Identification of rare cell populations in autofluorescence lifetime image data

Abstract

Drug-resistant cells and anti-inflammatory immune cells within tumor masses contribute to tumor aggression, invasion, and worse patient outcomes. These cells can be a small proportion (<10%) of the total cell population of the tumor. Due to their small quantity, the identification of rare cells is challenging with traditional assays. Single cell analysis of autofluorescence images provides a live-cell assay to quantify cellular heterogeneity. Fluorescence intensities and lifetimes of the metabolic coenzymes reduced nicotinamide adenine dinucleotide and oxidized flavin adenine dinucleotide allow quantification of cellular metabolism and provide features for classification of cells with different metabolic phenotypes. In this study, Gaussian distribution modeling and machine learning classification algorithms are used for the identification of rare cells within simulated autofluorescence lifetime image data of a large tumor comprised of tumor cells and T cells. A Random Forest machine learning algorithm achieved an overall accuracy of 95% for the identification of cell type from the simulated optical metabolic imaging data of a heterogeneous tumor of 20,000 cells consisting of 70% drug responsive breast cancer cells, 5% drug resistant breast cancer cells, 20% quiescent T cells and 5% activated T cells. High resolution imaging methods combined with single-cell quantitative analyses allows identification and quantification of rare populations of cells within heterogeneous cultures.

Keywords: NADH; breast cancer; cell analysis; drug response; fluorescence lifetime imaging; heterogeneity; modeling.

FIGURE 1

Representative histograms of OMI features to identify subpopulations within simulated OMI datasets of tumors. NAD(P)H α₁ (A–B) and optical redox ratio (C–D) data of a main population of drug responsive cancer cells (blue) and a subpopulation of either T cells (black) or drug resistant cancer cells (red). The main population consists of 100,000 cells and the subpopulation is 10,000 cells, 10% of the total population [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 2

Number of distinct cell populations identified using Gaussian mixed models within simulated OMI datasets of varying combinations of drug resistant cancer cells, drug responsive cancer cells, and T cells. [A] (top) the smaller population is 5% of the total population, 100,000 total simulated cells. [B] (bottom) the smaller population is 1% of the total population, 100,000 total simulated cells. The red Xs identify models where the proportion error exceeds 5% (false positive). These population and features cannot be counted as successful. The green check indicates the proportion, mean, and standard deviation of each population is identified correctly (less than 5% error. BC = breast cancer [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 3

Normalized mean and standard deviation values in which the model identifies two separate populations. [A] (top) shows the case where the subpopulation is 5% of the total population. [B] (bottom) shows the case where the subpopulation is 1% of the total population [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 4

Confusion matrices show the number of correctly and incorrectly identified cells and tables show the percent accuracy (left, blue) and error (right, orange) for each cell population (cell population details provided in Table S2). The top graph (I) shows the random Forest Model's performance for the train data, (II) shows the test data, (III) shows a blind 4 cell population with 45% responsive cancer cells, 45% resistant cancer cells, 5% quiescent T cells, and 5% activated T cells, (IV) shows a blind 4 cell population with 47.5% responsive cancer cells, 47.5% resistant cancer cells, 2.5% quiescent T cells, and 2.5% activated T cells, (V) shows a blind 4 cell population with 49.5% responsive cancer cells, 49.5% resistant cancer cells, 0.5% quiescent T cells and 0.5% activated T cells, (VI) shows a blind 4 cell population with 70% responsive cancer cells, 5% resistant cancer cells, 20% quiescent T cells, and 5% activated T cells, and (VII) shows the experimental T cell dataset with 47.5% quiescent T cells, and 52.4% activated T cells. BC = breast cancer, Q = quiescent, and a = activated [Color figure can be viewed at wileyonlinelibrary.com]