Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.16266 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909968652828672 |
|---|---|
| author | Costa, Paloma Casteleiro Kashani, Parnian Ghapandar Liu, Xuhui Chen, Alexander Portes, Ary Bec, Julien Marcu, Laura Ozcan, Aydogan |
| author_facet | Costa, Paloma Casteleiro Kashani, Parnian Ghapandar Liu, Xuhui Chen, Alexander Portes, Ary Bec, Julien Marcu, Laura Ozcan, Aydogan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16266 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pixel Super-Resolved Fluorescence Lifetime Imaging Using Deep Learning Costa, Paloma Casteleiro Kashani, Parnian Ghapandar Liu, Xuhui Chen, Alexander Portes, Ary Bec, Julien Marcu, Laura Ozcan, Aydogan Computer Vision and Pattern Recognition Machine Learning Medical Physics Optics 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. |
| title | Pixel Super-Resolved Fluorescence Lifetime Imaging Using Deep Learning |
| topic | Computer Vision and Pattern Recognition Machine Learning Medical Physics Optics |
| url | https://arxiv.org/abs/2512.16266 |