Deep learning-driven adaptive optics for single-molecule localization microscopy.
Deep learning-driven adaptive optics for single-molecule localization microscopy.
复制标题
DOI：
10.1038/s41592-023-02029-0
复制
发表时间：
2023-11
期刊：
影响因子：
48
通讯作者：
Huang, Fang
中科院分区：
文献类型：
--
作者：
Zhang, Peiyi;Ma, Donghan;Cheng, Xi;Tsai, Andy P.;Tang, Yu;Gao, Hao-Cheng;Fang, Li;Bi, Cheng;Landreth, Gary E.;Chubykin, Alexander A.;Huang, Fang
生物组织的非均匀折射率使单分子发射图案模糊和失真，产生图像伪影并降低单分子定位显微术（SMLM）可实现的分辨率。传统的无传感器自适应光学方法依赖于迭代的反射镜变化和图像质量指标。然而，这些度量导致不一致的度量响应，因此从根本上限制了它们用于组织中的畸变校正的功效。为了绕过迭代的试验然后评估过程，我们为SMLM开发了深度学习驱动的自适应光学，以允许直接推断波前畸变和近实时补偿。我们经过训练的深度神经网络监测来自单分子实验的个体发射模式，推断它们共享的波前失真，通过动态滤波器提供估计值，并驱动可变形镜来补偿样品引起的像差。我们证明，我们的方法同时估计和补偿28个波前变形形状，并通过>130 μ m厚的脑组织标本提高三维SMLM的分辨率和保真度。深度学习方法绕过与无传感器自适应光学相关的迭代试验，以补偿生物样本成像时的波前变形，从而实现改进的深层组织定位显微镜。
The inhomogeneous refractive indices of biological tissues blur and distort single-molecule emission patterns generating image artifacts and decreasing the achievable resolution of single-molecule localization microscopy (SMLM). Conventional sensorless adaptive optics methods rely on iterative mirror changes and image-quality metrics. However, these metrics result in inconsistent metric responses and thus fundamentally limit their efficacy for aberration correction in tissues. To bypass iterative trial-then-evaluate processes, we developed deep learning-driven adaptive optics for SMLM to allow direct inference of wavefront distortion and near real-time compensation. Our trained deep neural network monitors the individual emission patterns from single-molecule experiments, infers their shared wavefront distortion, feeds the estimates through a dynamic filter and drives a deformable mirror to compensate sample-induced aberrations. We demonstrated that our method simultaneously estimates and compensates 28 wavefront deformation shapes and improves the resolution and fidelity of three-dimensional SMLM through >130-µm-thick brain tissue specimens. A deep learning approach bypasses iterative trials associated with sensorless adaptive optics to compensate for wavefront deformations when imaging biological specimens, enabling improved deep tissue localization microscopy.
登录
查看更多内容
DOI：
10.1007/978-1-59745-483-4_32
发表时间：
2009
期刊：
Methods in molecular biology (Clifton, N.J.)
影响因子：
--
作者：
Hess ST;Gould TJ;Gunewardene M;Bewersdorf J;Mason MD
通讯作者：
Mason MD
影响因子：
16.2
作者：
Berry KP;Nedivi E
通讯作者：
Nedivi E
DOI：
10.1038/s43586-021-00066-7
发表时间：
2021-10-14
期刊：
NATURE REVIEWS METHODS PRIMERS
影响因子：
--
作者：
Hampson, Karen M.;Turcotte, Raphael;Booth, Martin J.
通讯作者：
Booth, Martin J.
影响因子：
16.2
作者：
Arenkiel, Benjamin R.;Peca, Joao;Feng, Guoping
通讯作者：
Feng, Guoping
影响因子：
3.8
作者：
Debarre, Delphine;Botcherby, Edward J.;Wilson, Tony
通讯作者：
Wilson, Tony