Deep learning-enabled classification of kidney allograft rejection on whole slide histopathologic images.

Background: Diagnosis of kidney transplant rejection currently relies on manual histopathological assessment, which is subjective and susceptible to inter-observer variability, leading to limited reproducibility. We aim to develop a deep learning system for automated assessment of whole-slide images (WSIs) from kidney allograft biopsies to enable detection and subtyping of rejection and to predict the prognosis of rejection. Method: We collected H&E-stained WSIs of kidney allograft biopsies at 400x magnification from January 2015 to September 2023 at two hospitals. These biopsy specimens were classified as T cell-mediated rejection, antibody-mediated rejection, and other lesions based on the consensus reached by two experienced transplant pathologists. To achieve feature extraction, feature aggregation, and global classification, we employed multi-instance learning and common convolution neural networks (CNNs). The performance of the developed models was evaluated using various metrics, including confusion matrix, receiver operating characteristic curves, the area under the curve (AUC), classification map, heat map, and pathologist-machine confrontations. Results: In total, 906 WSIs from 302 kidney allograft biopsies were included for analysis. The model based on multi-instance learning enables detection and subtyping of rejection, named renal rejection artificial intelligence model (RRAIM), with the overall 3-category AUC of 0.798 in the independent test set, which is superior to that of three transplant pathologists under nearly routine assessment conditions. Moreover, the prognosis models accurately predicted graft loss within 1 year following rejection and treatment response for rejection, achieving AUC of 0.936 and 0.756, respectively. Conclusion: We first developed deep-learning models utilizing multi-instance learning for the detection and subtyping of rejection and prediction of rejection prognosis in kidney allograft biopsies. These models performed well and may be useful in assisting the pathological diagnosis.

The impact of donor hepatitis B virus infection on transplant outcomes in deceased donor kidney transplantation recipients.

Background: The use of hepatitis B virus (HBV)-positive donor kidneys to expand the donor pool has been implemented, but limited evidence exists regarding their impact on transplant outcomes. This study aimed to investigate the effects of donor HBV infection on transplant outcomes. Methods: Donor and recipient data between 2015 and 2021 were collected. A total of 743 kidney transplant cases were screened, including 94 donor hepatitis B surface antigen (HBsAg)+/recipient HBsAg- (D+R-) and 649 donor HBsAg-/recipient HBsAg- (D-R-) cases. The analysis endpoints included recipient HBV infection, delayed graft function (DGF), peak estimated glomerular filtration rate (eGFR) within 12 months, recipient survival, and death-censored graft survival (DCGS). Results: The D+R- group had a significantly higher risk of HBV infection compared to the D-R- group (6/72 vs. 3/231; relative risk, 6.4; p = 0.007). The risk of HBV transmission decreased significantly with increasing hepatitis B surface antibody (HBsAb) titer (p for trend = 0.003). Furthermore, the D+R- group did not exhibit an increased risk of DGF compared to the D-R- group (odds ratio, 0.70; p = 0.51) in the multivariable mixed model. Both groups had similar peak eGFR within 12 months (ß = 1.01, p = 0.71), and this had no impact on patient survival (hazard ratio [HR], 0.36; p = 0.10) and DCGS (HR, 0.79, p = 0.59) in the shared-frailty Cox model. Conclusion: The use of HBsAg-positive donor kidneys appears relatively safe for HBV-immunized recipients in the short term. D+R- does not negatively affect graft function recovery and provides comparable posttransplant outcomes. Maintaining an HBsAb titer over 100 IU/L before transplantation is critical to reduce the risk of HBV transmission.

A bibliometric and knowledge-map analysis of antibody-mediated rejection in kidney transplantation.

OBJECTIVES: Antibody-mediated rejection (AMR) is a large obstacle to the long-term survival of allograft kidneys. It is urgent to find novel strategies for its prevention and treatment. Bibliometric analysis is helpful in understanding the directions of one field. Hence, this study aims to analyze the state and emerging trends of AMR in kidney transplantation. METHODS: Literature on AMR in kidney transplantation from 1999 to 2022 was collected from the Web of Science Core Collection. HistCite (version 12.03.17), CiteSpace (version 6.2.R2), Bibliometrix 4.1.0 Package from R language, and Gephi (https://gephi.org) were applied to the bibliometric analysis of the annual publications, leading countries/regions, core journals, references, keywords, and trend topics. RESULTS: A total of 2522 articles related to AMR in kidney transplantation were included in the analysis and the annual publications increased year by year. There were 10874 authors from 118 institutions located in 70 countries/regions contributing to AMR studies, and the United States took the leading position in both articles and citation scores. Halloran PF from Canada made the most contribution to AMR in kidney transplantation. The top 3 productive journals, American Journal of Transplantation, Transplantation, and Transplantation Proceedings, were associated with transplantation. Moreover, the recent trend topics mainly focused on transplant outcomes, survival, and clinical research. CONCLUSIONS: North American and European countries/regions played central roles in AMR of kidney transplantation. Importantly, the prognosis of AMR is the hotspot in the future. Noninvasive strategies like plasma and urine dd-cfDNA may be the most potential direction in the AMR field.

A randomized controlled trial to evaluate efficacy and safety of early conversion to a low-dose calcineurin inhibitor combined with sirolimus in renal transplant patients.

BACKGROUND: The calcineurin inhibitor (CNI)-based immune maintenance regimen that is commonly used after renal transplantation has greatly improved early graft survival after transplantation; however, the long-term prognosis of grafts has not been significantly improved. The nephrotoxicity of CNI drugs is one of the main risk factors for the poor long-term prognosis of grafts. Sirolimus (SRL) has been employed as an immunosuppressant in clinical practice for over 20 years and has been found to have no nephrotoxic effects on grafts. Presently, the regimen and timing of SRL application after renal transplantation vary, and clinical data are scarce. Multicenter prospective randomized controlled studies are particularly rare. This study aims to investigate the effects of early conversion to a low-dose CNI combined with SRL on the long-term prognosis of renal transplantation. METHODS: Patients who receive four weeks of a standard regimen with CNI + mycophenolic acid (MPA) + glucocorticoid after renal transplantation in multiple transplant centers across China will be included in this study. At week 5, after the operation, patients in the experimental group will receive an additional administration of SRL, a reduction in the CNI drug doses, withdrawal of MPA medication, and maintenance of glucocorticoids. In addition, patients in the control group will receive the maintained standard of care. The patients' vital signs, routine blood tests, routine urine tests, blood biochemistry, serum creatinine, BK virus (BKV)/ cytomegalovirus (CMV), and trough concentrations of CNI drugs and SRL at the baseline and weeks 12, 24, 36, 48, 72, and 104 after conversion will be recorded. Patient survival, graft survival, and estimated glomerular filtration rate will be calculated, and concomitant medications and adverse events will also be recorded. CONCLUSION: The study data will be utilized to evaluate the efficacy and safety of early conversion to low-dose CNIs combined with SRL in renal transplant patients. TRIAL REGISTRATION: Chinese Clinical Trial Registry, ChiCTR1800017277.

Redox Metabolism-Associated Molecular Classification of Clear Cell Renal Cell Carcinoma.

Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma. Redox metabolism has been recognized as the hallmark of cancer. But the concrete role of redox-related genes in patient stratification of ccRCC remains unknown. Herein, we aimed to characterize the molecular features of ccRCC based on the redox gene expression profiles from The Cancer Genome Atlas. Differentially expressed redox genes (DERGs) and vital genes in metabolism regulation were identified and analyzed in the ccRCC. Consensus clustering was performed to divide patients into three clusters (C1, C2, and C3) based on 139 redox genes with median FPKM value > 1. We analyzed the correlation of clusters with clinicopathological characteristics, immune infiltration, gene mutation, and response to immunotherapy. Subclass C1 was metabolic active with moderate prognosis and associated with glucose, lipid, and protein metabolism. C2 had intermediate metabolic activity with worse prognosis and correlated with more tumor mutation burden, neoantigen, and aneuploidy, indicating possible drug sensitivities towards immune checkpoint inhibitors. Metabolic exhausted subtype C3 showed high cytolytic activity score, suggesting better prognosis than C1 and C2. Moreover, the qRT-PCR was performed to verify the expression of downregulated DERGs including ALDH6A1, ALDH1L1, GLRX5, ALDH1A3, and GSTM3, and upregulated SHMT1 in ccRCC. Overall, our study provides an insight into the characteristics of molecular classification of ccRCC patients based on redox genes, thereby deepening the understanding of heterogeneity of ccRCC and allowing prediction of prognosis of ccRCC patients.

Donor Death Category Is an Effect Modifier Between Cold Ischemia Time and Post-transplant Graft Function in Deceased-Donor Kidney Transplant Recipients.

Objectives: We aimed to analyze the effect of cold ischemia time (CIT) on post-transplant graft function through mixed-effect model analysis to reduce the bias caused by paired mate kidneys. Methods: We reviewed all kidney transplantation records from 2015 to 2019 at our center. After applying the exclusion criteria, 561 cases were included for analysis. All donor characteristics, preservation and matching information, and recipient characteristics were collected. Transplant outcomes included delayed graft function (DGF) and estimated glomerular filtration rate (eGFR). Generalized linear mixed models were applied for analysis. We also explored potential effect modifiers, namely, donor death category, expanded criteria donors, and donor death causes. Results: Among the 561 cases, 79 DGF recipients developed DGF, and 15 recipients who died after surgery were excluded from the eGFR estimation. The median stable eGFR of the 546 recipients was 60.39 (47.63, 76.97) ml/min/1.73 m2. After adjusting for confounding covariates, CIT had a negative impact on DGF incidence [odds ratio = 1.149 (1.006, 1.313), P = 0.041]. In the evaluation of the impact on eGFR, the regression showed that CIT had no significant correlation with eGFR [ß = -0.287 (-0.625, 0.051), P = 0.096]. When exploring potential effect modifiers, only the death category showed a significant interaction with CIT in the effect on eGFR (P interaction = 0.027). In the donation after brain death (DBD) group, CIT had no significant effect on eGFR [ß = 0.135 (-0.433, 0.702), P = 0.642]. In the donation after circulatory death/donation after brain death followed by circulatory death (DCD/DBCD) group, CIT had a significantly negative effect on eGFR [ß= -0.700 (-1.196, -0.204), P = 0.006]. Compared to a CIT of 0-6 h, a CIT of 6-8 or 8-12 h did not decrease the post-transplant eGFR. CIT over 12 h (12-16 h or over 16 h) significantly decreased eGFR. With the increase in CIT, the regenerated eGFR worsened (P trend = 0.011). Conclusion: Considering the effect of paired mate kidneys, the risk of DGF increased with prolonged CIT. The donor death category was an effect modifier between CIT and eGFR. Prolonged CIT did not reduce the eGFR level in recipients from DBDs but significantly decreased the eGFR in recipients from DCDs/DBCDs. This result indicates the potential biological interaction between CIT and donor death category.

TSC1 Affects the Process of Renal Ischemia-Reperfusion Injury by Controlling Macrophage Polarization.

Renal ischemia-reperfusion injury (IRI) contributes to acute kidney injury (AKI), increases morbidity and mortality, and is a significant risk factor for chronic kidney disease (CKD). Macrophage infiltration is a common feature after renal IRI, and infiltrating macrophages can be polarized into the following two distinct types: M1 macrophages, i.e., classically activated macrophages, which can not only inhibit infection but also accelerate renal injury, and M2 macrophages, i.e., alternatively activated macrophages, which have a repair phenotype that can promote wound healing and subsequent fibrosis. The role of TSC1, which is a negative regulator of mTOR signaling that regulates macrophage polarization in inflammation-linked diseases, has been well documented, but whether TSC1 contributes to macrophage polarization in the process of IRI is still unknown. Here, by using a mouse model of renal ischemia-reperfusion, we found that myeloid cell-specific TSC1 knockout mice (termed Lyz-TSC1 cKO mice) had higher serum creatinine levels, more severe histological damage, and greater proinflammatory cytokine production than wild-type (WT) mice during the early phase after renal ischemia-reperfusion. Furthermore, the Lyz-TSC1 cKO mice showed attenuated renal fibrosis during the repair phase of IRI with decreased levels of M2 markers on macrophages in the operated kidneys, which was further confirmed in a cell model of hypoxia-reoxygenation (H/R) in vitro. Mechanistically, by using RNA sequencing of sorted renal macrophages, we found that the expression of most M1-related genes was upregulated in the Lyz-TSC1 cKO group (Supplemental Table 1) during the early phase. However, C/EBPß and CD206 expression was decreased during the repair phase compared to in the WT group. Overall, our findings demonstrate that the expression of TSC1 in macrophages contributes to the whole process of IRI but serves as an inflammation suppressor during the early phase and a fibrosis promoter during the repair phase.

Single-cell transcriptomics provides new insights into the role of fibroblasts during peritoneal fibrosis.

BACKGROUND: The contributions of various types of cell populations in dialysis-related peritoneal fibrosis are poorly understood. Single-cell RNA sequencing brings single-cell level resolution to the analysis of cellular transcriptomics, which provides a new way to further characterize the distinct roles and functional states of each cell population during peritoneal fibrosis. METHODS: Single-cell transcriptomics from normal peritoneal tissues of six patients, from effluent of patients with short-term peritoneal dialysis (less than 2 weeks, n = 6), and from long-term peritoneal dialysis patients (more than 6 years, n = 4) were analyzed. RESULTS: We identified a distinct cell component between samples among different groups. Functional analysis of the differentially expressed genes identified cell type specific biological processes relevant to different fibrosis stages. Well-known key molecular mechanisms participating in the pathophysiology of peritoneal fibrosis were vitrified, and some of them were found to be restricted to specific cell types. Gradually growing enrichment of PI3K/AKT/mTOR pathway and impairment of oxidative phosphorylation in mesothelial cells and fibroblasts were found from healthy control, short-term dialysis, to long-term dialysis, respectively. The fibroblasts' population obtained from the patients, who received peritoneal dialysis, showed a functional characteristic of immune-chemotaxis and immune response, which was characterized by broadly significant increase in the expression of interleukins, chemokines, cytokines, and human leukocyte antigens. Furthermore, we described the intercellular crosstalk networks based on receptor-ligand interactions, and highlighted a central role of fibroblasts in regulating the key mechanisms of peritoneal fibrosis through crosstalk with other cells. CONCLUSIONS: In summary, despite describing information for fibrogenic molecular mechanisms in the resolution level of individual cell populations, this work identifies the significant functional evolution of fibroblasts during peritoneal fibrosis. This study also reveals the intercellular receptor-ligand interactions in which the fibroblasts serve as a major node, eventually providing new insights into the role of fibroblasts during disease pathogenesis.

Deep Learning Algorithms for the Prediction of Posttransplant Renal Function in Deceased-Donor Kidney Recipients: A Preliminary Study Based on Pretransplant Biopsy.

BACKGROUND: Posttransplant renal function is critically important for kidney transplant recipients. Accurate prediction of graft function would greatly help in deciding acceptance or discard of allocated kidneys. METHODS: : Whole-slide images (WSIs) of H&E-stained donor kidney biopsies at × 200 magnification between January 2015 and December 2019 were collected. The clinical characteristics of each donor and corresponding recipient were retrieved. Graft function was indexed with a stable estimated glomerular filtration rate (eGFR) and reduced graft function (RGF). We used convolutional neural network (CNN)-based models, such as EfficientNet-B5, Inception-V3, and VGG19 for the prediction of these two outcomes. RESULTS: In total, 219 recipients with H&E-stained slides of the donor kidneys were included for analysis [biopsies from standard criteria donor (SCD)/expanded criteria donor (ECD) was 191/28]. The results showed distinct improvements in the prediction performance of the deep learning algorithm plus the clinical characteristics model. The EfficientNet-B5 plus clinical data model showed the lowest mean absolute error (MAE) and root mean square error (RMSE). Compared with the clinical data model, the area under the receiver operating characteristic (ROC) curve (AUC) of the clinical data plus image model for eGFR classification increased from 0.69 to 0.83. In addition, the predictive performance for RGF increased from 0.66 to 0.80. Gradient-weighted class activation mappings (Grad-CAMs) showed that the models localized the areas of the tubules and interstitium near the glomeruli, which were discriminative features for RGF. CONCLUSION: Our results preliminarily show that deep learning for formalin-fixed paraffin-embedded H&E-stained WSIs improves graft function prediction accuracy for deceased-donor kidney transplant recipients.

Carbamylated erythropoietin regulates immune responses and promotes long-term kidney allograft survival through activation of PI3K/AKT signaling.

Modulation of alloimmune responses is critical to improving transplant outcome and promoting long-term graft survival. To determine mechanisms by which a nonhematopoietic erythropoietin (EPO) derivative, carbamylated EPO (CEPO), regulates innate and adaptive immune cells and affects renal allograft survival, we utilized a rat model of fully MHC-mismatched kidney transplantation. CEPO administration markedly extended the survival time of kidney allografts compared with the transplant alone control group. This therapeutic effect was inhibited when the recipients were given LY294002, a selective inhibitor of the phosphoinositide 3-kinase (PI3K)/protein kinase B (AKT) signaling pathway or anti-EPO receptor (EPOR) antibody, in addition to CEPO. In vitro, CEPO inhibited the differentiation and function of dendritic cells and modulated their production of pro-inflammatory and anti-inflammatory cytokines, along with activating the PI3K/AKT signaling pathway and increasing EPOR mRNA and protein expression by these innate immune cells. Moreover, after CD4+ T cells were exposed to CEPO the Th1/Th2 ratio decreased and the regulatory T cell (Treg)/Th17 ratio increased. These effects were abolished by LY294002 or anti-EPOR antibody, suggesting that CEPO regulates immune responses and promotes kidney allograft survival by activating the PI3K/AKT signaling pathway in an EPOR-dependent manner. The immunomodulatory and specific signaling pathway effects of CEPO identified in this study suggest a potential therapeutic approach to promoting kidney transplant survival.

Machine learning for the prediction of severe pneumonia during posttransplant hospitalization in recipients of a deceased-donor kidney transplant.

BACKGROUND: Pneumonia accounts for the majority of infection-related deaths after kidney transplantation. We aimed to build a predictive model based on machine learning for severe pneumonia in recipients of deceased-donor transplants within the perioperative period after surgery. METHODS: We collected the features of kidney transplant recipients and used a tree-based ensemble classification algorithm (Random Forest or AdaBoost) and a nonensemble classifier (support vector machine, Naïve Bayes, or logistic regression) to build the predictive models. We used the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic curve (AUROC) to evaluate the predictive performance via ten-fold cross validation. RESULTS: Five hundred nineteen patients who underwent transplantation from January 2015 to December 2018 were included. Forty-three severe pneumonia episodes (8.3%) occurred during hospitalization after surgery. Significant differences in the recipients' age, diabetes status, HBsAg level, operation time, reoperation, usage of anti-fungal drugs, preoperative albumin and immunoglobulin levels, preoperative pulmonary lesions, and delayed graft function, as well as donor age, were observed between patients with and without severe pneumonia (P<0.05). We screened eight important features correlated with severe pneumonia using the recursive feature elimination method and then constructed a predictive model based on these features. The top three features were preoperative pulmonary lesions, reoperation and recipient age (with importance scores of 0.194, 0.124 and 0.078, respectively). Among the machine learning algorithms described above, the Random Forest algorithm displayed better predictive performance, with a sensitivity of 0.67, specificity of 0.97, positive likelihood ratio of 22.33, negative likelihood ratio of 0.34, AUROC of 0.91, and AUPRC of 0.72. CONCLUSIONS: The Random Forest model is potentially useful for predicting severe pneumonia in kidney transplant recipients. Recipients with a potential preoperative potential pulmonary infection, who are of older age and who require reoperation should be monitored carefully to prevent the occurrence of severe pneumonia.

Elucidating the molecular pathways and immune system transcriptome during ischemia-reperfusion injury in renal transplantation.

Ischemia reperfusion injury (IRI) is a major challenge for renal transplantation. This study was performed to explore the mechanisms and potential molecular targets involved in renal IRI. In this study, the gene datasets GSE43974 and GSE126805 from the Gene Expression Omnibus database, which include ischemic and reperfused renal specimens, were analyzed to determine differentially expressed genes (DEGs). Gene ontology annotations, Kyoto Encyclopedia of Genes and Genomes analysis, and gene set enrichment analysis were performed to determine the pathways that are significantly enriched during ischemia and reperfusion. We also determined the microenvironment cell types xCell and performed correlation analyses to reveal the relationship between the molecular pathways and microenvironment cell infiltration. We found 77 DEGs (76 up- and 1 downregulated) and 323 DEGs (312 up- and 11 downregulated) in the GSE43974 and GSE126805 datasets, respectively. Similar signaling pathway enrichment patterns were observed between the two datasets. The combined analyses demonstrate that the NOD-like receptor signaling pathway and its two downstream signaling pathways, MAPK and NF-kß, are the major significantly enriched pathways. The xCell analysis identified immune cells that are significantly changed after reperfusion, including hematopoietic stem cells, M2 macrophages, monocytes, Treg cells, conventional dendritic cells, and pro B-cells. Enrichment scores of the NOD-like receptor signaling pathway and its downstream pathways during IRI was significantly correlated with the change levels in class-switched memory B-cell and hematopoietic stem cells in both datasets. These data reveal the important role of the NOD-like receptor signaling pathway during IRI, and the close relationship between this pathway and infiltration of specific immune cell types. Our data provide compelling insights into the pathogenesis and potential therapeutic targets for renal IRI.