MSMTSeg: Multi-Stained Multi-Tissue Segmentation of Kidney Histology Images via Generative Self-Supervised Meta-Learning Framework.

Accurately diagnosing chronic kidney disease requires pathologists to assess the structure of multiple tissues under different stains, a process that is timeconsuming and labor-intensive. Current AI-based methods for automatic structure assessment, like segmentation, often demand extensive manual annotation and focus on single stain domain. To address these challenges, we introduce MSMTSeg, a generative self-supervised meta-learning framework for multi-stained multi-tissue segmentation in renal biopsy whole slide images (WSIs). MSMTSeg incorporates multiple stain transform models for style translation of inter-stain domains, a self-supervision module for obtaining pre-trained models with the domain-specific feature representation, and a meta-learning strategy that leverages generated virtual data and pre-trained models to learn the domain-invariant feature representation across multiple stains, thereby enhancing segmentation performance. Experimental results demonstrate that MSMTSeg achieves superior and robust performance, with mDSC of 0.836 and mIoU of 0.718 for multiple tissues under different stains, using only one annotated training sample for each stain. Our ablation study confirms the effectiveness of each component, positioning MSMTSeg ahead of classic advanced segmentation networks, recent few-shot segmentation methods, and unsupervised domain adaptation methods. In conclusion, our proposed few-shot cross-domain technology offers a feasible and cost-effective solution for multi-stained renal histology segmentation, providing convenient assistance to pathologists in clinical practice. The source code and conditionally accessible data are available at https://github.com/SnowRain510/MSMTSeg.

Prognostic prediction of idiopathic membranous nephropathy using interpretable machine learning.

BACKGROUND: Established prognostic models of idiopathic membranous nephropathy (IMN) were limited to traditional modeling methods and did not comprehensively consider clinical and pathological patient data. Based on the electronic medical record (EMR) system, machine learning (ML) was used to construct a risk prediction model for the prognosis of IMN. METHODS: Data from 418 patients with IMN were diagnosed by renal biopsy at the Fifth Clinical Medical College of Shanxi Medical University. Fifty-nine medical features of the patients could be obtained from EMR, and prediction models were established based on five ML algorithms. The area under the curve, recall rate, accuracy, and F1 were used to evaluate and compare the performances of the models. Shapley additive explanation (SHAP) was used to explain the results of the best-performing model. RESULTS: One hundred and seventeen patients (28.0%) with IMN experienced adverse events, 28 of them had compound outcomes (ESRD or double serum creatinine (SCr)), and 89 had relapsed. The gradient boosting machine (LightGBM) model had the best performance, with the highest AUC (0.892 ± 0.052, 95% CI 0.840-0.945), accuracy (0.909 ± 0.016), recall (0.741 ± 0.092), precision (0.906 ± 0.027), and F1 (0.905 ± 0.020). Recursive feature elimination with random forest and SHAP plots based on LightGBM showed that anti-phospholipase A2 receptor (anti-PLA2R), immunohistochemical immunoglobulin G4 (IHC IgG4), D-dimer (D-DIMER), triglyceride (TG), serum albumin (ALB), aspartate transaminase (AST), ß2-microglobulin (BMG), SCr, and fasting plasma glucose (FPG) were important risk factors for the prognosis of IMN. Increased risk of adverse events in IMN patients was correlated with high anti-PLA2R and low IHC IgG4. CONCLUSIONS: This study established a risk prediction model for the prognosis of IMN using ML based on clinical and pathological patient data. The LightGBM model may become a tool for personalized management of IMN patients.

Diagnosis of diabetic kidney disease in whole slide images via AI-driven quantification of pathological indicators.

Diagnosis of diabetic kidney disease (DKD) mainly relies on screening the morphological variations and internal lesions of glomeruli from pathological kidney biopsy. The prominent pathological alterations of glomeruli for DKD include glomerular hypertrophy and nodular mesangial sclerosis. However, the qualitative judgment of these alterations is inaccurate and inconstant due to the intra- and inter-subject variability of pathologists. It is necessary to design artificial intelligence (AI) methods for accurate quantification of these pathological alterations and outcome prediction of DKD. In this work, we present an AI-driven framework to quantify the volume of glomeruli and degree of nodular mesangial sclerosis, respectively, based on an instance segmentation module and a novel weakly supervised Macro-Micro Aggregation (MMA) module. Subsequently, we construct classic machine learning models to predict the degree of DKD based on three selected pathological indicators via factor analysis. These corresponding modules are trained and tested on a total of 281 whole slide images (WSIs) digitized from two hospitals with different scanners. Our designed AI framework achieved inspiring results with 0.926 mIoU for glomerulus segmentation, and 0.899 F1 score for glomerulus classification in the external testing dataset. Meantime, the visualized results of the MMA module could reflect the location of the lesions. The performance of predicting disease achieved the F1 score of 0.917, which further proved the effectiveness of our AI-driven quantification of pathological indicators. Additionally, the interpretation of the machine learning model with the SHAP method showed similar accordance with the development of DKD in pathology. In conclusion, the proposed auxiliary diagnostic technologies have the feasibility for quantitative analysis of glomerular pathological tissues and alterations in DKD. Pathological quantitative indicators will also make it more convenient to provide doctors with assistance in clinical practice.

Exploratory metabolomic analysis based on UHPLC-Q-TOF-MS/MS to study hypoxia-reoxygenation energy metabolic alterations in HK-2 cells.

PURPOSE: Renal ischemia-reperfusion injury(IRI)is a major cause of acute kidney injury(AKI), the injury and repair of renal tubular epithelial cells play an important role in the pathological process of IR-AKI. Metabolomics was used to detect cell metabolism alterations and metabolic reprogramming in the initial injury, peak injury, and recovery stage of human renal proximal tubular cells (HK-2 cells) to provide insights into clinical prevention and treatment of IRI-induced AKI. METHODS: An in vitro ischemia-reperfusion (H/R) injury and the recovery model of HK-2 cells were established at different times of hypoxia/reoxygenation. Comprehensive detection of metabolic alterations in HK-2 cells after H/R induction by nontarget metabolomics. Interconversion of glycolysis and fatty acid oxidation (FAO) in HK-2 cells after H/R induction was examined by western blotting and qRT-PCR. RESULTS: Multivariate data analysis found significant differences among the groups, with significant changes in metabolites such as glutamate, malate, aspartate, and L-palmitoylcarnitine. Hypoxia-reoxygenated HK-2 cells are accompanied by altered metabolisms such as disturbance of amino acid and nucleotide metabolism, dysregulation of lipid metabolism, increased glycolysis, and metabolic reprogramming, which manifests as a shift in energy metabolism from FAO to glycolysis. CONCLUSION: The development of IRI-induced AKI in HK-2 cells is accompanied by the disturbance of amino acid, nucleotide, and tricarboxylic acid cycle metabolism and specifically metabolic reprogramming of FAO to glycolytic conversion. The timely recovery of energy metabolism in HK-2 cells is of great significance for treating and prognosis IRI-induced AKI.

A Multifactorial Risk Score System for the Prediction of Diabetic Kidney Disease in Patients with Type 2 Diabetes Mellitus.

Purpose: In-depth investigations of risk factors for the identification of diabetic kidney disease (DKD) in type 2 diabetes mellitus (T2DM) are rare. We aimed to investigate the risk factors for developing DKD from multiple types of clinical data and conduct a comprehensive risk assessment for individuals with diabetes. Methods: We carried out a case-control study, enrolling 958 patients to identify the risk factors for developing DKD in T2DM patients from a database established from inpatient electronic medical records. Multivariable logistic regression was applied to develop a prediction model and the performance of the model was evaluated using the area under the curve (AUC) and calibration curve. A multifactorial risk score system was established according to the Framingham Study risk score. Results: DKD accounted for 34.03% of eligible patients in total. Twelve risk factors were selected in the final prediction model, including age, duration of diabetes, duration of hypertension, fasting blood glucose, fasting C-peptide, insulin use, systolic blood pressure, low-density lipoprotein, γ-glutamyl transpeptidase, platelet, uric acid, and thyroid stimulating hormone; and one protective factor, serum albumin. The prediction model showed an AUC of 0.862 (95% Confidence Interval (CI) 0.834-0.890) with an accuracy of 81.5% in the derivation dataset and an AUC of 0.876 (95% CI 0.825-0.928) in the validation dataset. The calibration curves were excellent and the estimated probability of DKD was more than 80% when the cumulative score for risk factors reached 17 points. Conclusion: Newly recognized risk factors were applied to assess the development of DKD in T2DM patients and the established risk score system was a reliable and feasible tool for assisting clinicians to identify patients at high risk of DKD.

Blockage of TIM-3 relieves lupus nephritis by expanding Treg cells and promoting their suppressive capacity in MRL/lpr mice.

T Cell Immunoglobulin and Mucin Containing Protein-3 (TIM-3) is an important immune checkpoint protein that is expressed in Tregs and affects their function. However, the expression and role of TIM-3 in modulating regulatory T cells (Tregs) in lupus nephritis (LN) are still unknown. In this study, we found that the percentage of TIM-3+ cells among spleen lymphocytes, CD4+ T cells and Tregs was higher in MRL/lpr mice than in MpJ mice. TIM-3high CD4+ T cells and TIM-3high Tregs were mainly responsible for the increase. The percentage of Tregs in TIM-3high CD4+ T cells was lower than that in TIM-3low CD4+ T cells, and the expression of CTLA-4 and IL-10 was lower in TIM-3high Tregs than in the TIM-3low Tregs in MRL/lpr mice. Blockade of TIM-3 in vivo significantly increased the Treg population and the expression of CTLA-4 and IL-10 in Tregs, thus relieving the LN symptoms and pathology in MRL/lpr mice. Additionally, bioinformatics analysis indicated that TIM-3 regulates Treg cells in LN mainly through cytokine-cytokine receptor interactions, the PI3K-Akt signaling pathway, the T cell receptor signaling pathway, Th17 cell differentiation and the FoxO signaling pathway. Together, our study has demonstrated that TIM-3 regulates Tregs in LN and that overexpression of TIM-3 in CD4+ T cells and Tregs leads to Treg quantity and quality deficiency in MRL/lpr mice. Blockade of TIM-3 protects against LN by expanding Tregs and enhancing their suppressive capacity. Finally, TIM-3 might be a potential therapeutic target for the treatment of LN.

Bone marrow inhibition induced by azathioprine in a patient without mutation in the thiopurine S-methyltransferase pathogenic site: A case report.

BACKGROUND: Azathioprine (AZA) and its close analog 6-mercaptopurine are thiopurines widely used in the treatment of patients with cancer, organ transplantation, and autoimmune or inflammatory diseases, including systemic lupus erythematosus. Bone marrow inhibition is a common side effect of AZA, and severe bone marrow inhibition is related to decreased thiopurine S-methyltransferase (TPMT) activity. CASE SUMMARY: We herein report a patient with proliferative lupus nephritis who was using AZA for maintenance therapy, had no common TPMT pathogenic site mutations, and exhibited severe bone marrow inhibition on the 15th day after oral administration. CONCLUSION: This report alerts physicians to the fact that even though the TPMT gene has no common pathogenic site mutation, severe myelosuppression may also occur.

Room-temperature synthesis of amino-functionalized magnetic covalent organic frameworks for efficient extraction of perfluoroalkyl acids in environmental water samples.

The novel amino-functionalized magnetic covalent organic framework nanocomposites (Fe3O4@[NH2]-COFs) were fabricated at room temperature, which were explored as a magnetic adsorbent for magnetic solid-phase extraction (MSPE). On the basis of the hydrophobic surfaces of magnetic nanocomposites and introduction of primary amines into the COFs shell, Fe3O4@[NH2]-COFs displayed excellent enrichment capacity in "catching" ultratrace perfluoroalkyl acids (PFAAs) from water samples because of the synergistic combination of hydrophobic and electrostatic interactions between PFAAs and Fe3O4@[NH2]-COFs. Under the optimized pretreatment and instrumental parameters, the proposed pretreatment approach, which hybridized MSPE using Fe3O4@[NH2]-COFs and HPLC-MS/MS, displayed favorable linearity (10-10,000 ng L-1) with R2 (0.9990-0.9999), low limits of detection (0.05-0.38 ng L-1), and excellent repeatability (3.7-9.2%). Moreover, the established approach was successfully utilized to determine PFAAs in real water samples with spiked recoveries ranging from 72.1% to 115.4%. Results indicated that Fe3O4@[NH2]-COFs would be a potential alternative for MSPE of PFAAs at ultra-low levels.