep learning has become a popular technique for semantic segmentation because of the high accuracy that has been demonstrated. The present Letter examined the efficacy of deep learning to segment the renal papilla, plaque, and plugs. A U‐Net model with ResNet‐34 encoder was tested; the Letter examined dropout (to avoid overtraining) and two different loss functions (to address the class imbalance problem. The models were then trained in 1666 images and tested on 185 images. The Jaccard‐cross‐entropy loss function was more effective than the focal loss function. The model with the dropout rate 0.4 was found to be more effective due to its generalisability. The model was largely successful at delineating the papilla. The model was able to correctly detect the plaques and plugs; however, small plaques were challenging. Deep learning was found to be applicable for segmentation of an endoscopic image for the papilla, plaque, and plug, with room for improvement.

AbstractThis review examines calcium and phosphate transport in the kidney through the lens of the rare X‐linked genetic disorder Dent disease. Dent disease type 1 (DD1) is caused by mutations in the CLCN5 gene encoding ClC‐5, a Cl−/H+ antiporter localized to early endosomes of the proximal tubule (PT). Phenotypic features commonly include low molecular weight proteinuria (LMWP), hypercalciuria, focal global sclerosis and chronic kidney disease; calcium nephrolithiasis, nephrocalcinosis and hypophosphatemic rickets are less commonly observed. Although it is not surprising that abnormal endosomal function and recycling in the PT could result in LMWP, it is less clear how ClC‐5 dysfunction disturbs calcium and phosphate metabolism. It is known that the majority of calcium and phosphate transport occurs in PT cells, and PT endocytosis is essential for calcium and phosphorus reabsorption in this nephron segment. Evidence from ClC‐5 KO models suggests that ClC‐5 mediates parathormone endocytosis from tubular fluid. In addition, ClC‐5 dysfunction alters expression of the sodium/proton exchanger NHE3 on the PT apical surface thus altering transcellular sodium movement and hence paracellular calcium reabsorption. A potential role for NHE3 dysfunction in the DD1 phenotype has never been investigated, either in DD models or in patients with DD1, even though patients with DD1 exhibit renal sodium and potassium wasting, especially when exposed to even a low dose of thiazide diuretic. Thus, insights from the rare disease DD1 may inform possible underlying mechanisms for the phenotype of hypercalciuria and idiopathic calcium stones.