Tissue Cytometry With Machine Learning in Kidney: From Small Specimens to Big Data

Abstract

Advances in cellular and molecular interrogation of kidney tissue have ushered a new era of understanding the pathogenesis of kidney disease and potentially identifying molecular targets for therapeutic intervention. Classifying cells in situ and identifying subtypes and states induced by injury is a foundational task in this context. High resolution Imaging-based approaches such as large-scale fluorescence 3D imaging offer significant advantages because they allow preservation of tissue architecture and provide a definition of the spatial context of each cell. We recently described the Volumetric Tissue Exploration and Analysis cytometry tool which enables an interactive analysis, quantitation and semiautomated classification of labeled cells in 3D image volumes. We also established and demonstrated an imaging-based classification using deep learning of cells in intact tissue using 3D nuclear staining with 4',6-diamidino-2-phenylindole (DAPI). In this mini-review, we will discuss recent advancements in analyzing 3D imaging of kidney tissue, and how combining machine learning with cytometry is a powerful approach to leverage the depth of content provided by high resolution imaging into a highly informative analytical output. Therefore, imaging a small tissue specimen will yield big scale data that will enable cell classification in a spatial context and provide novel insights on pathological changes induced by kidney disease.

Keywords: 3D imaging; artificial intelligence; cytometry analysis; deep learning; kidney injury.

FIGURE 1

Volumetric Tissue Exploration and Analysis (VTEA) basic workflow. VTEA is a user-friendly platform that allows interactive exploration of image volume (1) where image processing, segmentation, analysis and exploration could occur in a single workspace (2). In the analytical plot, each dot represents a cell with various features. The simplest analysis is in the form of a 2D scatter plot displaying features on the x and y axis (3). Gates can be drawn to chose and quantify a specific population of cells that can be directly visualized in the image volume (4). Conversely, regions of interest can be drawn in the image (5) to locate cells of interest in the scatter plot (6). This process allows for an explorative interplay between the image and the analytical space. Red arrowhead shows different tabs available in the workspace. Figure adapted and used with permission from Winfree et al. (2017b).

FIGURE 2

Unique nuclear staining signatures of various kidney cell types. DAPI staining alone reveals distinct signatures of chromatin condensation states and nuclear morphology of (a) thick ascending limbs (TAL), (b) proximal tubules (PT), (c) collecting ducts (CD), (d) T-cells, (e) neutrophils, (f) eosinophils, and (g) endothelial cells. Scale bar = 5 μm.

FIGURE 3

Agnostic discovery using machine learning and tissue cytometry. Proposed approach to use imaging data of cell nuclei in machine learning workflows that allow non-exhaustive classification of new classes that could be visualized and further analyzed using tissue cytometry. Green arrows point to the two proposed approaches: zero-shot and Bayesian non-exhaustive learning.