Identification of glomerulosclerosis using IBM Watson and shallow neural networks.

BACKGROUND: Advanced stages of different renal diseases feature glomerular sclerosis at a histological level which is observed by light microscopy on tissue samples obtained by performing a kidney biopsy. Computer-aided diagnosis (CAD) systems leverage the potential of artificial intelligence (AI) in healthcare to support physicians in the diagnostic process. METHODS: We propose a novel CAD system that processes histological images and discriminates between sclerotic and non-sclerotic glomeruli. To this goal, we designed, tested, and compared two artificial neural network (ANN) classifiers. The former implements a shallow ANN classifying hand-crafted features extracted from Regions of Interest (ROIs) by means of image-processing procedures. The latter, instead, employs the IBM Watson Visual Recognition System, which uses a deep artificial neural network making decisions taking the images as input, without the need to design any procedure for describing images with features. The input dataset consisted of 428 sclerotic glomeruli and 2344 non-sclerotic glomeruli derived from images of kidney biopsies scanned by the Aperio ScanScope System. RESULTS: Both AI approaches allowed to very accurately distinguish (mean MCC 0.95 and mean Accuracy 0.99) between sclerotic and non-sclerotic glomeruli. Although the systems may seem interchangeable, the approach based on feature extraction and classification would allow clinicians to gain information on the most discriminating features. In fact, further procedures could explain the classifier's decision by analysing which subset of features impacted the most on the final decision. CONCLUSIONS: We developed a customizable support system that can facilitate the work of renal pathologists both in clinical and research settings.

Performing an Ultrasound-Guided Percutaneous Needle Kidney Biopsy: An Up-To-Date Procedural Review.

Ultrasound-guided percutaneous renal biopsy (PRB) has revolutionized the clinical practice of nephrology in the last decades. PRB remains an essential tool for the diagnosis, prognosis, and therapeutic management of several renal diseases and for the assessment of renal involvement in systemic diseases. In this study, we examine the different applications and provide a review of the current evidence on the periprocedural management of patients. PRB is recommended in patients with significant proteinuria, hematuria, acute kidney injury, unexpected worsening of renal function, and allograft dysfunction after excluding pre- and post-renal causes. A preliminary ultrasound examination is needed to assess the presence of anatomic anomalies of the kidney and to identify vessels that might be damaged by the needle during the procedure. Kidney biopsy is usually performed in the prone position on the lower pole of the left kidney, whereas in patients with obesity, the supine antero-lateral position is preferred. After preparing a sterile field and the injection of local anesthetics, an automatic spring-loaded biopsy gun is used under ultrasound guidance to obtain samples of renal parenchyma for histopathology. After the procedure, an ultrasound scan must be performed for the prompt identification of potential early bleeding complications. As 33% of complications occur after 8 h and 91% occur within 24 h, the ideal post-procedural observation time is 24 h. PRB is a safe procedure and should be considered a routine part of the clinical practice of nephrology.

Metabolic Outcomes, Bone Health, and Risk of Polycystic Ovary Syndrome in Girls with Idiopathic Central Precocious Puberty Treated with Gonadotropin-Releasing Hormone Analogues.

BACKGROUND/AIMS: Gonadotropin-releasing hormone analogues (GnRHa) represent the gold standard treatment for central precocious puberty (CPP). We aimed to assess the effects of GnRHa treatment on metabolic outcomes, bone status, and polycystic ovary syndrome (PCOS) prevalence in young girls with idiopathic CPP (ICPP). METHODS: We enrolled 94 ICPP girls who were at least 2 years after menarche and had already attained adult height at the time of the study: 56 previously treated with depot triptorelin (3.4 ± 0.6 years) and 38 untreated. Auxological parameters, lipid profile, homeostatic model assessment of insulin resistance (HOMA-IR), bone state, and prevalence of PCOS were assessed. RESULTS: The 2 groups were similar for body mass index (BMI) and waist circumference. HOMA-IR, dehydroepi-androsterone sulfate, and Δ4-androstenedione were higher in the treated than in the untreated subjects (p < 0.001). Significant differences were found for amplitude-dependent speed of sound (p < 0.03) and bone transmission time z-scores (p < 0.01). The prevalence of PCOS was higher in the treated than in the untreated subjects (p < 0.04). CONCLUSION: GnRHa therapy is associated with hyperandrogenism and an increase in insulin resistance and PCOS prevalence, but not with increased BMI or lipid profile alterations. Long-term evaluations at the time of expected peak bone mass achievement are needed to understand the persistent or transient nature of subtle bone abnormalities.