Deep Learning-Assisted Multiphoton Microscopy to Reduce Light Exposure and Expedite Imaging in Tissues With High and Low Light Sensitivity.
Deep Learning-Assisted Multiphoton Microscopy to Reduce Light Exposure and Expedite Imaging in Tissues With High and Low Light Sensitivity.
复制标题
DOI：
10.1167/tvst.10.12.30
复制
发表时间：
2021-10-04
影响因子：
3
通讯作者：
Browne AW
中科院分区：
文献类型：
--
作者：
McAleer S;Fast A;Xue Y;Seiler MJ;Tang WC;Balu M;Baldi P;Browne AW
双光子激发荧光（2PEF）揭示有关组织功能的信息。对光毒性的担忧需要在成像过程中降低曝光量。减少激发光会限制荧光发射，从而降低图像质量。我们将深度学习 (DL) 超分辨率技术应用于低光照射下获取的图像，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：基于 U-Net 的方法和使用皮肤 (550) 和视网膜 (1200) 配对图像的基于块的回归方法，每种方法都有低分辨率和高分辨率配对图像。视网膜数据集是在低和高激光功率下从视网膜类器官获得的，皮肤数据集是通过平均 7 至 15 帧或 70 帧获得的。均方误差 (MSE) 和结构相似性指数度量 (SSIM) 是深度学习算法性能的结果度量。对于皮肤数据集，与 U-Net (4.032) 相比，补丁方法实现了较低的 MSE (3.768)，与 U-Net (0.783) 相比，补丁方法实现了较高的 SSIM (0.824)。对于视网膜数据集，patch 方法的平均 MSE 为 27,611，而 U-Net 方法为 146,855；平均 SSIM 为 0.636，而 U-Net 方法为 0.607。 patch 方法比 U-Net 方法（<1 秒）慢（303 秒）。 DL 可以减少 2PEF 成像中的激发光曝光，同时保留图像质量指标。 DL 方法将有助于将 2PEF 成像从台式系统转换为视网膜等光敏组织的体内成像。
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.
登录
查看更多内容
DOI：
10.1158/1078-0432.ccr-18-0385
发表时间：
2018-08-01
期刊：
Clinical cancer research : an official journal of the American Association for Cancer Research
影响因子：
--
作者：
Parmar C;Barry JD;Hosny A;Quackenbush J;Aerts HJWL
通讯作者：
Aerts HJWL
影响因子：
3.5
作者：
Masters, BR;So, PTC;Gratton, E
通讯作者：
Gratton, E
影响因子：
3.4
作者：
Schwarz, Christina;Sharma, Robin;Hunter, Jennifer J.
通讯作者：
Hunter, Jennifer J.
影响因子：
2.4
作者：
Urban, Gregor;Feil, Nate;Baldi, Pierre
通讯作者：
Baldi, Pierre
影响因子：
2.9
作者：
Asaoka, Ryo;Tanito, Masaki;Kiuchi, Yoshiaki
通讯作者：
Kiuchi, Yoshiaki