Recognition of intraglomerular histological features with deep learning in protocol transplant biopsies and their association with kidney function and prognosis
Ontology highlight
ABSTRACT:
SUBMITTER:
PROVIDER: S-EPMC10873504 | biostudies-literature | 2024 Feb
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The quality assurance provided by preimplantation biopsy quantification of chronic damage may allow greater use of kidneys from expanded criteria donors, and thereby expand the deceased donor pool. Preimplantation biopsy may, however, identify additional acute or chronic pathologies not considered in the scoring of chronic damage, and these may influence the decision to implant or discard the kidney. This single-centre retrospective cohort study of a contemporary UK donor population systematically characterised the nature of additional findings in 1,046 preimplantation and implantation biopsies over an eight-year period. A diverse range of findings were identified in 111/1,046 (11%) organs; most frequently diabetic glomerulopathy, focal segmental glomerulosclerosis, (micro)thrombi, neutrophil casts, and immunoglobulin/complement staining. Seventy (63%) of these were transplanted, with subsequent biopsy in 41 (58%) cases confirming that 80% of the initial acute changes had spontaneously resolved, while there was no progression of diabetic glomerulopathy, and the lesions of focal segmental glomerulosclerosis were not identified. Over 75% of assessable grafts with additional histological findings at the time of transplant showed adequate function at one-year following transplant. In conclusion, most histological abnormalities that may be identified in addition to chronic scarring in preimplantation kidney biopsies would not preclude transplantation nor predict poor graft function.
| S-EPMC11349550 | biostudies-literature
Project description:Interstitial fibrosis, tubular atrophy, and inflammation are major contributors to kidney allograft failure. Here we sought an objective, quantitative pathological assessment of these lesions to improve predictive utility and constructed a deep-learning-based pipeline recognizing normal vs. abnormal kidney tissue compartments and mononuclear leukocyte infiltrates. Periodic acid- Schiff stained slides of transplant biopsies (60 training and 33 testing) were used to quantify pathological lesions specific for interstitium, tubules and mononuclear leukocyte infiltration. The pipeline was applied to the whole slide images from 789 transplant biopsies (478 baseline [pre-implantation] and 311 post-transplant 12-month protocol biopsies) in two independent cohorts (GoCAR: 404 patients, AUSCAD: 212 patients) of transplant recipients to correlate composite lesion features with graft loss. Our model accurately recognized kidney tissue compartments and mononuclear leukocytes. The digital features significantly correlated with revised Banff 2007 scores but were more sensitive to subtle pathological changes below the thresholds in the Banff scores. The Interstitial and Tubular Abnormality Score (ITAS) in baseline samples was highly predictive of one-year graft loss, while a Composite Damage Score in 12-month post-transplant protocol biopsies predicted later graft loss. ITASs and Composite Damage Scores outperformed Banff scores or clinical predictors with superior graft loss prediction accuracy. High/intermediate risk groups stratified by ITASs or Composite Damage Scores also demonstrated significantly higher incidence of estimated glomerular filtration rate decline and subsequent graft damage. Thus, our deep-learning approach accurately detected and quantified pathological lesions from baseline or post-transplant biopsies and demonstrated superior ability for prediction of post-transplant graft loss with potential application as a prevention, risk stratification or monitoring tool.
| S-EPMC10285669 | biostudies-literature
Project description:Here, we retrospectively evaluated the informational yield of 338 post-reperfusion kidney transplant biopsies (including 95 living donations) assessed according to BANFF for the histological characteristics interstitial fibrosis and tubular atrophy (IF/TA), glomerulosclerosis, arteriosclerosis, and acute tubular injury (ATI). Associations with delayed graft function (DGF) and death-censored graft survival were explored through Cox-regression analyses. The maximum follow-up time was 11.4 years, with DGF observed in 108 (32%) cases. After deceased donation there was no association between DGF and histologic parameters. Univariable Cox-regression unveiled an association of IF/TA and glomerulosclerosis with long-term death-censored graft survival (HR per 10% increase: IF/TA 1.63; 95% CI 1.17-2.28; p = 0.003; glomerulosclerosis 1.19; 95% CI 1.01-1.39; p = 0.031). In multivariable Cox regression analyses, adjusted for recognized clinical risk variables like expanded criteria donor-status, donor age, history of diabetes, and HLA-mismatches, only IF/TA maintained association over the total observation period in deceased donations and in the total cohort. Arteriosclerosis and ATI were not associated with clinical outcome after deceased donation. Especially ATI did not affect delayed graft function if only deceased donations were considered. Our data underlines the role of organ quality for transplant outcome prior to acute lesions such as ATI during the transplantation process.
| S-EPMC11744053 | biostudies-literature
Project description:IntroductionStudies are needed to assess the quality of transcriptome analysis in paired human tissue samples preserved by different methods and different gene amplification platforms to enable data comparisons across experimenters.MethodsRNA was extracted from kidney biopsies, either submerged in RNA-stabilizing solution (RSS) or stored in formalin-fixed, paraffin-embedded (FFPE) blocks. RNA quality and integrity were compared. Gene expression of the common rejection module and other immune cell genes were quantified for both tissue preservation methods in the same sample using conventional quantitative polymerase chain reaction (QPCR) by 2 different commercial platforms, (fluidigm [FD]) or barcoded-oligos (nanostring [NS]).ResultsRNA quality was inferior in FFPE tissues. Despite this, gene expression for 19 measured genes on the same sample, stored in FFPE or RSS, were strongly correlated on the FD (r = 0.81) or NS platforms (r = 0.82). For the same samples, interplatform gene expression correlations were excellent (r = 0.80) for RSS and moderate (r = 0.66) for FFPE. Significant differences in gene expression were confirmed on both platforms (FD: P = 1.1E-03; NS: P = 2.5E-04) for biopsy-confirmed acute rejection.ConclusionOur study provided supportive evidence that despite a low RNA quality of archival FFPE kidney transplantation tissue, small quantities of this tissue can be obtained from existing paraffin blocks to provide a viable and rich biospecimen source for focused gene expression assays. In addition, reliable and reproducible gene expression evaluation can be performed on these FFPE tissues using either a QPCR-based or a barcoded-oligo approach, which provides opportunities for collaborative analytics.
| S-EPMC5976814 | biostudies-literature
Project description:Delayed graft function (DGF) is a strong risk factor for development of interstitial fibrosis and tubular atrophy (IFTA) in kidney transplants. Quantitative assessment of inflammatory infiltrates in kidney biopsies of DGF patients can reveal predictive markers for IFTA development. In this study, we combined multiplex tyramide signal amplification (mTSA) and convolutional neural networks (CNNs) to assess the inflammatory microenvironment in kidney biopsies of DGF patients (n = 22) taken at 6 weeks post-transplantation. Patients were stratified for IFTA development (<10% versus ≥10%) from 6 weeks to 6 months post-transplantation, based on histopathological assessment by three kidney pathologists. One mTSA panel was developed for visualization of capillaries, T- and B-lymphocytes and macrophages and a second mTSA panel for T-helper cell and macrophage subsets. The slides were multi spectrally imaged and custom-made python scripts enabled conversion to artificial brightfield whole-slide images (WSI). We used an existing CNN for the detection of lymphocytes with cytoplasmatic staining patterns in immunohistochemistry and developed two new CNNs for the detection of macrophages and nuclear-stained lymphocytes. F1-scores were 0.77 (nuclear-stained lymphocytes), 0.81 (cytoplasmatic-stained lymphocytes), and 0.82 (macrophages) on a test set of artificial brightfield WSI. The CNNs were used to detect inflammatory cells, after which we assessed the peritubular capillary extent, cell density, cell ratios, and cell distance in the two patient groups. In this cohort, distance of macrophages to other immune cells and peritubular capillary extent did not vary significantly at 6 weeks post-transplantation between patient groups. CD163+ cell density was higher in patients with ≥10% IFTA development 6 months post-transplantation (p < 0.05). CD3+CD8-/CD3+CD8+ ratios were higher in patients with <10% IFTA development (p < 0.05). We observed a high correlation between CD163+ and CD4+GATA3+ cell density (R = 0.74, p < 0.001). Our study demonstrates that CNNs can be used to leverage reliable, quantitative results from mTSA-stained, multi spectrally imaged slides of kidney transplant biopsies.
| S-EPMC8292146 | biostudies-literature
Project description:The molecular changes in the parenchyma that reflect disturbances in the function of kidney transplants are unknown. We studied the relationships among histopathology, gene expression, and renal function in 146 human kidney transplant biopsies performed for clinical indications. Impaired function (estimated GFR) correlated with tubular atrophy and fibrosis but not with inflammation or rejection. Functional deterioration before biopsy correlated with inflammation and tubulitis and was greater in cases of rejection. Microarray analysis revealed a correlation between impaired renal function and altered expression of sets of transcripts consistent with tissue injury but not with those consistent with cytotoxic T cell infiltration or IFN-gamma effects. Multivariate analysis of clinical variables, histologic lesions, and transcript sets confirmed that expression of injury-related transcript sets independently correlated with renal function. Analysis of individual genes confirmed that the transcripts with the greatest positive or negative correlations with renal function were those suggestive of response to injury and parenchymal dedifferentiation not inflammation. We defined new sets of genes based on individual transcripts that correlated with renal function, and these highly correlated with the previously developed injury sets and with atrophy and fibrosis. Thus, in biopsies performed for clinical reasons, functional disturbances are reflected in transcriptome changes representing tissue injury and dedifferentiation but not the inflammatory burden.
| S-EPMC2678047 | biostudies-literature
Project description:BackgroundTertiary lymphoid tissues (TLTs) are ectopic lymphoid tissues found in chronically inflamed organs. Although studies have documented TLT formation in transplanted kidneys, the clinical relevance of these TLTs remains controversial. We examined the effects of TLTs on future graft function using our histologic TLT maturity stages and the association between TLTs and Banff pathologic scores. We also analyzed the risk factors for the development of TLTs.MethodsSerial protocol biopsy samples (0 hour, 1, 6, and 12 months) without rejection were retrospectively analyzed from 214 patients who underwent living donor kidney transplantation. TLTs were defined as lymphocyte aggregates with signs of proliferation and their stages were determined by the absence (stage I) or presence (stage II) of follicular dendritic cells.ResultsOnly 4% of patients exhibited TLTs at the 0-hour biopsy. Prevalence increased to almost 50% at the 1-month biopsy, and then slightly further for 12 months. The proportion of advanced stage II TLTs increased gradually, reaching 19% at the 12-month biopsy. Presence of stage II TLTs was associated with higher risk of renal function decline after transplantation compared with patients with no TLT or stage I TLTs. Stage II TLTs were associated with more severe tubulitis and interstitial fibrosis/tubular atrophy at 12 months and predicted poorer graft function independently from the degree of interstitial inflammation. Pretransplantation rituximab treatment dramatically attenuated the development of stage II TLTs.ConclusionsTLTs are commonly found in clinically stable transplanted kidneys. Advanced stage II TLTs are associated with progressive graft dysfunction, independent of interstitial inflammation.
| S-EPMC8763171 | biostudies-literature
Project description:Morphologic examination of tissue biopsies is essential for histopathological diagnosis. However, accurate and scalable cellular quantification in human samples remains challenging. Here, we present a deep learning-based approach for antigen-specific cellular morphometrics in human kidney biopsies, which combines indirect immunofluorescence imaging with U-Net-based architectures for image-to-image translation and dual segmentation tasks, achieving human-level accuracy. In the kidney, podocyte loss represents a hallmark of glomerular injury and can be estimated in diagnostic biopsies. Thus, we profiled over 27,000 podocytes from 110 human samples, including patients with antineutrophil cytoplasmic antibody-associated glomerulonephritis (ANCA-GN), an immune-mediated disease with aggressive glomerular damage and irreversible loss of kidney function. We identified previously unknown morphometric signatures of podocyte depletion in patients with ANCA-GN, which allowed patient classification and, in combination with routine clinical tools, showed potential for risk stratification. Our approach enables robust and scalable molecular morphometric analysis of human tissues, yielding deeper biological insights into the human kidney pathophysiology.
| S-EPMC8119189 | biostudies-literature
Project description:Hepatic steatosis droplet quantification with histology biopsies has high clinical significance for risk stratification and management of patients with fatty liver diseases and in the decision to use donor livers for transplantation. However, pathology reviewing processes, when conducted manually, are subject to a high inter- and intra-reader variability, due to the overwhelmingly large number and significantly varying appearance of steatosis instances. This process is challenging as there is a large number of overlapped steatosis droplets with either missing or weak boundaries. In this study, we propose a deep-learning-based region-boundary integrated network for precise steatosis quantification with whole slide liver histopathology images. The proposed model consists of two sequential steps: a region extraction and a boundary prediction module for foreground regions and steatosis boundary prediction, followed by an integrated prediction map generation. Missing steatosis boundaries are next recovered from the predicted map and assembled from adjacent image patches to generate results for the whole slide histopathology image. The resulting steatosis measures both at the pixel level and steatosis object-level present strong correlation with pathologist annotations, radiology readouts and clinical data. In addition, the segregated steatosis object count is shown as a promising alternative measure to the traditional metrics at the pixel level. These results suggest a high potential of artificial intelligence-assisted technology to enhance liver disease decision support using whole slide images.
| S-EPMC7502534 | biostudies-literature
Project description:Convolutional neural networks (CNNs) are revolutionizing digital pathology by enabling machine learning-based classification of a variety of phenotypes from hematoxylin and eosin (H&E) whole slide images (WSIs), but the interpretation of CNNs remains difficult. Most studies have considered interpretability in a post hoc fashion, e.g. by presenting example regions with strongly predicted class labels. However, such an approach does not explain the biological features that contribute to correct predictions. To address this problem, here we investigate the interpretability of H&E-derived CNN features (the feature weights in the final layer of a transfer-learning-based architecture). While many studies have incorporated CNN features into predictive models, there has been little empirical study of their properties. We show such features can be construed as abstract morphological genes ("mones") with strong independent associations to biological phenotypes. Many mones are specific to individual cancer types, while others are found in multiple cancers especially from related tissue types. We also observe that mone-mone correlations are strong and robustly preserved across related cancers. Importantly, linear mone-based classifiers can very accurately separate 38 distinct classes (19 tumor types and their adjacent normals, AUC = [Formula: see text] for each class prediction), and linear classifiers are also highly effective for universal tumor detection (AUC = [Formula: see text]). This linearity provides evidence that individual mones or correlated mone clusters may be associated with interpretable histopathological features or other patient characteristics. In particular, the statistical similarity of mones to gene expression values allows integrative mone analysis via expression-based bioinformatics approaches. We observe strong correlations between individual mones and individual gene expression values, notably mones associated with collagen gene expression in ovarian cancer. Mone-expression comparisons also indicate that immunoglobulin expression can be identified using mones in colon adenocarcinoma and that immune activity can be identified across multiple cancer types, and we verify these findings by expert histopathological review. Our work demonstrates that mones provide a morphological H&E decomposition that can be effectively associated with diverse phenotypes, analogous to the interpretability of transcription via gene expression values. Our work also demonstrates mones can be interpreted without using a classifier as a proxy.
| S-EPMC9177767 | biostudies-literature