Spatial resolution improved fluorescence lifetime imaging via deep learning

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, and robustness. Inspired by the concept of Edge Artificial Intelligence (Edge AI), we propose a robust approach that enables fast FLI with no degradation of accuracy. This approach couples a recurrent neural network (RNN), which is trained to estimate the fluorescence lifetime directly from raw timestamps without building histograms, to SPAD TCSPC systems, thereby drastically reducing transfer data volumes and hardware resource utilization, and enabling real-time FLI acquisition. We train two variants of the RNN on a synthetic dataset and compare the results to those obtained using center-of-mass method (CMM) and least squares fitting (LS fitting). Results demonstrate that two RNN variants, gated recurrent unit (GRU) and long short-term memory (LSTM), are comparable to CMM and LS fitting in terms of accuracy, while outperforming them in the presence of background noise by a large margin. To explore the ultimate limits of the approach, we derive the Cramer-Rao lower bound of the measurement, showing that RNN yields lifetime estimations with near-optimal precision. To demonstrate real-time operation, we build a FLI microscope based on an existing SPAD TCSPC system comprising a 32[Formula: see text]32 SPAD sensor named Piccolo. Four quantized GRU cores, capable of processing up to 4 million photons per second, are deployed on the Xilinx Kintex-7 FPGA that controls the Piccolo. Powered by the GRU, the FLI setup can retrieve real-time fluorescence lifetime images at up to 10 frames per second. The proposed FLI system is promising and ideally suited for biomedical applications, including biological imaging, biomedical diagnostics, and fluorescence-assisted surgery, etc.

Fluorescence Lifetime Measurements and Analyses: Protocols Using Flow Cytometry and High-Throughput Microscopy

This chapter focuses on applications and protocols that involve the measurement of the fluorescence lifetime as an informative cytometric parameter. The timing of fluorescence decay has been well-studied for cell counting, sorting, and imaging. Therefore, provided herein is an overview of the techniques used, how they enhance cytometry protocols, and the modern techniques used for lifetime analysis. The background and theory behind fluorescence decay kinetic measurements in cells is first discussed followed by the history of the development of time-resolved flow cytometry. These sections are followed by a review of applications that benefit from the quantitative nature of fluorescence lifetimes as a photophysical trait. Lastly, perspectives on the modern ways in which the fluorescence lifetime is scanned at high throughputs which include high-speed microscopy and machine learning are provided.

Probing organoid metabolism using fluorescence lifetime imaging microscopy (FLIM): The next frontier of drug discovery and disease understanding

Organoid models have been used to address important questions in developmental and cancer biology, tissue repair, advanced modelling of disease and therapies, among other bioengineering applications. Such 3D microenvironmental models can investigate the regulation of cell metabolism, and provide key insights into the mechanisms at the basis of cell growth, differentiation, communication, interactions with the environment and cell death. Their accessibility and complexity, based on 3D spatial and temporal heterogeneity, make organoids suitable for the application of novel, dynamic imaging microscopy methods, such as fluorescence lifetime imaging microscopy (FLIM) and related decay time-assessing readouts. Several biomarkers and assays have been proposed to study cell metabolism by FLIM in various organoid models. Herein, we present an expert-opinion discussion on the principles of FLIM and PLIM, instrumentation and data collection and analysis protocols, and general and emerging biosensor-based approaches, to highlight the pioneering work being performed in this field.

Compact and robust deep learning architecture for fluorescence lifetime imaging and FPGA implementation

This paper reports a bespoke adder-based deep learning network for time-domain fluorescence lifetime imaging (FLIM). By leveraging thel1-norm extraction method, we propose a 1D Fluorescence Lifetime AdderNet (FLAN) without multiplication-based convolutions to reduce the computational complexity. Further, we compressed fluorescence decays in temporal dimension using a log-scale merging technique to discard redundant temporal information derived as log-scaling FLAN (FLAN+LS). FLAN+LS achieves 0.11 and 0.23 compression ratios compared with FLAN and a conventional 1D convolutional neural network (1D CNN) while maintaining high accuracy in retrieving lifetimes. We extensively evaluated FLAN and FLAN+LS using synthetic and real data. A traditional fitting method and other non-fitting, high-accuracy algorithms were compared with our networks for synthetic data. Our networks attained a minor reconstruction error in different photon-count scenarios. For real data, we used fluorescent beads' data acquired by a confocal microscope to validate the effectiveness of real fluorophores, and our networks can differentiate beads with different lifetimes. Additionally, we implemented the network architecture on a field-programmable gate array (FPGA) with a post-quantization technique to shorten the bit-width, thereby improving computing efficiency. FLAN+LS on hardware achieves the highest computing efficiency compared to 1D CNN and FLAN. We also discussed the applicability of our network and hardware architecture for other time-resolved biomedical applications using photon-efficient, time-resolved sensors.

Deep learning-based high-speed, large-field, and high-resolution multiphoton imaging

Multiphoton microscopy is a formidable tool for the pathological analysis of tumors. The physical limitations of imaging systems and the low efficiencies inherent in nonlinear processes have prevented the simultaneous achievement of high imaging speed and high resolution. We demonstrate a self-alignment dual-attention-guided residual-in-residual generative adversarial network trained with various multiphoton images. The network enhances image contrast and spatial resolution, suppresses noise, and scanning fringe artifacts, and eliminates the mutual exclusion between field of view, image quality, and imaging speed. The network may be integrated into commercial microscopes for large-scale, high-resolution, and low photobleaching studies of tumor environments.