Urine Sediment Analysis Research Articles

The Usefulness of Lordosis Load Test and Urinary Biochemistry in the Diagnosis of Orthostatic Proteinuria.

Introduction Renal disease is commonly suspected in patients with proteinuria. Renal biopsy might be considered based on the patient's clinical history and the results of diagnostic tests. However, as orthostatic proteinuria is benign and requires no treatment, it is important to obtain a diagnosis without renal biopsy whenever possible. Therefore, up to now, for the diagnosis of orthostatic proteinuria, in addition to resting urinalysis evaluation (disappearance of proteinuria), we have performed the lordosis load test and urine biochemistry of the samples showing peak proteinuria in a lordosis load test. Method We retrospectively enrolled all patients who visited the pediatric department and underwent the lordosis load test at Kanazawa Medical Center between 2011 and 2020. In the present study, samples with the highest concentrations of protein after the lordosis load test were subjected to general urinary biochemistry and urinary sediment analysis. Patients were followed up with the lordosis load test for several years. Results Enrolled in the study were 68 patients with OP. The mean age at the time of diagnosis was 11.5 years (range, six to 16 years). General urinary tests, urinary sediment, and urinary biochemistry including N-acetyl-beta-D-glucosaminidase (NAG), alpha1-microglobulin(α1MG), and beta 2-microglobulin (β2MG) were normal in all patients with orthostatic proteinuria except one case who was a premature baby. Conclusion If proteinuria disappears after two hours of rest, and urinary biochemistry of the samples showing peak proteinuria in the lordosis load test is normal, orthostatic proteinuria can be diagnosed more accurately.

The Clinical Impact of Urinalysis Screened by Automated Microscopy Compared to Reference Manual Analysis.

Clinical laboratories have replaced conventional manual urine microscopy with automated urinalysis; however, concerns persist regarding its validity in detecting specific elements of urinary sediment crucial for evaluating kidney diseases. This study aimed to assess the accuracy of urinary sediment analysis performed by a large hospital laboratory compared to a standardized microscopic review, focusing on patients both with and without kidney disease. Urine samples were randomly selected from routine laboratory specimens at a university hospital. Laboratory analysis was performed using LabUmat 2 and Urised 3 PRO equipment (Abbott Diagnostics). In the automated analysis, technicians had the option to reclassify urinary sediment elements and, if needed, conduct manual microscopic evaluations to validate findings. The laboratory's analysis was compared with a "reference" analysis, which was double-blinded and conducted by two experienced technicians using bright-field and phase-contrast microscopy. 503 samples were selected, with 52.3% originating from nephrology outpatient clinic patients. Overall agreement between the laboratory results and the reference analysis was 42.1%. The sensitivity (SN) of the laboratory examination for detecting pathological casts, lipiduria, and renal tubular cells was low (<50%), while specificity (SP) was high (>98%). However, for hyaline casts (SN: 50.4%; SP: 80.9%) and dysmorphic red blood cells (SN: 62.3%; SP: 96.2%), accuracy was intermediate. Performance was better for hematuria (SN: 86.1%; SP: 82.3%; ICC: 0.703; R: 0.828) and leukocyturia (SN: 84.9%; SP: 95.1%; ICC: 0.807; R: 0.861). In patients with kidney disease (N=248) and in samples manually reviewed by the laboratory (N=115), accuracy for each urinary element was comparable to the overall sample findings. However, when assessing the ability to identify elements suggestive of nephropathy, only samples manually reviewed by the laboratory showed statistically similar results to those obtained by the reference analysis (p= 0.503, McNemar's test). Employing automated urinalysis seems to be accurate for detecting hematuria and leukocyturia, as well as for screening patients without kidney diseases. However, clinical laboratories attending complex patients should employ personalized strategies to help decide when to perform manual review, thus avoiding misleading urinalysis results.

Diagnostic Utility of Urine Microscopy in Kidney Diseases.

Urine sediment analysis is a highly valuable yet underutilized test in today's advanced medical landscape. The analysis of urine sediment is a simple, cost-effective, and powerful diagnostic tool in the hands of a skilled nephrologist, generally in all kidney diseases and particularly more so in the setting of acute kidney injury (AKI). The impact of AKI is far-reaching and encompasses elevated mortality rates, increased morbidity, longer hospital stays, and higher overall healthcare expenses. Timely and compartmental diagnosis of AKI with the use of a simple urine sediment analysis leads to targeted therapeutic strategies and also serves as a prognostic guide. The widespread use of automated analysis in recent times has its own set of limitations, as it fails to identify pathological casts, crystals, and dysmorphic red blood cells (RBCs). Hence, it is the need of the hour to learn this time-honored art of urine sediment analysis, to provide comprehensive patient care.

#2745 New strategies for capturing undiagnosed chronic kidney disease in patients at risk

Abstract Background and Aims Chronic Kidney Disease (CKD) is recognized as a health problem in the general population. The worldwide incidence of chronic kidney disease (CKD) is increasing, driven by aging populations and a higher prevalence of type 2 diabetes (T2D) and hypertension. The CKD is generally asymptomatic, and the diagnosis depends on the laboratory monitoring of the patients. The KDIGO consensus statement recommend the implementation of screening programs in patients at high risk of CKD development. We present the first results of a sentinel surveillance program of CKD in a healthcare area for detecting undiagnosed CKD in patients at risk. Method Our health department covers the metropolitan area of Valencia, attending 341, 972 citizens through 31 primary care centers. A CKD screening program has been established in this population based on a middleware clinical decision support (CDS) system “CDS-Ripple Down - Abbott Diagnostics” integrated in an electronic request system and in the electronic health records. When a general practitioner doctor order a lab test, the middleware CDS system detects high risk patients for CKD defined by age: >65 to <90, diabetes mellitus, hypertension, or obesity. Automatically, the system adds serum creatinine, estimated glomerular filtration rate (eGFR), urine albumin-to-creatinine ratio (UACR) and urine sediment analysis if it has not been requested (sentinel program). Then, the patients are classified into KDIGO stages based on eGFR and UACR and the CDS system detect those with progression (Fig. 1). Only patients with UACR > 300 mg/g, eGFR < 30 ml/min/1.73, or progression were referred to nephrology. A nephrologist then decides whether patients require a face-to-face visit or provides recommendations to primary care physicians. Results From 01/11/2023 to 31/12/2023, 4, 989 reports were generated by CDS-system corresponding to 122 laboratory test per day. 99, 33% were added by the sentinel program. 3, 970 (79.6%) patients did not have CKD (KDIGO G1-2 or UACR <30 mg/g), 887 (17.8%) patients CKD not suitable for referral to Nephrology (KDIGO 3 and UACR 30-300 mg/g without progression, and 130 (2, 6%) were referred to Nephrology. (Fig. 2) Patients referred to Nephrology had a median age of 79 years [IQR: 72-85], 68 (52, 3%) were women. Twenty-seven patients (20%) were classified as KDIGO G2 A3, 19 (14, 6%) as KDIGO G4 A1 and 18 (13, 8) as KDIGO G2 A2. Fifty-seven patients (43, 8%) have been scheduled to face-to-face at nephrology consultation (1.1% of the total sample), and 73 (56, 1%) have been referred to their primary care doctors with recommendations (1.5% of the total sample). Among the patients referred to Nephrology by the CDS system, the reasons for not scheduling a face-to-face visit in Nephrology were mild decrease in eGFR (n = 18), UACR A2 (n = 24), elderly patients with low Kidney Failure Risk Equation (n = 5), urological pathology (n = 10), dependent patient and/or palliative situation (n = 5) and other causes (n = 11). Conclusion A novel CKD automatic screening method for capturing undiagnosed CKD among patients at risk has been developed. After screening around 5 000 patients at risk in two months, 2.6% of them presented criteria for referral to Nephrology. Only 1.4% required face-to-face visit. If we continue at this screening rate, it is expected that half of our population at risk of developing CKD will have been screened in less than one year. Computer systems with algorithms programmed and improved by a multidisciplinary team can establish a sentinel route (reviewing patients medical records), interpreting analytical values (calculating progressions, KDIGO stages, KFRE risk...) and producing automatic interpretive reports that integrates all the elements of CKD clinical attention allowing us to carry out this population screening.

#1760 Four cases of ADTKD: AFM analysis of urine sediment

Abstract Background and Aims Autosomal Dominant Tubulointerstitial kidney disease (ADTKD) is a rare disease (16 per million), associated with CV events, hypertension, and gout. ADTKD is characterized by interstitial fibrosis, tubular atrophy, microcysts, and progressive CKD. We describe a case of a family with clinical characteristics of ADTKD and provide for the first time a characterization of their urinary sediment. Given the tendency of a specific type of ADTKD caused by UMOD mutation to form tubular crystals, we have also tested the ability of the urine from ADTKD patients to precipitate and form crystals in vitro. Method We examined clinical features and urinary sediment of a family with ADTKD: a 51 years old woman with CKD (eGFR 30 mL/min/1.73 m2, CDK-EPI 2021) and her three sons, a 20 years old male, two daughters of 26 and 24 years old, all with hyperuricemia. Genetic analysis is not yet available. The test of urine precipitation consisted of the analysis of crystals after air-drying a thin layer of urine after enrichment of the organic quota by triple centrifugation for 10 minutes at 1000 rpm. Urinary sediments were also studied by Atomic Force Microscopy (ICSPI nGauge AFM) to achieve a resolution of 20 nm of crystals. Results Clinical data for the four patients are reported in the table. None of the patients showed proteinuria. The urine sediment of all patients showed rare WBC (in greater amounts only in patient 1), rare amorphous granular casts, and rare tubular cells. Three patients showed formations of variably sized crystals in vitro. The precipitation test did not show crystals in patient 1, whereas patients 2-3 showed several rosette-type crystals often with a wagon-wheel concentric contour which resembled leucine crystals or CaCO3. Adding formalin to the samples resulted in a more clear organization of crystals in wagon-wheel structures. AFM imaging of the crystals showed rod-like structures branching with an angle of 35°. Conclusion ADTKD remains a poorly understood genetic condition with no specific treatment options. Our data suggest that patients with this condition may have an enhanced tendency to form crystals in vitro. Speculatively, this might induce tubular injury in vivo. Data from UMOD-ko animal models showed intrarenal crystals (not better specified). Genetic alterations of branched aminoacids metabolism (such as leucine in Maple syrup disease) can also cause tubular diseases, although the systemic manifestations are very different from our patients. Genetic analysis of our family will give further information on the proteins involved in these crystal structures.

Correlation of Blood Creatinine Levels with The Result of Urine Sediment Analysis in Chronic Kidney Failure Patient

Chronic Kidney Failure is a condition caused by a gradual and chronic decline in kidney function. This situation can affect to creatinine levels. Creatinine is the result of endogenous metabolism that is useful for assessing glomerular function, in the event of renal dysfunction then the filtration ability of creatinine will be reduced and serum creatinine will increase. Urine sediment is produced from the results of urine concentration consisting of calcium salts. This concentrated urine comes from the kidneys with a variety of causes, one of which is chronic kidney failure, flows through the ureter to the bladder and continues to the urethra until the urethral. Objective: To find out the correlation of blood creatinine levels with the results of urine sediment analysis in patients with chronic kidney failure. Method: This research is observational analytical with a cross sectional approach to determine the correlation between independent and dependent variables. The sample is taken purposive sampling by selecting a sample based on certain criteria. The collected data is then analyzed using Spearman statistical tests. Results: Examination of creatinine levels in chronic kidney failure patients obtained 6.67 mg/dl. The average urine sediment found erythrocytes as many 2-3/HPF to many/HPF. Conclusion: There is a correlation of blood creatinine levels with the results of urine sediment analysis in patients with chronic kidney failure.

Evaluating the State of Glomerular Disease by Analyzing Urinary Sediments: mRNA Levels and Immunofluorescence Staining for Various Markers.

Renal biopsy is the gold standard for making the final diagnosis and for predicting the progression of renal disease, but monitoring disease status by performing biopsies repeatedly is impossible because it is an invasive procedure. Urine tests are non-invasive and may reflect the general condition of the whole kidney better than renal biopsy results. We therefore investigated the diagnostic value of extensive urinary sediment analysis by immunofluorescence staining for markers expressed on kidney-derived cells (cytokeratin: marker for tubular epithelial cells, synaptopodin: marker for podocytes, claudin1: marker for parietal epithelial cells, CD68: marker for macrophages (MΦ), neutrophil elastase: marker for neutrophils). We further examined the expression levels of the mRNAs for these markers by real-time reverse transcription polymerase chain reaction. We also examined the levels of mRNAs associated with the M1 (iNOS, IL-6) and M2 (CD163, CD204, CD206, IL-10) MΦ phenotypes. Evaluated markers were compared with clinical and histological findings for the assessment of renal diseases. Claudin1- and CD68-positive cell counts in urinary sediments were higher in patients with glomerular crescents (especially cellular crescents) than in patients without crescents. The relative levels of mRNA for CD68 and the M2 MΦ markers (CD163, CD204, CD206, and IL-10) in urinary sediments were also higher in patients with glomerular crescents. These data suggest that immunofluorescence staining for claudin1 and CD68 in urinary sediments and the relative levels of mRNA for CD68 and M2 MΦ markers in urinary sediments are useful for evaluating the state of glomerular diseases.

Comparative study of urine erythrocyte detection by urine dry chemical analyzer, urine sediment analyzer and microscope

Comparative study of urine erythrocyte detection by urine dry chemical analyzer, urine sediment analyzer and microscope

Amoxicillin overdose in the pediatric emergency department: A descriptive study

ObjectiveTo describe the characteristics of pediatric patients treated in the emergency department due to amoxicillin overdosing. MethodA retrospective single-center observational study was conducted on patients aged 0 to 16 years treated in a pediatric emergency department due to amoxicillin overdosing between 2011 and 2021. Epidemiological and anthropometric data was collected as well as information on the circumstances of overdosing, clinical manifestations, emergency department management, and discharge destination. ResultsThe study comprised 15 patients, 66.6% of them male, with a median age of 3.8 years (interquartile range: 1.9). The most frequent cause of overdosing was accidental ingestion (8/15; 53.3%). Amoxicillin was mainly ingested in liquid form, except for one case with autolytic attempt, where it was ingested in the form of tablets. Eighty percent of subjects (12/15) received a single dose of the drug. The median time to presentation to emergency department was 2.1 hours from ingestion (interquartile range: 2.7) and the median dose of amoxicillin was 219 mg/kg/dose (interquartile range: 148). All patients were asymptomatic, with a normal physical examination. Blood tests were performed in 7 patients (46.6%) and urinary sediment analysis in 2 (13.3%), all of them without alterations. Activated charcoal was administered to 5 (33.3%), patients with a median time to administration of one hour (interquartile range: 1.2). All patients were discharged to their homes. Eleven cases (73.3%) required withdrawal of amoxicillin. ConclusionsAmoxicillin overdosing in this study did not appear to result in adverse effects, despite the fact that the recommended doses were significantly exceeded.

Swin-LBP: a competitive feature engineering model for urine sediment classification

Automated urine sediment analysis has become an essential part of diagnosing, monitoring, and treating various diseases that affect the urinary tract and kidneys. However, manual analysis of urine sediment is time-consuming and prone to human bias, and hence there is a need for an automated urine sediment analysis systems using machine learning algorithms. In this work, we propose Swin-LBP, a handcrafted urine sediment classification model using the Swin transformer architecture and local binary pattern (LBP) technique to achieve high classification performance. The Swin-LBP model comprises five phases: preprocessing of input images using shifted windows-based patch division, six-layered LBP-based feature extraction, neighborhood component analysis-based feature selection, support vector machine-based calculation of six predicted vectors, and mode function-based majority voting of the six predicted vectors to generate four additional voted vectors. Our newly reconstructed urine sediment image dataset, consisting of 7 distinct classes, was utilized for training and testing our model. Our proposed model has several advantages over existing automated urinalysis systems. Firstly, we used a feature engineering model that enables high classification performance with linear complexity. This means that it can provide accurate results quickly and efficiently, making it an attractive alternative to time-consuming and biased manual urine sediment analysis. Additionally, our model outperformed existing deep learning models developed on the same source urine sediment image dataset, indicating its superiority in urine sediment classification. Our model achieved 92.60% accuracy for 7-class urine sediment classification, with an average precision of 92.05%. These results demonstrate that the proposed Swin-LBP model can provide a reliable and efficient solution for the diagnosis, surveillance, and therapeutic monitoring of various diseases affecting the kidneys and urinary tract. The proposed model's accuracy, speed, and efficiency make it an attractive option for clinical laboratories and healthcare facilities. In conclusion, the Swin-LBP model has the potential to revolutionize urine sediment analysis and improve patient outcomes in the diagnosis and treatment of urinary tract and kidney diseases.

Comparison of the clinical performance of the Atyp.C parameter of the UF-5000 fully automated urine particle analyzer with that of microscopic urine sediment analysis

a) ObjectivesUrinalysis is one of the most common laboratory screening tests to detect problems in the renal and urinary system; however, they cannot detect atypical cells (Atyp.Cs). The Sysmex UF-5000, a fully automated urine particle analyzer, can detect Atyp.Cs via its Atyp.C parameter. This study aimed to compare the clinical value of the Atyp.C parameter with that of urine sediment microscopy. b) MethodA total of 471 leftover urine samples were submitted to the Department of Clinical Laboratory at the University of Tokyo Hospital for urinalysis by manual sediment microscopy examination and UF-5000 Atyp.C analysis. c) ResultOf 471 submitted samples, 117 were positive for Atyp.Cs by urine sediment and 354 samples were negative. The histological subtypes of the Atyp.Cs included 105 cases of suspected urothelial carcinoma cells, 10 suspected squamous carcinoma cells, and 2 of suspected adenocarcinoma cells. The Atyp.C values for the Atyp.C-positive and -negative groups were 2.64 ± 0.69 and 0.38 ± 0.16, respectively. The optimal Atyp.C cutoff value determined by the receiver operating characteristic curve analysis was 0.4/μL. The area under the curve was 0.856, with a sensitivity of 79.5% and specificity of 85.1%. Atyp.C values of the UF-5000 showed high predictive performance for Atyp.C-positive specimens identified by urine sediment microscopy. d) ConclusionsThis study shows that a combination of UF-5000 analysis and microscopic examination of urine sediment improves Atyp.C detection in urine sediment analysis. These results suggest that Atyp.C measured by UF-5000 could be a useful screening parameter in routine testing of urine samples.

Urine CXCL10 to Assess BK Polyomavirus Replication After Kidney Transplantation.

Urine CXCL10 is a biomarker for renal allograft inflammation induced by rejection, urinary tract infection, or BK polyomavirus (BKPyV) replication. This study aimed to compare urine CXCL10 levels in different stages of BKPyV reactivation and to investigate urine CXCL10 as a biomarker for BKPyV replication. We included 763 urine samples (235 patients) from an interventional, randomized trial obtained in the context of regular screening for urine CXCL10 levels. All urine samples had a complete urine sediment analysis, no rejection episode noted within 30 d before urine collection, and a urine decoy cell analysis was conducted within ±3 d. Urine CXCL10 levels were 2.31 ng/mmol in samples without BKPyV viruria, slightly rose to 4.35 ng/mmol with BKPyV viruria, and then markedly increased to 16.42 ng/mmol when decoy cells were detectable, but still in the absence of BKPyV DNAemia ( P < 0.001). The highest urine CXCL10 values were observed in samples with BKPyV DNAemia (median 42.59 ng/mmol). The area under the curve of urine CXCL10 levels to detect ≥3 decoy cells was 0.816. At a CXCL10 cutoff of 3 ng/mmol, the negative predictive value was 97%. The area under the curve of urine CXCL10 levels to detect BKPyV DNAemia was 0.882, with a negative predictive value of 99% at a CXCL10 cutoff of 3 ng/mmol. Urine CXCL10 levels are already significantly elevated in BKPyV viruria (especially with decoy cell shedding) and further increase with BKPyV DNAemia. Low urine CXCL10 values can rule out the presence of ≥3 decoy cells and BKPyV DNAemia with high certainty.

Urinary isomorphic red blood cells for the prediction of disease severity and renal outcomes in MPO-ANCA-associated vasculitis: a retrospective cohort study.

Hematuria is common in myeloperoxidaseanti-neutrophil cytoplasmic antibodyassociated vasculitis(ANCA-MPO). Previous studies have mainly focused on urinary dysmorphic red blood cells and few have reported the clinical significance of isomorphic urinaryred blood cells. Therefore, the main aim of this study was to assess the predictive yield of urinary isomorphic red blood cells for disease severity and renal outcomes in patients with ANCA-MPO associated vasculitis. A total of 191 patients with ANCA-MPOassociated vasculitiswith hematuria were retrospectively selectedand were divided into two groups (withisomorphic red blood cells versus dysmorphic red blood cells) according to the percentage of isomorphic red blood cells on urinary sediment analysis. Clinical, biological and pathological data at diagnosis were compared. Patients were followed up for a median of 25months and progression to end-stage kidneydisease and death were regarded as main outcome events. Additionally, univariate and multivariate Cox regression models were used to estimate the risk factors for end-stage kidneydisease. Out of 191 patients, 115 (60%) had ≥ 70% and 76 (40%) had < 30% urine isomorphic red blood cells. Compared with patients in the dysmorphic red blood cell group, patients in the isomorphic red blood cell group had a significantly lower estimated glomerular filtration rate(eGFR) [10.41mL/min (IQR 5.84-17.06) versus 12.53 (6.81-29.26); P = 0.026], higher Birmingham Vasculitis Activity Score [16 (IQR 12-18) versus 14 (10-18); P = 0.005] and more oftenreceived plasma exchange [40.0% versus 23.7% (P = 0.019)] at diagnosis. Kidney biopsies revealed a higher proportion of patients with glomerular basement membrane fracture in the isomorphic red blood cell group [46.3% versus 22.9% (P = 0.033)]. Furthermore, patients with predominant urinary isomorphic red blood cells were more likely to progress to end-stage kidney disease [63.5% versus 47.4% (P = 0.028)] and had a higher risk ofdeath [31.3% versus 19.7% (P = 0.077)]. The end-stage kidney disease-free survival was lower in patients in the isomorphic red blood cell group (P = 0.024). However, urine isomorphic red blood cells ≥ 70% could not predict the presence of end-stage kidney disease in multivariate Cox analysis. Myeloperoxidase-anti-neutrophil cytoplasmic antibodyassociated vasculitis patients with predominant urinary isomorphic red blood cells at diagnosis had more severe clinical manifestations and a higher risk of poor renal outcomes. In this respect, urinary isomorphic red blood cells could be viewed as a promising biomarker of ANCA_MPO vasculitisseverity and progression.

Evaluation of automated microscopy sediment analysis in urinary tract infection screening: a practical insight in adjusting fixed cut-off values for urine culture

PurposeThe aim of our study was to evaluate a procedure in which urine culture was only being performed based on fixed cut-off values of urine sediment analysis with intention to prevent unnecessary negative urine cultures.MethodsFrom January 2018 to August 2018, all urine samples from patients visiting the urology outpatient department were analyzed. Urine culture was only performed if urine sediment contained more than 130 bacteria per microliter and/or more than 50 leukocytes per microliter.ResultsIn total, 2821 urine cultures with accompanying urine sediments were analyzed. 2098 cultures (74.4%) were defined negative and 723 (25.6%) positive. By adjusting cut-off values of sediment analysis > 20 per microliter or bacteria more than 330 per microliter, 1051 cultures would have been saved with an estimated cost reduction of € 31.470. Eleven clinically relevant urine cultures would have been missed (1%).ConclusionUsing cut-offs values leads to a notable decrease of the total number of urine cultures. According to our analysis, adjusting cut-off values could result in 37% less urine cultures and almost 50% less negative cultures. Hereby, unnecessary cost can be prevented [in our department estimated €31.470 in eight months (€ 47.205/year)].

The Importance of Urine Sediment Analysis in the Diagnosis and Management of Acute Kidney Injury

The Urine sediment analysis is an extremely valuable yet underutilized test. Our case discussion aims to highlight its diagnostic value and emphasize the role of physicians in the performance of the test as diagnosis and management strategies may differ, leading to clinical improvement and more specific therapeutic interventions.

Automated Urine Cell Image Classification Model Using Chaotic Mixer Deep Feature Extraction.

Microscopic examination of urinary sediments is a common laboratory procedure. Automated image-based classification of urinary sediments can reduce analysis time and costs. Inspired by cryptographic mixing protocols and computer vision, we developed an image classification model that combines a novel Arnold Cat Map (ACM)- and fixed-size patch-based mixer algorithm with transfer learning for deep feature extraction. Our study dataset comprised 6,687 urinary sediment images belonging to seven classes: Cast, Crystal, Epithelia, Epithelial nuclei, Erythrocyte, Leukocyte, and Mycete. The developed model consists of four layers: (1) an ACM-based mixer to generate mixed images from resized 224 ×224 input images using fixed-size 16 ×16 patches; (2) DenseNet201 pre-trained on ImageNet1K to extract 1,920 features from each raw input image, and its six corresponding mixed images were concatenated to form a final feature vector of length 13,440; (3) iterative neighborhood component analysis to select the most discriminative feature vector of optimal length 342, determined using a k-nearest neighbor (kNN)-based loss function calculator; and (4) shallow kNN-based classification with ten-fold cross-validation. Our model achieved 98.52% overall accuracy for seven-class classification, outperforming published models for urinary cell and sediment analysis. We demonstrated the feasibility and accuracy of deep feature engineering using an ACM-based mixer algorithm for image preprocessing combined with pre-trained DenseNet201 for feature extraction. The classification model was both demonstrably accurate and computationally lightweight, making it ready for implementation in real-world image-based urine sediment analysis applications.

Analytical performance evaluation of two automated urine sediment analysers using two levels of commercially available quality control material.

Evaluate the in-clinic performance of point-of-care sediment analysers, Analyzer V (Vetscan SA, Abaxis) and Analyzer S (SediVue DX, IDEXX), using assayed, bilevel (2 concentrations) urine quality control material to determine if instrument specifications are acceptable for semi-quantitative clinical urine sediment analysis. Accuracy, precision and clinical utility of Analyzer V and Analyzer S measurements were evaluated using a bilevel, assayed quality control material in 23 veterinary practices. Photomicrographs taken by the instruments facilitated manual review and quality assessment. Analyzer V and Analyzer S under-identified the presence of cystine crystals with 83 and 13% inaccuracy in the positive quality control material, respectively. Analyzer V and Analyzer S over-reported bacteria in the sterile quality control material with 82 and 94% specificity, respectively. Analyzer V and Analyzer S reported RBCs and WBCs within manufacturer specifications with excellent sensitivity (93 to 100%) and specificity (100%). Additional improvement is needed to better classify crystal types and reduce false positives for bacteria before clinical use. While normal samples can generally be trusted, a manual review of abnormal samples is required to ensure that clinically important urine components are correctly evaluated. Future studies should evaluate the performance of these instruments with species-specific urine sediment.

An Image Recognition Method for Urine Sediment Based on Semi-supervised Learning

Because there are many categories, large morphological differences and few labels of urinary sediment components, and uneven data in urine sediment images recognition, the accuracy and recall rate of the existing urine sediment images recognition methods are not ideal. The main purpose of this paper is to improve the accuracy and recall of urine sediment image recognition by proposing a urine sediment image classification method based on semi-supervised learning. This paper proposes a method based on semi-supervised learning to classify urine sediment images. This algorithm designs a re-parameterization network (US-RepNet) for low-resolution urine sediment microscopic images to extract complex features of urine sediment images. The dual attention module is introduced on Us-RepNet to increase the extraction of fine-grained features from urine sediment images. And the cross-entropy loss (C.E. loss) function is optimized to train an unbiased classifier to improve long-tailed distribution image classification. The experimental results show that the accuracy of proposed method can reach 94% with only a small amount of labeled data for 16 types of urine sediment images under long-tail distribution. The algorithm can recognize most types, and reduces the need for labeled information, while achieving excellent recognition and classification performance. Comprehensive analysis shows that it can be used as a practical reference for urine sediment analysis. • Re-parameterization network is used to recognize low-resolution microscopic images. • Re-parameterization network can effectively extract the features of urine sediment images. • CSAM increases the extraction of fine-grained features. • Unbiased classifier is trained under the improved C.E. loss function.

Calcium salt crystalluria in a captive chimpanzee (Pantroglodytes) population.

Urinalysis is a rapid, non-invasive method used to obtain diagnostic information on primates. While several studies have investigated dipstick and specific gravity values in chimpanzees, urine sediment analysis is often excluded. Crystalluria, observed during urine sediment analysis, can be benign or indicate renal pathologies. In total, 665 urine samples from sanctuary-housed chimpanzees were analyzed over the course of 17 months for pH, specific gravity, time of collection, and crystalluria. Calcium salt crystalluria was seen in 9.0% of the samples from 23.7% of the individuals in the study. Urinary pH and specific gravity were significantly higher in samples with crystalluria than in those lacking crystalluria, while time of collection did not differ between the two groups. While diet is the most likely cause of the crystalluria in this population, several medications could also cause urinary crystallization. Further exploration of the significance of calcium salt crystalluria in chimpanzees is warranted.

Urine Sediment Examination: Comparison Between Laboratory-Performed Versus Nephrologist-Performed Microscopy and Accuracy in Predicting Pathologic Diagnosis in Patients with Acute Kidney Injury.

Automated urine technology is becoming standard for urinalysis microscopy. We sought to compare the urine sediment analysis performed by nephrologist to the analysis performed by the laboratory. When available, we also compared the suggested diagnosis per nephrologists' sediment analysis to the biopsy diagnosis. We identified patients with AKI that had urine microscopy with sediment analysis performed by the laboratory (Laboratory-UrSA) and by a nephrologist (Nephrologist-UrSA) within 72 hours of each other. We collected data to determine the following: number of RBCs and WBCs per HPF, presence and type of casts per LPF, and presence of dysmorphic RBCs. We evaluated agreement between the Laboratory-UrSA and the Nephrologist-UrSA using cross tabulation and Kappa statistic. When available, we categorized the nephrologist sediment findings into four categories: (1) bland, (2) suggestive of acute tubular injury (ATI), (3) suggestive of glomerulonephritis (GN), and (4) suggestive of acute interstitial nephritis (AIN). In a group of patients with kidney biopsy within thirty days of the Nephrologist-UrSA, we assessed agreement between the nephrologist diagnosis and the biopsy diagnosis. We included 387 patients with both Laboratory-UrSA and Nephrologist-UrSA. The agreement was moderate for presence of RBCs (Kappa 0.46, 95% CI: 0.37, 0.55), fair for WBCs (Kappa 0.36, 95% CI: 0.27, 0.45). There was no agreement for casts (Kappa 0.026, 95% CI: -0.04, 0.07). Eighteen dysmorphic RBCs were detected on Nephrologist-UrSA compared to zero on Laboratory-UrSA. Among the 33 patients with kidney biopsy, 100% ATI and 100% GN suggested per Nephrologist-UrSA were confirmed on the biopsy. Of the 5 patients with bland sediment on the Nephrologist-UrSA, 40% showed ATI pathologically while the other 60% demonstrated GN. A nephrologist is more likely to recognize the presence of pathologic casts and dysmorphic RBCs. Correct identification of these casts carries important diagnostic and prognostic value when evaluating kidney disease.