Phasor analysis of NADH FLIM identifies pharmacological disruptions to mitochondrial metabolic processes in the rodent cerebral cortex

Abstract

Investigating cerebral metabolism in vivo at a microscopic level is essential for understanding brain function and its pathological alterations. The intricate signaling and metabolic dynamics between neurons, glia, and microvasculature requires much more detailed understanding to better comprehend the mechanisms governing brain function and its disease-related changes. We recently demonstrated that pharmacologically-induced alterations to different steps of cerebral metabolism can be distinguished utilizing 2-photon fluorescence lifetime imaging of endogenous reduced nicotinamide adenine dinucleotide (NADH) fluorescence in vivo. Here, we evaluate the ability of the phasor analysis method to identify these pharmacological metabolic alterations and compare the method's performance with more conventional nonlinear curve-fitting analysis. Visualization of phasor data, both at the fundamental laser repetition frequency and its second harmonic, enables resolution of pharmacologically-induced alterations to mitochondrial metabolic processes from baseline cerebral metabolism. Compared to our previous classification models based on nonlinear curve-fitting, phasor-based models required fewer parameters and yielded comparable or improved classification accuracy. Fluorescence lifetime imaging of NADH and phasor analysis shows utility for detecting metabolic alterations and will lead to a deeper understanding of cerebral energetics and its pathological changes.

Fig 1

(a-d) Representative fluorescence intensity images of (a,b) endogenous NADH fluorescence and (c,d) the topically-applied astrocyte label sulforhodamine 101 in the anesthetized rat cerebral cortex. Imaging was performed (a,c) before and (b,d) after BMI-induced focal seizure activity, Scale bar: 50 μm (e) Time-resolved fluorescence decays for NADH in solution (teal) and (red) in the rat cortex before pharmacological inhibition and after KCN (blue) administration. Fluorescence decays were measured at each pixel in the images and used for phasor computations. (f) Corresponding phasor contour representations of the same data, with peak phasor coordinates listed. Colored circles indicate previously-computed lifetime values of cortical NADH. Solid arrows represent the fractionally-weighted vectorial contribution of each lifetime to the phasor measurement.

Fig 2

(a) Pharmacological agents categorized by affected metabolic process, color-coded for subsequent panels (b) Induced changes to NADH intensity relative to baseline levels in pixels corresponding to astrocytic cell bodies and neuropil. * indicates statistically significant variation from baseline (c)Phasor plots for cortical NADH after application of different pharmacological inhibitors at the fundamental laser repetition frequency (ω = 2π × 80 MHz) and (c) second harmonic (ω = 4π × 80 MHz). Lower insets zoomed in to show standard deviational ellipses of each pharmacological reagent, along with data points used to compute ellipses. Ellipse boundary and data points are colored to correspond with reagents in (a). Each data point shape corresponds to a different animal.