FLIMJ: An open-source ImageJ toolkit for fluorescence lifetime image data analysis

Abstract

In the field of fluorescence microscopy, there is continued demand for dynamic technologies that can exploit the complete information from every pixel of an image. One imaging technique with proven ability for yielding additional information from fluorescence imaging is Fluorescence Lifetime Imaging Microscopy (FLIM). FLIM allows for the measurement of how long a fluorophore stays in an excited energy state, and this measurement is affected by changes in its chemical microenvironment, such as proximity to other fluorophores, pH, and hydrophobic regions. This ability to provide information about the microenvironment has made FLIM a powerful tool for cellular imaging studies ranging from metabolic measurement to measuring distances between proteins. The increased use of FLIM has necessitated the development of computational tools for integrating FLIM analysis with image and data processing. To address this need, we have created FLIMJ, an ImageJ plugin and toolkit that allows for easy use and development of extensible image analysis workflows with FLIM data. Built on the FLIMLib decay curve fitting library and the ImageJ Ops framework, FLIMJ offers FLIM fitting routines with seamless integration with many other ImageJ components, and the ability to be extended to create complex FLIM analysis workflows. Building on ImageJ Ops also enables FLIMJ's routines to be used with Jupyter notebooks and integrate naturally with science-friendly programming in, e.g., Python and Groovy. We show the extensibility of FLIMJ in two analysis scenarios: lifetime-based image segmentation and image colocalization. We also validate the fitting routines by comparing them against industry FLIM analysis standards.

Fig 1. Relationships between components of FLIMJ and ImageJ2.

FLIMJ Ops depends on FLIMLib and communicates with other supporting ops (mathematical, statistical, and input/output tools) through the Ops framework. This schematic shows two different ways to access FLIMLib. The scripting path goes through the ops-framework to the FLIMJ-Ops library, and the GUI path goes through the FLIMJ-UI to FLIMJ-Ops.

Fig 2

A) Breast cancer tissues from 107 patients METABRIC study were stained with antibodies: anti-HER3-IgG-Alexa546 (donor) and anti-HER2-IgG-Cy5 (acceptor) [37]. Serial sections were stained with donor+acceptor (DA, FRET pair) and with donor alone (D, control). Average lifetime values (T_D and T_DA) can be determined for the tumor from the two serial sections using FLIMJ after segmentation. The FRET efficiency can be calculated according to FRETeff = 1 –TDA/TD. B) Weka Trainable Segmentation plugin was used to segment the tissue areas. The FLIMJ user interface showing a typical transient and fit from the tissue. We used the LM fitting with a mono-exponential model. C) Zoom into a smaller region. Composite image from FLIMJ showing lifetime information. Pure lifetime map with Weka segmentation shown in yellow. Segmentation result of the lifetime within the tumor with artifactual tissue removed. From T_D = 2.23 ns and T_DA = 2.16 ns, we estimate a FRET efficiency for this example tumor area as 3.1% as a measure of HER2-HER3 dimerization on the tumor in this patient.

Fig 3. Microglia colocalization analysis using NADH FLIM and CX3CR1-GFP labels [39, 46].

A) The analysis workflow describing how microglia are visualized using a specific antibody, followed by NADH FLIM acquisition and FLIMJ analysis B) NADH FLIM data analysis using 2-component fit in FLIMJ-UI. Users can choose the intensity threshold, kernel size, fitting model, noise model, model restraints, and the number of components. The single curve fit is fast, and the “Fit Dataset” button performs fits for all the pixels. The fit result and fitting-parameters can be exported from the export tab on the lower right part of the UI. C) Overlaid images of antibody (green) and lifetime image (red) to show the pixels with overlapping NADH and GFP signal. D) Coloc2 analysis of mean lifetime and microglia antibody image.

Fig 4

A) Validation of FLIMLib LMA lifetime estimation against hardware vendor-provided software (SPCImage) for fluorescein in water. B) The phasor plot for the data is also shown as a proof of principle of the FLIMLib Phasor function for fit-less estimation of lifetime parameters. The two parallels of lifetime histograms and phasor plots are the current laboratory standards for FLIM analysis. The phasor is plotted on a universal circle derived from the endpoints of the fit-range (117 MHz).

Fig 5. FLIM Validation using a simulated dataset for 1-component fitting.

The lifetime values range from 0.2 ns to 6.0 ns that fit within the fitting range of 10 ns. A) Ground truth lifetime distribution. B) Ground truth is compared against lifetime estimates obtained using B) LMA, C) RLD, and D) Phasor. The insets in panels B-D shows the maps of lifetime estimates generated by each method. E) The phasor plot for the estimates shown in panel D. Panels F-H) shows how Bayesian fits generate a better accuracy in low-photon decay curves. F) The ground truth data was trimmed down to a fraction of total photons (10% - 90%). The data is divided diagonally half as noisy and clean. Three representative images of 10%, 50%, and 90% of total photons are compared for total photons and a sample decay curve at 4ns. A different color-map is used here to highlight that this is the photon counts and not the lifetime map. G, H) The differences between fit results of the noisy (10% - 90% photons) and clean decay curves of a range of lifetime values (0.2–6.0 ns) are presented in panel H. The LMA distribution shows a larger variance at lower photons in comparison to Bayes. Bayes fit gives a better representation to the clean curve than LMA with as low as 10% total photons. Panel G compares two representative distribution of photons: 10% and 90% for both Bayes and LMA. Bayes converges approximately four times better than LMA. The inset in panel G shows how the values are extracted for 32-lifetime value.

Fig 6. FLIM Validation using simulated 2-component lifetime data.

The figure shows the simulated data with fixed lifetime values, 2.1 ns, and 0.4 ns. A) The intensity image for the simulated dataset is shown here. Note that this scale is for photons. B) Five sample lifetime curves are shown to demonstrate the variation in their intensity levels and decay rates. C) This panel compares the Global fitting routine and LMA for the two-component model. The color maps are the same between the panels of each parameter. The three parameters shown are Z (offset), A1 (amplitude of species 1), and A2 (amplitude of species 2). Both LMA and Global fitting reproduce the apparent fraction of two species, but we find that global fitting yields less noise and works twice as fast. (This dataset is provided in the SCIFIO sample datasets or https://samples.scif.io/Gray-FLIM-datasets.zip).