Deep-3D microscope: 3D volumetric microscopy of thick scattering samples using a wide-field microscope and machine learning
Deep-3D microscope: 3D volumetric microscopy of thick scattering samples using a wide-field microscope and machine learning
复制标题
DOI：
10.1364/boe.444488
复制
发表时间：
2022-01-01
影响因子：
3.4
通讯作者：
Veeraraghavan, Ashok
中科院分区：
文献类型：
--
作者：
Li, Bowen;Tan, Shiyu;Veeraraghavan, Ashok
共焦显微镜是一种标准的方法，用于获得具有高轴向和横向分辨率的样品的体积图像，特别是在处理散射样品时。不幸的是，与传统显微镜相比，共焦显微镜相当昂贵。此外，共聚焦显微镜中的点扫描导致成像速度慢，并且由于高剂量的激光能量而导致光漂白。在本文中，我们展示了如何利用机器学习的进步来“教”传统的宽视场显微镜，每个实验室都可以使用的显微镜，像共聚焦显微镜一样产生3D体积图像。其关键思想是使用宽视场显微镜获得具有不同焦点设置的多个图像，并使用基于3D生成对抗网络（GAN）的神经网络来学习使用宽视场显微镜获得的模糊低对比度图像堆栈与使用共聚焦显微镜获得的清晰高对比度图像堆栈之间的映射。在用宽场共焦堆栈对训练网络之后，该网络可以可靠且准确地重建3D体积图像，其在横向分辨率，z切片和图像对比度方面与共焦图像相媲美。我们的实验结果表明，泛化能力，以处理看不见的数据，稳定的重建结果，高空间分辨率，即使成像厚（类似于40微米）的高散射样品。我们相信，这种基于学习的显微镜有可能为每个拥有宽视场显微镜的实验室带来共焦成像质量。(C)2021 Optica出版集团根据Optica开放获取出版协议的条款
Confocal microscopy is a standard approach for obtaining volumetric images of a sample with high axial and lateral resolution, especially when dealing with scattering samples. Unfortunately, a confocal microscope is quite expensive compared to traditional microscopes. In addition, the point scanning in confocal microscopy leads to slow imaging speed and photobleaching due to the high dose of laser energy. In this paper, we demonstrate how the advances in machine learning can be exploited to "teach" a traditional wide-field microscope, one that's available in every lab, into producing 3D volumetric images like a confocal microscope. The key idea is to obtain multiple images with different focus settings using a wide-field microscope and use a 3D generative adversarial network (GAN) based neural network to learn the mapping between the blurry low-contrast image stacks obtained using a wide-field microscope and the sharp, high-contrast image stacks obtained using a confocal microscope. After training the network with widefield-confocal stack pairs, the network can reliably and accurately reconstruct 3D volumetric images that rival confocal images in terms of its lateral resolution, z-sectioning and image contrast. Our experimental results demonstrate generalization ability to handle unseen data, stability in the reconstruction results, high spatial resolution even when imaging thick (similar to 40 microns) highly-scattering samples. We believe that such learning-based microscopes have the potential to bring confocal imaging quality to every lab that has a wide-field microscope. (C) 2021 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement