Department of Computer Science, University of California, Irvine, Irvine, CA, USA.
Institute for Genomics and Bioinformatics, University of California, Irvine, Irvine, CA, USA.
Transl Vis Sci Technol. 2021 Oct 4;10(12):30. doi: 10.1167/tvst.10.12.30.
Two-photon excitation fluorescence (2PEF) reveals information about tissue function. Concerns for phototoxicity demand lower light exposure during imaging. Reducing excitation light reduces the quality of the image by limiting fluorescence emission. We applied deep learning (DL) super-resolution techniques to images acquired from low light exposure to yield high-resolution images of retinal and skin tissues.
We analyzed two methods: a method based on U-Net and a patch-based regression method using paired images of skin (550) and retina (1200), each with low- and high-resolution paired images. The retina dataset was acquired at low and high laser powers from retinal organoids, and the skin dataset was obtained from averaging 7 to 15 frames or 70 frames. Mean squared error (MSE) and the structural similarity index measure (SSIM) were outcome measures for DL algorithm performance.
For the skin dataset, the patches method achieved a lower MSE (3.768) compared with U-Net (4.032) and a high SSIM (0.824) compared with U-Net (0.783). For the retinal dataset, the patches method achieved an average MSE of 27,611 compared with 146,855 for the U-Net method and an average SSIM of 0.636 compared with 0.607 for the U-Net method. The patches method was slower (303 seconds) than the U-Net method (<1 second).
DL can reduce excitation light exposure in 2PEF imaging while preserving image quality metrics.
DL methods will aid in translating 2PEF imaging from benchtop systems to in vivo imaging of light-sensitive tissues such as the retina.
双光子激发荧光（2PEF）可揭示组织功能信息。出于对光毒性的担忧，在成像过程中需要降低光暴露。减少激发光会限制荧光发射，从而降低图像质量。我们应用深度学习（DL）超分辨率技术处理低光曝光采集的图像，以生成视网膜和皮肤组织的高分辨率图像。
我们分析了两种方法：一种是基于 U-Net 的方法，另一种是基于成对的皮肤（550）和视网膜（1200）图像的基于补丁的回归方法，每个方法都有低分辨率和高分辨率的配对图像。视网膜数据集是从视网膜类器官在低功率和高功率激光下获取的，皮肤数据集是通过平均 7 到 15 帧或 70 帧获得的。均方误差（MSE）和结构相似性指数度量（SSIM）是 DL 算法性能的衡量标准。
对于皮肤数据集，与 U-Net 相比，补丁方法的 MSE 更低（3.768），SSIM 更高（0.824）。对于视网膜数据集，与 U-Net 方法相比，补丁方法的平均 MSE 为 27611，U-Net 方法为 146855，平均 SSIM 为 0.636，U-Net 方法为 0.607。补丁方法比 U-Net 方法慢（303 秒）（<1 秒）。
DL 可在保持图像质量指标的同时降低 2PEF 成像中的激发光暴露。
张宇
刘长军
