双光子激发显微镜是研究脑神经元活动的重要工具。基于传统机械式逐点激光扫描技术的双光子激发显微镜成像速度较慢，无法进行脑神经元活动的实时观察研究。此外，高速双光子激发显微成像需要配置高重复频率飞秒激光，以保证在较短的像素停留时间内获得较高的信息强度。本文提出了基于声光偏转的并行GHz超快激光扫描技术，通过设计射频编码方案，在920 nm波段搭建了高速GHz超快激光扫描系统。通过调整时间和空间重合，最终在15~31 MHz频率范围内获得了33个可分辨的并行GHz超快激光扫描光束，为实现高速双光子激发显微成像提供了技术支撑。

The volumetric imaging of two-photon microscopy expands the focal depth and improves the throughput, which has unparalleled superiority for three-dimension samples, especially in neuroscience. However, emerging in volumetric imaging is still largely customized, which limits the integration with commercial two-photon systems. Here, we analyzed the key parameters that modulate the focal depth and lateral resolution of polarized annular imaging and proposed a volumetric imaging module that can be directly integrated into commercial two-photon systems using conventional optical elements. This design incorporates the beam diameter adjustment settings of commercial two-photon systems, allowing flexibility to adjust the depth of focus while maintaining the same lateral resolution. Further, the depth range and lateral resolution of the design were verified, and the imaging throughput was demonstrated by an increase in the number of imaging neurons in the awake mouse cerebral cortex.

双光子成像技术已被广泛应用于活体肿瘤成像、神经功能成像以及大脑疾病研究等领域，但双光子成像视场较小（视场直径一般在1 mm以内），限制了其进一步应用。虽然通过特殊的光学设计或者自适应光学技术能够有效增大视场，但复杂的光路设计、高昂的器件成本以及繁琐的操作过程限制了这些技术的推广。提出了一种利用深度学习技术替代自适应光学技术扩展双光子成像视场的新思路，在低成本（无须特殊物镜，无须相位补偿装置）、易操作的前提下实现了大视场双光子成像。设计了一种适用于光学显微系统中扩展双光子成像视场的nBRAnet网络框架，为使该网络框架可以更好地利用特征图信息，在该框架中引入残差模块和空间注意力机制，同时去除了数据归一化处理，以增加图像对比度信息。实验结果表明：所提深度学习方法可以有效地代替自适应光学技术，增强扩展视场中的精细结构特征，并恢复扩展视场的成像分辨率和信噪比，使双光子成像视场直径扩展到3.46 mm，峰值信噪比超过27 dB。深度学习方法具有成本低、操作简单、图像增强效果显著等特点，有望为跨区域脑成像或全脑成像提供一种经济实用的方案。

本文提出利用离轴抛物镜共焦中继系统来改善双光子成像视场边缘像质变差的问题, 进而提升双光子成像视场。不同于传统的双胶合透镜扫描中继系统, 离轴抛物镜共焦扫描中继系统由一对离轴抛物镜构成, 扫描振镜位于抛物面镜焦点处。仿真和试验结果均显示, 该系统能有效优化视场边缘的像散、场曲和畸变情况, 提高成像质量。利用该扫描系统, 我们实现了视场为2.4 mm×2.4 mm, 横向分辨率为1 μm的大视场双光子显微成像, 能清晰分辨小鼠大脑切片中的神经轴突结构。

Two-photon microscopy normally suffers from the scattering of the tissue in biological imaging. Multidither coherent optical adaptive technique (COAT) can correct the scattered wavefront in parallel. However, the determination of the corrective phases may not be completely accurate using conventional method, which undermines the performance of this technique. In this paper, we theoretically demonstrate a method that can obtain more accurate corrective phases by determining the phase values from the square root of the fluorescence signal. A numerical simulation model is established to study the performance of adaptive optics in two-photon microscopy by combining scalar diffraction theory with vector diffraction theory. The results show that the distortion of the wavefront can be corrected more thoroughly with our method in two-photon imaging. In our simulation, with the scattering from a 450-μm-thick mouse brain tissue, excitation focal spots with higher peak-to-background ratio (PBR) and images with higher contrast can be obtained. Hence, further enhancement of the multidither COAT correction performance in two-photon imaging can be expected.