Deep-learning model for evaluating histopathology of acute renal tubular injury.

Tubular injury is the most common cause of acute kidney injury. Histopathological diagnosis may help distinguish between the different types of acute kidney injury and aid in treatment. To date, a limited number of study has used deep-learning models to assist in the histopathological diagnosis of acute kidney injury. This study aimed to perform histopathological segmentation to identify the four structures of acute renal tubular injury using deep-learning models. A segmentation model was used to classify tubule-specific injuries following cisplatin treatment. A total of 45 whole-slide images with 400 generated patches were used in the segmentation model, and 27,478 annotations were created for four classes: glomerulus, healthy tubules, necrotic tubules, and tubules with casts. A segmentation model was developed using the DeepLabV3 architecture with a MobileNetv3-Large backbone to accurately identify the four histopathological structures associated with acute renal tubular injury in PAS-stained mouse samples. In the segmentation model for four structures, the highest Intersection over Union and the Dice coefficient were obtained for the segmentation of the "glomerulus" class, followed by "necrotic tubules," "healthy tubules," and "tubules with cast" classes. The overall performance of the segmentation algorithm for all classes in the test set included an Intersection over Union of 0.7968 and a Dice coefficient of 0.8772. The Dice scores for the glomerulus, healthy tubules, necrotic tubules, and tubules with cast are 91.78 ± 11.09, 87.37 ± 4.02, 88.08 ± 6.83, and 83.64 ± 20.39%, respectively. The utilization of deep learning in a predictive model has demonstrated promising performance in accurately identifying the degree of injured renal tubules. These results may provide new opportunities for the application of the proposed methods to evaluate renal pathology more effectively.

Graft lymphoma in a kidney transplant recipient: a case report.

Posttransplant lymphoproliferative disorders (PTLDs) are severe complications with heterogeneous clinical pictures involving abnormal lymphoproliferation in solid organ transplants and are known to be closely associated with Epstein-Barr virus (EBV) infection. Herein, we present a case of graft lymphoma in a febrile kidney transplant recipient. A 37-year-old woman was admitted with an abrupt 39 °C fever, mild graft discomfort, and gross hematuria. She had received deceased donor kidney transplantation 8 years earlier, but developed graft failure due to a recurrence of immunoglobulin A nephropathy. Laboratory tests revealed anemia and elevated levels of inflammatory markers. Enhanced abdominopelvic computed tomography showed graft swelling with perirenal fat stranding. Thus, we administered antibiotics for a urinary tract infection and increased the doses of steroids due to suspicion of graft intolerance syndrome. However, the patient's symptoms gradually worsened. Eventually, we performed graft nephrectomy and histologically confirmed EBV-positive diffuse large B cell lymphoma. We report a case in which a PTLD was considered in the differential diagnosis of a kidney transplant recipient with symptoms similar to those of a urinary tract infection or graft intolerance syndrome.

Serum VEGF-D level is correlated with renal dysfunction and proteinuria in patients with diabetic chronic kidney disease.

ABSTRACT: Biomarkers associated with chronic kidney disease (CKD) may play a crucial role in the early diagnosis of diabetic kidney disease. However, there have been few reports published on serum vascular endothelial cell growth factor (VEGF)-D in patients with diabetic CKD. We divided patients with diabetic CKD into two groups: CKD 3-4 and CKD 5. In total, 42 patients with diabetic kidney disease and seven healthy controls without diabetes mellitus were enrolled in this study. An observational study was conducted to evaluate the serum VEGF-D levels and other clinical parameters in each group and to assess the relationship among these factors. The serum levels of VEGF-D were higher in the CKD 3-4 group and CKD 5 group than in the control group. However, there was no significant difference in serum levels of VEGF-D between CKD stage 3-4 group and CKD stage 5 group. Correlation analysis showed that serum VEGF-D was negatively correlated with estimated glomerular filtration rate but positively correlated with serum creatinine, urine albumin-to-creatinine ratio, and urine protein-to-creatinine ratio. Serum VEGF-D was a good biomarker in receiver operating characteristic analysis and independently associated with CKD stages in multiple linear regression analysis. Circulating VEGF-D was positively correlated with blood growth/differentiation factor-15, endostatin, and chemokine (C-X-C motif) ligand 16 levels. Serum VEGF-D levels were correlated with renal dysfunction, albuminuria, and proteinuria in patients with diabetic kidney disease. Elucidation of the role of VEGF-D as a biomarker requires further study.

Kidney transplantation in human immunodeficiency virus-infected patients: a report of two cases and a review of the literatures.

Human immunodeficiency virus (HIV) infection was traditionally considered an absolute contraindication for transplantation because of concerns about HIV disease progression due to immunosuppression. Since potent antiretroviral therapies (ARTs) have become widely available, the prognosis of HIV-infected kidney transplant recipients has dramatically improved. Recent results of prospective multicenter trials on kidney transplantation (KT) in HIV-positive candidates have demonstrated the success and challenges of transplantation in this population. Several studies have reported comparable patient and graft outcomes between HIV-infected and HIV-uninfected recipients after KT in the era of potent combined ARTs. We report two cases of HIV-infected patients who underwent KT at our hospital. In this paper, we present a detailed report of two cases and provide a short review of the existing literature.