Proc. SPIE. 11648, Multiphoton Microscopy in the Biomedical Sciences XXI
KEYWORDS: Signal to noise ratio, Convolutional neural networks, Imaging systems, Image segmentation, Denoising, Microscopy, Luminescence, Signal processing, Fluorescence lifetime imaging, In vivo imaging
Fluorescence lifetime imaging microscopy (FLIM) systems are limited by their slow processing speed, low signal- to-noise ratio (SNR), and expensive and challenging hardware setups. In this work, we demonstrate applying a denoising convolutional network to improve FLIM SNR. The network will integrated with an instant FLIM system with fast data acquisition based on analog signal processing, high SNR using high-efficiency pulse-modulation, and cost-effective implementation utilizing off-the-shelf radio-frequency components. Our instant FLIM system simultaneously provides the intensity, lifetime, and phasor plots in vivo and ex vivo. By integrating image de- noising using the trained deep learning model on the FLIM data, provide accurate FLIM phasor measurements are obtained. The enhanced phasor is then passed through the K-means clustering segmentation method, an unbiased and unsupervised machine learning technique to separate different fluorophores accurately. Our experimental in vivo mouse kidney results indicate that introducing the deep learning image denoising model before the segmentation effectively removes the noise in the phasor compared to existing methods and provides clearer segments. Hence, the proposed deep learning-based workflow provides fast and accurate automatic segmentation of fluorescence images using instant FLIM. The denoising operation is effective for the segmentation if the FLIM measurements are noisy. The clustering can effectively enhance the detection of biological structures of interest in biomedical imaging applications.
We propose and demonstrate a novel multiphoton frequency-domain fluorescence lifetime imaging microscopy (MPM-FD-FLIM) system that is able to generate 3D lifetime images in deep scattering tissues. The imaging speed of FD-FLIM is improved using phase multiplexing, where the fluorescence signal is split and mixed with the reference signal from the laser in a multiplexing manner. The system allows for easy generation of phasor plots, which not only address multi-exponential decay problems but also clearly represent the dynamics of the fluorophores being investigated. Lastly, a sensorless adaptive optics setup is used for FLIM imaging in deep scattering tissues. The capability of the system is demonstrated in fixed and living animal models, including mice and zebrafish.