Pixel Super-Resolved Fluorescence Lifetime Imaging Using Deep Learning

2025/12/18 by Costa, Paloma Casteleiro, Kashani, Parnian Ghapandar, Liu, Xuhui +5
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Medical Physics (physics.med-ph) #Optics (physics.optics)

paper · doi:10.48550/arxiv.2512.16266

Abstract

Fluorescence lifetime imaging microscopy (FLIM) is a powerful quantitative technique that provides metabolic and molecular contrast, offering strong translational potential for label-free, real-time diagnostics. However, its clinical adoption remains limited by long pixel dwell times and low signal-to-noise ratio (SNR), which impose a stricter resolution-speed trade-off than conventional optical imaging approaches. Here, we introduce FLIM_PSR_k, a deep learning-based multi-channel pixel super-resolution (PSR) framework that reconstructs high-resolution FLIM images from data acquired with up to a 5-fold increased pixel size. The model is trained using the conditional generative adversarial network (cGAN) framework, which, compared to diffusion model-based alternatives, delivers a more robust PSR reconstruction with substantially shorter inference times, a crucial advantage for practical deployment. FLIM_PSR_k not only enables faster image acquisition but can also alleviate SNR limitations in autofluorescence-based FLIM. Blind testing on held-out patient-derived tumor tissue samples demonstrates that FLIM_PSR_k reliably achieves a super-resolution factor of k = 5, resulting in a 25-fold increase in the space-bandwidth product of the output images and revealing fine architectural features lost in lower-resolution inputs, with statistically significant improvements across various image quality metrics. By increasing FLIM's effective spatial resolution, FLIM_PSR_k advances lifetime imaging toward faster, higher-resolution, and hardware-flexible implementations compatible with low-numerical-aperture and miniaturized platforms, better positioning FLIM for translational applications.

Citations

• Virtual Staining of Label-Free Tissue in Imaging Mass Spectrometry
• High-Resolution Image Synthesis with Latent Diffusion Models
• Generative Modeling by Estimating Gradients of the Data Distribution
• Image-to-Image Translation with Conditional Adversarial Networks

Related

• Deep Learning for Fluorescence Lifetime Predictions Enables High-Throughput In Vivo Imaging
• Fast fluorescence lifetime imaging analysis via extreme learning machine
• Enhancing Fluorescence Lifetime Parameter Estimation Accuracy with Differential Transformer Based Deep Learning Model Incorporating Pixelwise Instrument Response Function
• Compact and Robust Deep Learning Architecture for Fluorescence Lifetime Imaging and FPGA Implementation
• Deep Compressive Macroscopic Fluorescence Lifetime Imaging