Identification of Rare Cell Populations in Autofluorescence Lifetime Image Data

Evaluation of Cellpose segmentation with sequential thresholding for instance segmentation of cytoplasms within autofluorescence images

BACKGROUND

Autofluorescence imaging of the coenzyme, reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H), provides a label-free technique to assess cellular metabolism. Because NAD(P)H is localized in the cytosol and mitochondria, instance segmentation of cell cytoplasms from NAD(P)H images allows quantification of metabolism with cellular resolution. However, accurate cytoplasmic segmentation of autofluorescence images is difficult due to irregular cell shapes and cell clusters.

METHOD

Here, a cytoplasm segmentation method is presented and tested. First, autofluorescence images are segmented into cells via either hand-segmentation or Cellpose, a deep learning-based segmentation method. Then, a cytoplasmic post-processing algorithm (CPPA) is applied for cytoplasmic segmentation. CPPA uses a binarized segmentation image to remove non-segmented pixels from the NAD(P)H image and then applies an intensity-based threshold to identify nuclei regions. Errors at cell edges are removed using a distance transform algorithm. The nucleus mask is then subtracted from the cell segmented image to yield the cytoplasm mask image. CPPA was tested on five NAD(P)H images of three different cell samples, quiescent T cells, activated T cells, and MCF7 cells.

RESULTS

Using POSEA, an evaluation method tailored for instance segmentation, the CPPA yielded F-measure values of 0.89, 0.87, and 0.94 for quiescent T cells, activated T cells, and MCF7 cells, respectively, for cytoplasm identification of hand-segmented cells. CPPA achieved F-measure values of 0.84, 0.74, and 0.72 for Cellpose segmented cells.

CONCLUSION

These results exceed the F-measure value of a comparative cell segmentation method (CellProfiler, ∼0.50-0.60) and support the use of artificial intelligence and post-processing techniques for accurate segmentation of autofluorescence images for single-cell metabolic analyses.

Unlocking the potential of T-cell metabolism reprogramming: Advancing single-cell approaches for precision immunotherapy in tumour immunity

As single-cell RNA sequencing enables the detailed clustering of T-cell subpopulations and facilitates the analysis of T-cell metabolic states and metabolite dynamics, it has gained prominence as the preferred tool for understanding heterogeneous cellular metabolism. Furthermore, the synergistic or inhibitory effects of various metabolic pathways within T cells in the tumour microenvironment are coordinated, and increased activity of specific metabolic pathways generally corresponds to increased functional activity, leading to diverse T-cell behaviours related to the effects of tumour immune cells, which shows the potential of tumour-specific T cells to induce persistent immune responses. A holistic understanding of how metabolic heterogeneity governs the immune function of specific T-cell subsets is key to obtaining field-level insights into immunometabolism. Therefore, exploring the mechanisms underlying the interplay between T-cell metabolism and immune functions will pave the way for precise immunotherapy approaches in the future, which will empower us to explore new methods for combating tumours with enhanced efficacy.

Applications of machine learning in time-domain fluorescence lifetime imaging: a review

Many medical imaging modalities have benefited from recent advances in Machine Learning (ML), specifically in deep learning, such as neural networks. Computers can be trained to investigate and enhance medical imaging methods without using valuable human resources. In recent years, Fluorescence Lifetime Imaging (FLIm) has received increasing attention from the ML community. FLIm goes beyond conventional spectral imaging, providing additional lifetime information, and could lead to optical histopathology supporting real-time diagnostics. However, most current studies do not use the full potential of machine/deep learning models. As a developing image modality, FLIm data are not easily obtainable, which, coupled with an absence of standardisation, is pushing back the research to develop models which could advance automated diagnosis and help promote FLIm. In this paper, we describe recent developments that improve FLIm image quality, specifically time-domain systems, and we summarise sensing, signal-to-noise analysis and the advances in registration and low-level tracking. We review the two main applications of ML for FLIm: lifetime estimation and image analysis through classification and segmentation. We suggest a course of action to improve the quality of ML studies applied to FLIm. Our final goal is to promote FLIm and attract more ML practitioners to explore the potential of lifetime imaging.

Label-free spatially maintained measurements of metabolic phenotypes in cells

Metabolic reprogramming at a cellular level contributes to many diseases including cancer, yet few assays are capable of measuring metabolic pathway usage by individual cells within living samples. Here, autofluorescence lifetime imaging is combined with single-cell segmentation and machine-learning models to predict the metabolic pathway usage of cancer cells. The metabolic activities of MCF7 breast cancer cells and HepG2 liver cancer cells were controlled by growing the cells in culture media with specific substrates and metabolic inhibitors. Fluorescence lifetime images of two endogenous metabolic coenzymes, reduced nicotinamide adenine dinucleotide (NADH) and oxidized flavin adenine dinucleotide (FAD), were acquired by a multi-photon fluorescence lifetime microscope and analyzed at the cellular level. Quantitative changes of NADH and FAD lifetime components were observed for cells using glycolysis, oxidative phosphorylation, and glutaminolysis. Conventional machine learning models trained with the autofluorescence features classified cells as dependent on glycolytic or oxidative metabolism with 90%-92% accuracy. Furthermore, adapting convolutional neural networks to predict cancer cell metabolic perturbations from the autofluorescence lifetime images provided improved performance, 95% accuracy, over traditional models trained via extracted features. Additionally, the model trained with the lifetime features of cancer cells could be transferred to autofluorescence lifetime images of T cells, with a prediction that 80% of activated T cells were glycolytic, and 97% of quiescent T cells were oxidative. In summary, autofluorescence lifetime imaging combined with machine learning models can detect metabolic perturbations between glycolysis and oxidative metabolism of living samples at a cellular level, providing a label-free technology to study cellular metabolism and metabolic heterogeneity.

Comparison of phasor analysis and biexponential decay curve fitting of autofluorescence lifetime imaging data for machine learning prediction of cellular phenotypes

Introduction: Autofluorescence imaging of the coenzymes reduced nicotinamide (phosphate) dinucleotide (NAD(P)H) and oxidized flavin adenine dinucleotide (FAD) provides a label-free method to detect cellular metabolism and phenotypes. Time-domain fluorescence lifetime data can be analyzed by exponential decay fitting to extract fluorescence lifetimes or by a fit-free phasor transformation to compute phasor coordinates. Methods: Here, fluorescence lifetime data analysis by biexponential decay curve fitting is compared with phasor coordinate analysis as input data to machine learning models to predict cell phenotypes. Glycolysis and oxidative phosphorylation of MCF7 breast cancer cells were chemically inhibited with 2-deoxy-d-glucose and sodium cyanide, respectively; and fluorescence lifetime images of NAD(P)H and FAD were obtained using a multiphoton microscope. Results: Machine learning algorithms built from either the extracted lifetime values or phasor coordinates predict MCF7 metabolism with a high accuracy (∼88%). Similarly, fluorescence lifetime images of M0, M1, and M2 macrophages were acquired and analyzed by decay fitting and phasor analysis. Machine learning models trained with features from curve fitting discriminate different macrophage phenotypes with improved performance over models trained using only phasor coordinates. Discussion: Altogether, the results demonstrate that both curve fitting and phasor analysis of autofluorescence lifetime images can be used in machine learning models for classification of cell phenotype from the lifetime data.