Ultrafast Imaging With Optical Encoding and Compressive Sensing
Ultrafast Imaging With Optical Encoding and Compressive Sensing
复制标题
DOI：
10.1109/jlt.2018.2880816
复制
发表时间：
2019-02-01
影响因子：
4.7
通讯作者：
Wang, Xu
中科院分区：
文献类型：
--
作者：
Matin, Amir;Dai, Bo;Wang, Xu
串行时间编码放大显微镜（STEAM）是一种新兴的技术，它能够以GHz的扫描速率捕获超快现象。高成像速度和高空间分辨率之间的权衡仍然是一个问题，其中最大扫描速率受到数字化仪的采样率和光纤中的时间色散的限制，以避免数据混合。在本文中，我们使用压缩传感框架下的最先进的优化算法来解决这些限制，并通过考虑单个光学组件（如激光光谱分布、编码掩模图案、光纤色散和系统中的光学噪声）的影响，基于我们提出的实验设置建立数据采集模型。介绍了基于STEAM成像系统的交替方向乘子全变差正则化方法（ADMM-TV）和离散小波硬阈值化方法（DWT-Hrd）。我们的研究结果表明，10 GHz的扫描速率可以实现相比，传统的1 GHz的显微成像系统，同时保持高的图像重建质量的结构相似性指数测量（SSIM）。结果表明，在这两种优化算法中，ADMM-TV优于DWT-Hrd 20%的SSIM测量。最后，它示出，具有70%-80%的光透射通过掩模揭示了重建质量方面的最佳结果。
Serial time-encoded amplified microscopy (STEAM) is an emerging technology, which enables an ultrafast phenomena to be captured at GHz scan rate. The tradeoff between high imaging speed and high spatial resolution remains a problem where the maximum scan rate is limited by the sampling rate of the digitizer and the temporal dispersion in the fiber to avoid data blending. In this paper, we address these limitations using state-of-the-art optimization algorithms under compressive sensing framework and establish the data acquisition model based on our proposed experimental setup by considering the effect of individual optical components such as laser spectral profile, encoding mask patterns, dispersion of the fiber, and optical noise in the system. We introduce two methods of alternating direction method of multipliers with total variation regularization (ADMM-TV) and discrete wavelet hard thresholding (DWT-Hrd) for STEAM-based imaging systems. Our results demonstrate that a 10-GHz scan rate can be achieved compared to the conventional 1-GHz microscopy imaging system while maintaining high image reconstruction quality in terms of structural similarity index measurement (SSIM). It is shown that among the two proposed optimization algorithms, ADMM-TV outperforms DWT-Hrd by 20% in SSIM measurements. Finally, it is shown that having 70%-80% light transmission through the mask reveals the optimum results in terms of reconstruction quality.