Diagnosis Of Renal Pathology Research Articles

B-009 Verification of Result Interchangeability Between Two Analyzers in the Determination of Uric Acid and Urea

Abstract Background Uric acid and urea are two parameters widely used in the diagnosis and management of renal pathology. In our laboratory, they are determined using Atellica Solution® analyzers (Siemens Healthineers). After validating a new Siemens equipment, Atellica CI®, it is essential to ensure result interchangeability in our laboratory accredited by ISO 15189:2012. Objectives evaluate the interchangeability of results for uric acid and urea measured by Atellica Solution® and CI® analyzers. Methods A total of 40 serum samples from patients with uric acid values between 1.3 and 15.2 mg/dL, and another 40 serum samples from patients with urea values between 7 and 142 mg/dL were processed in parallel. Statistical analysis of the results was performed using Passing-Bablok regression and Bland Altman mean difference analysis with Method Validator Version 1.19. Results are expressed with their 95% confidence interval. Results Uric Acid: After analyzing Bland-Altman differences, a statistically significant slight systematic error was found, as the 95% CI does not include 0, with slightly higher results in CI 1900®. Regarding Passing-Bablok regression analysis, there were no systematic errors of constant type (since the 95% CI of the intercept includes 0) but a discreet significant proportional systematic error was observed (the confidence interval of the slope does not include 1).Urea: In Bland-Altman analysis, a discreet systematic error was observed as the 95% CI of the mean difference does not include the null value. Regarding Passing-Bablok regression analysis, there were no systematic errors of constant type (since the 95% CI of the intercept includes 0) or proportional type (since the 95% CI of the slope includes 1), indicating interchangeability between both analyzers. Conclusions The results obtained by both Atellica Solution® and CI® analyzers for uric acid and urea assays are interchangeable since the statistically significant differences observed can be considered analytically and clinically insignificant.

Predicting prognostic factors in kidney transplantation using a machine learning approach to enhance outcome predictions: a retrospective cohort study.

Accurate forecasting of clinical outcomes after kidney transplantation is essential for improving patient care and increasing the success rates of transplants. Our study employs advanced machine learning (ML) algorithms to identify crucial prognostic indicators for kidney transplantation. By analyzing complex datasets with ML models, we aim to enhance prediction accuracy and provide valuable insights to support clinical decision-making. Analyzing data from 4077 KT patients (June 1990 - May 2015) at a single center, this research included 27 features encompassing recipient/donor traits and peri-transplant data. The dataset was divided into training (80%) and testing (20%) sets. Four ML models-eXtreme Gradient Boosting (XGBoost), Feedforward Neural Network, Logistic Regression, and Support Vector Machine-were trained on carefully selected features to predict the success of graft survival. Performance was assessed by precision, sensitivity, F1 score, Area Under the Receiver Operating Characteristic (AUROC), and Area Under the Precision-Recall Curve. XGBoost emerged as the best model, with an AUROC of 0.828, identifying key survival predictors like T-cell flow crossmatch positivity, creatinine levels two years post-transplant and human leukocyte antigen mismatch. The study also examined the prognostic importance of histological features identified by the Banff criteria for renal biopsy, emphasizing the significance of intimal arteritis, interstitial inflammation, and chronic glomerulopathy. The study developed ML models that pinpoint clinical factors crucial for KT graft survival, aiding clinicians in making informed post-transplant care decisions. Incorporating these findings with the Banff classification could improve renal pathology diagnosis and treatment, offering a data-driven approach to prioritizing pathology scores.

Segmentation and thickness calculation of glomerular basement membrane using RADS-Net in glomerular microscopic images

Glomerular ultrastructure needs to be observed under transmission electron microscopy during pathological diagnosis of renal biopsies. Evaluating the glomerular basement membranes (GBM) is necessary for the renal pathological diagnosis. There is little work that performs well for full-flow automated analysis of GBM in whole-glomerular electron microscopy images, including GBM segmentation, location, and thickness calculation. To address this problem, we propose a network architecture, RADS-Net, whose segmentation module combines the advantages of ViT and CNN to achieve better performance in GBM and electron dense deposit (EDD) segmentation tasks. It also contains an uncertainty evaluation module and a location module to exclude unsuitable regions for measurement and extract accurate GBM contours. We propose a GBM thickness calculation method based on statistical learning method, skeletonization algorithm, and improved region growth method. Systematic experiments demonstrate that our proposed segmentation network achieves superior accuracy compared to other competing methods. Additionally, the computed GBM thickness, after an automatic screening of suitable fields of view, meets the requirements for pathology evaluation.

First case report of PLA2R-related monotypic (IgG-κ positive) membranous nephropathy concurrent with leukocyte chemotactic factor 2 amyloidosis

BackgroundMembranous nephropathy (MN) is a major pattern of nephrotic syndrome (NS) in adults. Some MN have secondary causes and some may be accompanied with other glomerular diseases. MN patients coexisting with amyloidosis are very rare, and mostly was polytypic MN. Herein, we describe the first report which identifying monotype PLA2R-MN (κ light chain) concurrent with leukocyte chemotactic factor 2 amyloidosis (ALECT2). This rare case highlights the importance of renal pathology for diagnosis.Case presentationWe describe a case of a 60-year-old male patient with persistent proteinuria and low serum albumin for nine months. No monoclonal component was revealed by serum and urine immunofixation electrophoresis but serum PLA2R antibody was positive. The patient was empirically treated with Leflunomide and Losartan, but edema was not improved. The diagnosis of renal pathology is PLA2R-related monotypic (IgG-κ positive) MN concurrent with ALECT2. Methylprednisolone, cyclosporine A and anticoagulant (rivaroxaban) were prescribed resulting in a complete remission of NS.ConclusionsMN patients concurrent with ALECT2 presented massive proteinuria or NS. When nephrotic range proteinuria is present in ALECT2, it is important to consider that it may be due to a concomitant underlying nephropathy especially MN and treated according to MN will get good therapeutic effect.

Validation and comparison of diabetic retinopathy-based diagnostic models for diabetic nephropathy

To validate and compare the efficacy of two noninvasive diagnostic models for diabetic nephropathy (DN) based on diabetic retinopathy (DR). A total of 565 patients with type 2 diabetes undergoing kidney biopsy in the Department of Nephrology, PLA General Hospital from January, 1993 to December, 2014 were studied. The patients were divided into DN group and non-diabetic nephropathy (NDRD) group according to renal pathological diagnosis. The data from the 22-year period were divided into 3 stages based on chronological order: early stage (from 1993 to 2003), middle stage (from 2004 to April, 2012), and late stage (from May, 2012 to December, 2014). The changes in clinical features and pathological diagnosis of the patients with renal biopsy over the 22 years were analyzed. The published DNT model and JDB model, both based on DR, were validated and compared for diagnostic effectiveness of DN, and the characteristics of the misdiagnosed cases were analyzed. The incidences of hypertension and DR and levels of glycosylated hemoglobin (HbA1c), creatinine and 24-h urinary protein were all significantly higher, while hemoglobin and triglyceride levels were lower in DN group than in NDRD group (P<0.05). The proportion of NDRD cases increased gradually over time, with IgA nephropathy and membranous nephropathy as the main pathological types. The AUC of JDB model was 0.946, similar to that of NDT model (0.925; P=0.198). The disease course of diabetes, hematuria and incidence of DR were important clinical features affecting the diagnostic accuracy of the models. The clinical features and pathological diagnosis of DR change over time. The non-invasive diagnostic models based on DR have good diagnostic efficacy for DN.

VGG16-based intelligent image analysis in the pathological diagnosis of IgA nephropathy

ObjectiveIgA nephropathy (IgAN) is the most common primary glomerular disease worldwide, with heterogeneous clinical and pathological manifestations, and is a common cause of end-stage renal disease. Early detection and effective intervention measures are essential for improving the outcome of IgAN. Machine learning methods can make the pathological analysis, early detection and diagnosis, and prognosis prediction of IgAN more automated and accurate. This article discusses the application of machine learning methods in IgAN, from optimizing pathological diagnosis to discovering non-invasive specific biomarkers, predicting disease progression, and evaluating prognosis. It is the key to reducing the incidence rate and mortality of end-stage renal disease by relying on intelligent image analysis of VGG16 for accurate detection and diagnosis of IgA nephropathy to enable clinical to take effective prevention and treatment measures. MethodsA total of 452 cases of kidney disease admitted to the nephrology department of our hospital from January 2018 to February 2023 were selected, and it was ruled out that pathological diagnosis could not be made due to the small number of samples submitted for renal puncture; After excluding suspected cases of renal biopsy pathology diagnosis and patients who did not undergo immunofluorescence examination, a total of 135 confirmed IgA nephropathy patients were subjected to image analysis. The internationally recognized 5-level semi-quantitative method was used for evaluation, and traditional image processing methods were selected to segment and extract fluorescence deposition areas. Transform the input image into color space and generate a binary image using the adaptive threshold method in the two feature dimensions of color and brightness. Then, VGG16 regions were separated and merged to obtain independent sedimentary regions. VGG16 was used to add BN layers and SE visual attention to fully extract sensitive features with high inter-class similarity and significant intra-class differences in the IgA nephropathy image classification task. The contour, area, and average brightness of each sedimentary region were calculated, and automatic computer recognition of fluorescence deposition intensity and shape was obtained to improve the accuracy of IgA nephropathy image classification. ResultsThe artificial intelligence image analysis based on VGG16 can achieve the interpretation of IgA nephropathy immunofluorescence results with a higher coincidence rate compared to the results of pathological diagnostic doctors. IgA reaches 88.9%, IgG reaches 85.8%, IgM reaches 83.8%, and C3 reaches 88.6%. Therefore, it can assist pathological diagnostic doctors in interpreting IgA nephropathy immunofluorescence. ConclusionBy fully utilizing computer and network technologies to change the pathological workflow, improve the work efficiency of pathological diagnostic doctors, reduce the misdiagnosis rate caused by fatigue during film reading, and make pathological diagnosis more accurate and objective.

Cytological method of research in the diagnosis of urinary pathology in liver cirrhosis

Objective. To determine the possibilities of cytological method of urine cellular sediment examination for diagnosis and differential diagnosis of renal and urinary tract pathology in liver cirrhosis.Materials and methods. A standard observational study of 50 inpatients with liver cirrhosis was performed. Cytological preparations of urine sediment were prepared by liquid cytology and cytocentrifugation methods and after fixation were Results. Cytological study of cellular urine sediment in hospitalized patients with cirrhosis revealed dysmorphic (leached) erythrocytes in 31% of cases, statistically significantly more frequently in patients with decompensation of the disease and 30-day mortality (p&lt;0,05). Microflora in the urine was found in 63% of patients, more often of mixed nature (27%). In 46% of patients with decompensated liver cirrhosis, including acute renal injury, cytological preparation of urinary sediment is represented by multicellular elements with the presence of superficial and deep urothelium and renal epithelium.Conclusions. Cytological method of studying the cellular urine sediment is an accessible, informative and cheap diagnostic method, the possibilities of which are to determine the presence and origin of cellular elements (urothelium of the surface and deep layers, altered erythrocytes), microflora and its source (genital tract, urinary tract), which, in combination with other methods, allows to verify the diagnosis of the patient and to carry out differential diagnosis of acute tubular necrosis and hepatorenal syndrome.

Clinico-pathological features of diabetic and non-diabetic renal diseases in type 2 diabetic patients: a retrospective study from a 10-year experience in a single center.

To compare clinical and pathological characteristics as well as prognosis between diabetic nephropathy (DN) and non-diabetic renal disease (NDRD) so as to explore potential diagnostic criteria of DN and provide some guidance for the treatment of type 2 diabetes mellitus (T2DM) patients with kidney involvement. T2DM patients with renal impairment who underwent kidney biopsy were included in this study, who were classified into 3 groups (DN, NDRD, DN with NDRD) based on their renal pathological diagnosis. Baseline clinical characteristics as well as follow-up data were collected and analyzed among 3 groups. Logistic regression was performedto determine the best predictors for DN diagnosis. Additional 34 MN patients without diabetes were enrolled by propensity score matching method to compare serum PLA2R antibody titer and kidney outcomes between diabetic MN patients and MN alone. Among 365 patients with type 2 diabetes who underwent kidney biopsy, 179 (49.0%) patients were diagnosed with NDRD alone and 37 (10.1%) patients with NDRD combined DN. Risk factors for DN development in T2DM patients were longer time since diabetes diagnosis, higher level of serum creatinine, absence of hematuria and presence of diabetic retinopathy by multivariate analysis. Lower rate of proteinuria remission and higher risk of renal progression were observed in DN group compared with NDRD group. Membranous nephropathy was the most common NDRD in diabetic patients. There was no difference in serum PLA2R antibody positiveness or titer between MN patients with or without T2DM. There was lower remission rate but similar renal progression in diabetic MN when age, gender, baseline eGFR, albuminuria and IFTA score were adjusted. Non-diabetic renal disease is not uncommon in T2DM patients with renal impairment, which has better prognosis with proper treatment. Coexisting diabetic status does not exert negative impact on renal progression in MN patients, and immunosuppressive agents should be administered when necessary.

Pathogenesis and histological changes of nephropathy associated with COVID-19.

Coronavirus disease 2019 (COVID-19) can cause damage to multiple organ, not only to the lungs, but also to the kidneys. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) can cause acute and chronic kidney disease through direct viral infection, indirect injury, and vaccination-related injury. Like lung injury, kidney injury is also an important aspect affecting the severity and prognosis of SARS-CoV-2. This article summarizes the pathogenesis, pathological manifestations, and clinical features of SARS-CoV-2 direct or indirect renal injury. Including direct injury, indirect injury, special comorbidities (receiving kidney transplantation and chronic kidney disease), and vaccine-related renal injury, and exploring the possible therapeutic effect of anti-SARS-CoV-2 therapy on renal injury. The purpose is to provide reference for understanding COVID-19-related renal injury, guiding clinical and pathological diagnosis and treatment, and evaluating prognosis.

Artificial intelligence in renal pathology: Current status and future.

Renal biopsy pathology is an essential gold standard for the diagnosis of most kidney diseases. With the increase in the incidence rate of kidney diseases, the lack of renal pathologists, and an imbalance in their distribution, there is an urgent need for a new renal pathological diagnosis model. Advances in artificial intelligence (AI) along with the growing digitization of pathology slides for diagnosis are promising approach to meet the demand for more accurate detection, classification, and prediction of the outcome of renal pathology. AI has contributed substantially to a variety of clinical applications, including renal pathology. Deep learning, a subfield of AI that is highly flexible and supports automatic feature extraction, is increasingly being used in multiple areas of pathology. In this narrative review, we first provide a general description of AI methods, and then discuss the current and prospective applications of AI in the field of renal pathology. Both diagnostic and predictive prognostic applications are covered, emphasizing AI in renal pathology images, predictive models, and 3D in renal pathology. Finally, we outline the challenges associated with the implementation of AI platforms in renal pathology and provide our perspective on how these platforms might change in this field.

Mechanisms underlying acupuncture therapy in chronic kidney disease: A narrative overview of preclinical studies and clinical trials.

Chronic kidney disease (CKD) is associated with high incidence, low awareness, and high disability rates among the population. Moreover, the disease significantly affects the physical and mental health of patients. Approximately 25% of patients with CKD develop end-stage renal disease (ESRD) within 20 years of diagnosis and have to rely on renal replacement therapy, which is associated with high mortality, heavy economic burden, and symptoms including fatigue, pain, insomnia, uremia pruritus, and restless leg syndrome. Currently, the means to delay the progress of CKD are insufficient; therefore, developing strategies for delaying CKD progression has important practical implications. In recent years, more and more people are accepting the traditional Chinese medical technique "acupuncture." Acupuncture has been shown to improve the uncomfortable symptoms of various diseases through stimulation (needling, medicinal moxibustion, infrared radiation, and acupressure) of acupoints. Its application has been known for thousands of years, and its safety and efficacy have been verified. As a convenient and inexpensive complementary therapy for CKD, acupuncture has recently been gaining interest among clinicians and scientists. Nevertheless, although clinical trials and meta-analysis findings have demonstrated the efficacy of acupuncture in reducing albuminuria, improving glomerular filtration rate, relieving symptoms, and improving the quality of life of patients with CKD, the underlying mechanisms involved are still not completely understood. Few studies explored the correlation between acupuncture and renal pathological diagnosis. The aim of this study was to conduct a literature review summarizing the currently known mechanisms by which acupuncture could delay the progress of CKD and improve symptoms in patients with ESRD. This review help provide a theoretical basis for further research regarding the influence of acupuncture on renal pathology in patients with CKD, as well as the differences between specific therapeutic mechanisms of acupuncture in different renal pathological diagnosis. The evidence in this review indicates that acupuncture may produce marked effects on blocking and reversing the critical risk factors of CKD progression (e.g., hyperglycemia, hypertension, hyperlipidemia, obesity, aging, and anemia) to improve the survival of patients with CKD via mechanisms including oxidative stress inhibition, reducing inflammatory effects, improving hemodynamics, maintaining podocyte structure, and increasing energy metabolism.

A new pathological perspective on thrombotic microangiopathy.

Thrombotic microangiopathy (TMA) refers to a condition caused by microvascular injury that includes thrombosis, hemolytic anemia, and thrombocytopenia. There are two classic TMAs, hemolytic uremic syndrome (HUS) and thrombotic thrombocytopenic purpura, as well as an atypical HUS (aHUS). aHUS includes a broad spectrum of disorders with diverse etiologies and shares clinical manifestations with classic TMA; however, it frequently lacks typical clinical and laboratory findings. These traits can confuse clinicians and pathologists in terms of renal pathologic diagnosis, especially in cases where TMA is associated with other glomerulopathies or hypertensive renal disease. In this review, new paradigms for classifying TMA and the diversity of histopathologic changes including associated renal diseases are discussed. Renal biopsy is an important and useful diagnostic tool for diagnosing TMA and identifying TMA changes in other renal diseases, including hypertension. Adopting the term “TMA features” for TMA-like changes in glomerulus or artery/arteriole in addition to the pathological diagnosis of glomerulopathy would be informative to clinicians for a prompt diagnosis and treatment of aHUS.

Disease spectrum of 9 310 cases of renal biopsy pathological diagnosis from a single center in China.

The pathological types of renal diseases have changed in the past decade, but it lacks large sample analysis in Hunan Province. This study aims to retrospectively analyze the composition characteristics of pathological spectrum of kidney disease in Hunan Province in recent 10 years, compare the changes of pathological types of kidney disease. We collected a total of 9 310 kidney biopsy cases from 2011 to 2020 registered in the kidney biopsy system of the Nephrology Institute of the Second Xiangya Hospital of Central South University. Patients were assigned into a 14-24 years old group, a 25-44 years old group, a 45-59 years old group, and a ≥60 years old group, and divided into 2 time periods, namely 2011-2015 and 2016-2020. Pathological types of renal disease were divided into primary glomerulonephritis (PGN), secondary glomerulonephritis (SGN), tubulo-interstitial nephritis (TIN), hereditary kidney disease, and other pathological types. PGN accounted for 66.93% cases. Among PGN, IgA nephropathy (IgAN) (42.83%), membranous nephropathy (MN) (19.16%), minimal change glomerulopathy (12.46%), and focal segmental glomerulosclerosis (FSGS) (14.97%) were the 4 most common pathological types. Compared with the group in the period of 2011-2015, IgAN (46.74% vs 37.33%) and MN (21.26% vs 16.18%) were increased significantly in years 2016-2020 (both P<0.001). SGN accounted for 24.49% cases, of which lupus nephritis (LN) (26.91%), hypertensive nephropathy (HT) (14.47%), diabetic nephropathy (DN) (12.25%), and henoch-schonlein purpuric nephritis (HSPN) (13.44%) were the 4 most common pathological types. LN (32.53%), HSPN (12.97%), hepatitis B virus associated nephritis (HBVN) (10.98%), HT (9.48%) were the most common SGN in the period of 2011-2015. In the period of 2016-2020, the top 4 pathological types of SGN were LN (23.21%), HT (17.75%), DN (15.84%), and HSPN (13.74%). LN was the most common type in young adults ≤44 years old. HT, DN, and monoclonal immunoglobulin associated renal disease (including amyloidosis nephropathy) became the main pathological types of SGN in middle-aged and elderly patients. IgAN remains the primary pathological type of kidney disease in China in the recent years. The patients with the age of 25-44 years old have the largest proportion of IgAN. With increases in age, the proportion of IgAN gradually decreases. MN increases to different degrees at various ages, while cases of HT, DN, and monoclonal immunoglobulin-related renal damage have increased. This single-center renal pathology spectrum can provide clinical evidence for diagnosis, prevention and epidemiological study.

Schistosoma japonicum infection associated with membranous nephropathy: a case report

BackgroundSchistosomiasis is one of the most contagious parasitic diseases affecting humans; however, glomerular injury is a rare complication mainly described with Schistosoma mansoni infection. We report a case of membranous nephropathy associated with Schistosoma japonicum infection in a Chinese man.Case presentationA 51-year-old Chinese male with a long history of S. japonicum infection presented to the hospital with a slowly progressing severe lower limb edema and foaming urine for over 5 months. Serum S. japonicumantigen test was positive and immunohistochemistry showed that the glomeruli were positive for the antigens. The renal pathologic diagnosis was stage III membranous nephropathy. The patient was treated with glucocorticoid, praziquantel, and an angiotensin-converting enzyme inhibitor. The edema in both lower limbs disappeared within 2 weeks, but his renal function declined progressively and proteinuria persisted after 5 months of therapy.ConclusionsDifferent classes of schistosomal glomerulopathy have completely different clinical manifestation and prognosis. Therefore, efforts should focus on alleviating symptoms, prevention, and early detection. S. japonicumassociated with membranous nephropathy may show a good curative effect and prognosis. However, it is necessary to monitor the renal function in such patients.

Assessment of Cystatin C-Based GFR Estimating Equations as a Novel Reliable Biomarker for Renal Pathology Diagnosis in Patients with Mild to Severe Tubular Affection

Background and Objective: Serum creatinine, a commonly used biomarker in determining glomerular filtration rate (GFR) and chronic kidney disease (CKD) stage, is highly variable biologically and does not rise until > 50% of renal function (RF) impairment occurs. Also, its production is not constant & is affected by many factors as muscle mass, age, inflammation. On the other hand, Cystatin C shows more stable production making it more suitable for assessment of kidney function. Also, It has been shown that the progression of CKD to renal failure, even in glomerular diseases, correlated better with the degree of tubular damage and interstitial fibrosis. So, our aim was to investigate the relation between kidney function assessed by different cystatin (Cys-C)-based estimated glomerular filtration rate (eGFR) in comparison to the gold standard Iohexol (Ioh) based measured (m)GFR in relation to the pathological degree of tubular damage in renal biopsy. To our knowledge, this is the first study that evaluates the relation of (Cys-C)-based eGFR to tubulointerstitial fibrosis in renal biopsy. Methods: This cross-sectional study was performed on 20 CKD cases who attended the Nephrology Department at Ain Shams University, where a renal biopsy was obtained, and individuals were allocated into two groups: group A (GA) with mild tubular affection (TA) and group B (GB) with moderate to severe TA. All participants were referred for measure-ment of GFR using Iohexol (Ioh) together with serum Cys-C level and eGFR was calculated using different Cys-C-based GFR estimating equations, which were further compared using Multivariate Linear Regression and Bland-Altman analyses. Results: Our results revealed a substantial statistical difference among the two studied groups regarding Hb, s creatinine, urea. GB had significantly lower levels for both eGFR and mGFR (82, 93, 115, or 115) ml/min/1.73m2, Vs. GA (200, 123, 162 or 124) ml/min/1.73m2, according to GFR_iohexol, Stevens, Grubb, and CKD_EPI_CYST equations, respectively, p 0.05. A significant correlation between CKD-EPI CYST and mGFR_Iohexol (Ioh) for GA was found (R = 0.601, p = 0.030), where there was a non-substantial relation between any of the used equations and the mGFR in category B (p > 0.05). There was no independent association between the eGFR results and Iohexol clearance. Stevens eGFR had the highest-level bias 33.9 compared with CKD_EPI_CYST (28) and Grubb eGFR (22.85). Conclusion: eGFR by CysC-based equations underestimate GFR in comparison to GFR-iohexol. There is significant correlation between eGFR by CysC-based equations and the gold standard GFR-iohexol only in mild degree of tubular affection and only with CKD-EPI-CYST equation. Stevens equation showed the highest bias while Grubb equation showed the least bias. Although cystatin-based equations have demonstrated a high level of correlation with measured GFR, they are still regarded as imprecise and cannot be established as equal to measured GFR or as a gold standard for GFR estimate.

Cycle-consistent GAN-based stain translation of renal pathology images with glomerulus detection application

Motivation: Renal biopsy is an irreplaceable diagnostic tool for kidney diseases. Glomeruli provide important information for an accurate disease diagnosis. This paper applies deep learning techniques to automate translation of renal pathology images and glomerulus detection to improve the efficiency and accuracy on pathological diagnoses. Methods: This paper first proposes a new method for automatic translation of different renal pathology staining styles using the cycle-consistent Generative Adversarial Network (GAN). This paper then proposes the combination of faster region-based convolutional neural network (R-CNN) with an aspect ratio filter to detect glomeruli in light microscopy images processed with four different stains at various optical magnifications. Finally, this paper improves glomerulus detection at different stains by using translated image stains from the CycleGAN. Results: To show the effectiveness of the translation and detection methods, in addition to quantitative analysis of the results, the involvement of assessment from four physicians is also performed. Experimental results show that the physicians fail to differentiate real and translated stains and the automatic glomerulus detection method outperforms that manually labeled by the physicians. Conclusion: The proposed method works well and improves the efficiency of renal pathological diagnosis. This work contributes in the area of automated medical diagnosis.

P0102A REVIEW OF RENAL BIOPSIES IN A LARGE UK RENAL CENTRE- A 20 YEAR EXPERIENCE

Abstract Background and Aims Percutaneous renal biopsy is the mainstay of renal pathological diagnosis. Not only does it secure an accurate diagnosis, but also lends itself to guiding the prognosis of a myriad of renal disorders. An important diagnostic modality for nephrologists, they have contributed greatly to the field of nephrology, both in terms of the classification of diseases and assisting in understanding their pathogenesis. Adequacy of the tissue samples of at least ten to fifteen glomeruli is generally preferred. The aim of our retrospective study was to review the renal biopsies done in one large UK renal centre, namely Salford Royal Foundation Trust, over the last twenty years. This Trust covers a catchment area that serves approximately 1.5 million people. Method A list of all renal biopsies performed at Salford Royal Foundation Trust between January 2000 to January 2020 was generated by our pathology department. Following this, each individual biopsy report was reviewed. In addition to this, certain information was collated from individual patient records; namely patient demographics, the indication for biopsy, tissue type (native or transplant), histological diagnosis and outcomes. Our centre has an excellent electronic patient record (EPR). This enabled us to analyse full clinical data retrospectively for each case. Results Between January 2000 and January 2020 a total of 3555 renal biopsies were performed at Salford Royal Foundation Trust. These biopsies were performed solely by nephrology specialists and supervised trainees, under ultrasound guidance. 177.5 biopsies were performed on average, per year, ranging between 140 – 203. 90% of biopsies were performed on native kidneys, with 10% being performed on transplanted kidneys. 10% of biopsies had normal histology morphologically when reviewed by light microscopy. There diagnoses of these included entities minimal change disease and thin basement membrane disease most commonly. IgA nephropathy was the most common glomerular pathology identified, in keeping with the wealth of published literature. There were over 525 biopsies done confirming IgAN as the primary pathology. 7% of biopsies had a crescentic glomerular pathology when examined histologically. The main causes included crescentic IgA nephropathy and anca-associated vasculitis. Conclusion Kidney biopsies have long been regarded as safe, minimally invasive procedures are of paramount importance to our diagnostic armamentarium. Our data echoes that of already published pathology series, IgAN being the most common glomerular pathology in our series. We further plan to analyse the various conditions and their outcomes in further detail.

Machine learning in nephrology: scratching the surface.

Machine learning shows enormous potential in facilitating decision-making regarding kidney diseases. With the development of data preservation and processing, as well as the advancement of machine learning algorithms, machine learning is expected to make remarkable breakthroughs in nephrology. Machine learning models have yielded many preliminaries to moderate and several excellent achievements in the fields, including analysis of renal pathological images, diagnosis and prognosis of chronic kidney diseases and acute kidney injury, as well as management of dialysis treatments. However, it is just scratching the surface of the field; at the same time, machine learning and its applications in renal diseases are facing a number of challenges. In this review, we discuss the application status, challenges and future prospects of machine learning in nephrology to help people further understand and improve the capacity for prediction, detection, and care quality in kidney diseases.

Anti-C1q antibodies in lupus nephritis and their correlation with the disease activity.

Systemic lupus erythematosus (SLE) is an autoimmune connective tissue disorder. Renal involvement usually develops in the first few years of illness and should be detected early by periodic urine analysis and quantitation of proteinuria. The aim of our work was to evaluate the biological marker [anti-complement 1q antibodies (anti-C1q Ab)] in lupus nephritis (LN) patients and its correlation to SLE disease activity. Sixty-five subjects were divided into four groups; Group I: SLE patients with LN (proteinuria >0.5 g/day), Group II: SLE patients without LN (all of them had a lupus flares rather than nephritis; active nonrenal), Group III: SLE patients without any activity (inactive disease), and Group IV: Control group. All subjects underwent urine analysis, complete blood picture, liver function tests, kidney function tests, albumin/ creatinine ratio, antinuclear antibody, anti-double stranded DNA (anti-dsDNA) antibody, C3, C4, and anti-C1q Ab. All patients in the first group underwent renal biopsy and pathological diagnosis showed: Class II in two patients, Class III and IV in nine patients, and Class V in four patients. Anti-C1q Ab were found in the serum of SLE patients and not in the control group and showed an association with active lupus with much higher concentration in active renal group, specifically those with severe renal histological lesions (proliferative form). There was significant statistical positive correlation between anti-C1q Ab with anti-dsDNA and SLE disease activity index in both active groups. There was statistically significant negative correlation between anti-C1q Ab with C3 and C4 in both active groups. Anti-C1q Ab could be used as useful marker for active lupus, especially with nephritis.

Utility of Genomic Testing after Renal Biopsy

Background: Renal biopsy is the mainstay of renal pathological diagnosis. Despite sophisticated diagnostic techniques, it is not always possible to make a precise pathological diagnosis. Our aim was to identify a genetic cause of disease in patients who had undergone renal biopsy and determine if genetic testing altered diagnosis or treatment. Methods: Patients with suspected familial kidney disease underwent a variety of next-generation sequencing (NGS) strategies. The subset of these patients who had also undergone native kidney biopsy was identified. Histological specimens were reviewed by a consultant pathologist, and genetic and pathological diagnoses were compared. Results: Seventy-five patients in 47 families underwent genetic sequencing and renal biopsy. Patients were grouped into 5 diagnostic categories based on pathological diagnosis: tubulointerstitial kidney disease (TIKD; n = 18); glomerulonephritis (GN; n = 15); focal segmental glomerulosclerosis and Alport Syndrome (n = 11); thrombotic microangiopathy (TMA; n = 17); and nonspecific pathological changes (n = 14). Thirty-nine patients (52%) in 21 families (45%) received a genetic diagnosis; 13 cases (72%) with TIKD, 4 (27%) with GN, 6 (55%) with focal segmental glomerulosclerosis/Alport syndrome, and 10 (59%) with TMA and 6 cases (43%) with nonspecific features. Genetic testing resulted in changes in understanding of disease mechanism in 21 individuals (54%) in 12 families (57%). Treatment would have been altered in at least 26% of cases (10/39). Conclusions: An accurate genetic diagnosis can result in changes in clinical diagnosis, understanding of pathological mechanism, and treatment. NGS should be considered as a complementary diagnostic technique to kidney biopsy in the evaluation of patients with kidney disease.