In Situ Classification of Cell Types in Human Kidney Tissue Using 3D Nuclear Staining

Abstract

To understand the physiology and pathology of disease, capturing the heterogeneity of cell types within their tissue environment is fundamental. In such an endeavor, the human kidney presents a formidable challenge because its complex organizational structure is tightly linked to key physiological functions. Advances in imaging‐based cell classification may be limited by the need to incorporate specific markers that can link classification to function. Multiplex imaging can mitigate these limitations, but requires cumulative incorporation of markers, which may lead to tissue exhaustion. Furthermore, the application of such strategies in large scale 3‐dimensional (3D) imaging is challenging. Here, we propose that 3D nuclear signatures from a DNA stain, DAPI, which could be incorporated in most experimental imaging, can be used for classifying cells in intact human kidney tissue. We developed an unsupervised approach that uses 3D tissue cytometry to generate a large training dataset of nuclei images (NephNuc), where each nucleus is associated with a cell type label. We then devised various supervised machine learning approaches for kidney cell classification and demonstrated that a deep learning approach outperforms classical machine learning or shape‐based classifiers. Specifically, a custom 3D convolutional neural network (NephNet3D) trained on nuclei image volumes achieved a balanced accuracy of 80.26%. Importantly, integrating NephNet3D classification with tissue cytometry allowed in situ visualization of cell type classifications in kidney tissue. In conclusion, we present a tissue cytometry and deep learning approach for in situ classification of cell types in human kidney tissue using only a DNA stain. This methodology is generalizable to other tissues and has potential advantages on tissue economy and non‐exhaustive classification of different cell types.

Label‐free imaging of non‐deparaffinized sections of the human kidney to determine tissue quality and signatures of disease

“…Such an approach allows the performance of tissue cytometry analysis on the tissue using the volumetric tissue exploration and analysis (VTEA) software (Winfree et al, 2017). There are numerous analyses that can be explored with the ability to label nuclei on non‐deparaffinized samples, ranging in complexity from cell count/cell density analysis to machine learning techniques to determine cell types based on the nuclear morphology, as we have previously shown with fresh frozen as well as 4% PFA‐fixed kidney specimens (Woloshuk et al, 2021). By segmenting all the nuclei in the imaging data, the total number of cells present in the tissue section shown in Figure 7a was measured and found to be 11,863 nuclei.…”

Integrated cytometry with machine learning applied to high-content imaging of human kidney tissue for in-situ cell classification and neighborhood analysis

“…To improve data handling the SQL based Java database h2 was also implemented ( Figure S1A ) 30 . Furthermore, additional functionality has been added to VTEA including but not limited to: 1) compatibility with other segmentation and analysis tools, 2) archiving and sharing data 3) generating multiclass training dataset for use in image classification ( Figure S1B ) 23 .…”

“…Image data used in figures 3,4 and 5 or figure 1 and S2 was previously and separately analyzed in Woloshuk et al, 2021 or Winfree et al, 2017 10,23 . The analyses herein are wholly separate and independent of those analyses.…”

Profiling Immune Cells in the Kidney Using Tissue Cytometry and Machine Learning

“…Out of these, the proportion and distribution of immune cells vary depending on the renal area but still likely be in the range of thousands (55). Recently, we investigated whether 3D nuclear staining with 4′,6-diamidino-2phenylindole (DAPI) (64), a nuclear stain commonly used in most fluorescence imaging methods contains enough information for reliable classification of human kidney cells in situ using a supervised learning framework (65). DAPI is commonly used in multiple platforms of research and can be easily performed as part of large-scale 3D imaging.…”