Integrated Cytometry With Machine Learning Applied to High-Content Imaging of Human Kidney Tissue for In Situ Cell Classification and Neighborhood Analysis

Winfree, Seth; McNutt, Andrew; Khochare, Suraj; Borgard, Tyler J.; Barwinska, Daria; Sabo, Angela R; Ferkowicz, Michael J.; Williams, James C.; Lingeman, James E.; Gulbronson, Connor J.; Kelly, Katherine J.; Sutton, Timothy A.; Dagher, Pierre C.; Eadon, Michael T.; Dunn, Kenneth W.; El‐Achkar, Tarek M.

doi:10.1016/j.labinv.2023.100104

Cited by 6 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar approaches have been useful for other routine histologic stains 30,31 , and tools to support segmentation of routine kidney histology are now accessible online 32 . Another generalized approach uses non-speci c stains for F-actin 9 or nuclear morphology 15 which are correlated with validated cell-type markers to make inferences about cell identity using machine learning. Extensively trained models, such as these, are ideal for common, highly reproducible stains.…”

Section: Discussionmentioning

confidence: 99%

“…There are relatively few techniques [7][8][9] available to extract spatial data from stained kidney tissue that can study 10 4 cells or more per sample, as is routinely achieved with single cell approaches. More commonly, IF analyses require time-consuming scoring or counting procedures or semi-automated thresholding approaches.…”

Section: Introductionmentioning

confidence: 99%

“…Many approaches are available to segment and/or classify biomedical images that emulate manual approaches but, in theory, overcome the time and cost limitations of ROI-based strategies. Despite their potential, these approaches have received only limited attention for studying kidney disease 8,9,15,16 , in part because deploying these techniques across large numbers of samples in a cost-effective fashion is challenging.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High-throughput image analysis with deep learning captures heterogeneity and spatial relationships after kidney injury

McElliott

Al-Suraimi

Telang

et al. 2023

Preprint

View full text Add to dashboard Cite

Recovery from acute kidney injury can vary widely in patients and in animal models. Immunofluorescence staining can provide spatial information about heterogeneous injury responses, but often only a fraction of stained tissue is analyzed. Deep learning can expand analysis to larger areas and sample numbers. Here we report one approach to leverage deep learning tools to quantify heterogenous responses to kidney injury that can be deployed without specialized equipment or programming expertise. We first demonstrated that deep learning models generated from small training sets accurately identified a range of stains and structures with performance similar to that of trained human observers. We then showed this approach accurately tracks the evolution of folic acid induced kidney injury in mice and highlights spatially clustered tubules that fail to repair. We then demonstrated that this approach captures the variation in recovery across a robust sample of kidneys after ischemic injury. Finally, we showed markers of failed repair after ischemic injury were correlated both spatially within and between animals and that failed repair was inversely correlated with peritubular capillary density. Combined, we demonstrate the utility and versatility of our approach to capture spatially heterogenous responses to kidney injury.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High-throughput image analysis with deep learning captures heterogeneity and spatial relationships after kidney injury

McElliott

Al-Suraimi

Telang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

A spatially anchored transcriptomic atlas of the human kidney papilla identifies significant immune injury in patients with stone disease

et al. 2023

View full text Add to dashboard Cite

Kidney stone disease causes significant morbidity and increases health care utilization. In this work, we decipher the cellular and molecular niche of the human renal papilla in patients with calcium oxalate (CaOx) stone disease and healthy subjects. In addition to identifying cell types important in papillary physiology, we characterize collecting duct cell subtypes and an undifferentiated epithelial cell type that was more prevalent in stone patients. Despite the focal nature of mineral deposition in nephrolithiasis, we uncover a global injury signature characterized by immune activation, oxidative stress and extracellular matrix remodeling. We also identify the association of MMP7 and MMP9 expression with stone disease and mineral deposition, respectively. MMP7 and MMP9 are significantly increased in the urine of patients with CaOx stone disease, and their levels correlate with disease activity. Our results define the spatial molecular landscape and specific pathways contributing to stone-mediated injury in the human papilla and identify associated urinary biomarkers.

show abstract

Spatiotemporal immune atlas of a clinical-grade gene-edited pig-to-human kidney xenotransplant

Cheung,

Asiimwe,

Erman

et al. 2024

Nat Commun

View full text Add to dashboard Cite

Pig-to-human xenotransplantation is rapidly approaching the clinical arena; however, it is unclear which immunomodulatory regimens will effectively control human immune responses to pig xenografts. Here, we transplant a gene-edited pig kidney into a brain-dead human recipient on pharmacologic immunosuppression and study the human immune response to the xenograft using spatial transcriptomics and single-cell RNA sequencing. Human immune cells are uncommon in the porcine kidney cortex early after xenotransplantation and consist of primarily myeloid cells. Both the porcine resident macrophages and human infiltrating macrophages express genes consistent with an alternatively activated, anti-inflammatory phenotype. No significant infiltration of human B or T cells into the porcine kidney xenograft is detectable. Altogether, these findings provide proof of concept that conventional pharmacologic immunosuppression may be able to restrict infiltration of human immune cells into the xenograft early after compatible pig-to-human kidney xenotransplantation.

show abstract

Integrated Cytometry With Machine Learning Applied to High-Content Imaging of Human Kidney Tissue for In Situ Cell Classification and Neighborhood Analysis

Cited by 6 publications

References 31 publications

High-throughput image analysis with deep learning captures heterogeneity and spatial relationships after kidney injury

High-throughput image analysis with deep learning captures heterogeneity and spatial relationships after kidney injury

A spatially anchored transcriptomic atlas of the human kidney papilla identifies significant immune injury in patients with stone disease

Spatiotemporal immune atlas of a clinical-grade gene-edited pig-to-human kidney xenotransplant

Contact Info

Product

Resources

About