拉曼显微成像技术无需样本制备，具有无损、无创、对水溶液不敏感的优点，可在微米或纳米尺度下表征样本的生化组分及分布，成为生命科学领域重要的研究工具。随着对复杂生物样本研究的不断深入，拉曼显微成像也被期待能够实现对生物样本中的分子组成与分布的动态立体观测。首先，系统性地梳理近年来三维拉曼显微成像技术的研究进展，包括基于自发拉曼散射、相干拉曼散射、表面增强拉曼散射以及拉曼标签的不同三维成像方法的技术手段、改进策略与实验结果。然后，总结了不同成像技术在细胞生物学、发育生物学等方面的应用进展。最后展望了不同三维拉曼显微成像技术在生物医学光学显微成像技术应用中所面临的挑战和发展前景。

Coherent anti-Stokes Raman scattering (CARS) microscopy can resolve the chemical components and distribution of living biological systems in a label-free manner and is favored in several disciplines. Current CARS microscopes typically use bulky, high-performance solid-state lasers, which are expensive and sensitive to environmental changes. With their relatively low cost and environmental sensitivity, supercontinuum fiber (SF) lasers with a small footprint have found increasing use in biomedical applications. Upon these features, in this paper, we homebuilt a lowcost CARS microscope based on a SF laser module (scCARS microscope). This SF laser module is specially customized by adding a time-synchronized seed source channel to the SF laser to form a dual-channel output laser. The performance of the scCARS microscope is evaluated with dimethyl sulfoxide, whose results confirm a spatial resolution of better than 500 nm and a detection sensitivity of millimolar concentrations. The dual-color imaging capability is further demonstrated by imaging different species of mixed microspheres. We finally explore the potential of our scCARS microscope by mapping lipid droplets in different cancer cells and corneal stromal lenses.

无透镜计算显微成像是一种低成本、高效的成像技术。这种成像方式具有大视野、高通量的特点，能够实时地对细胞进行无标记成像。提出了一种轻量化网络模型(Depthwise-ResNeXt)，将该神经网络与无透镜计算显微成像进行有机结合，实现了实时准确的细胞分类。使用SUM、MCF10A、ECa109、CL-1四种细胞作为分类数据，Depthwise-ResNeXt对这四类细胞的分类准确率达到92.8%，参数量仅有806 kB。该网络证明了神经网络与无透镜计算显微成像在细胞分类领域相结合的可能性，并大大降低了神经网络在细胞分类方面的应用成本。

Early diagnosis and fast detection with a high accuracy rate of lung cancer are important to improve the treatment effect. In this research, an early fast diagnosis and in vivo imaging method for lung adenocarcinoma are proposed by collecting the spectral data from normal and patients' cells/tissues, such as Fourier infrared spectroscopy (FTIR), UV-vis absorbance, and fluorescence spectra using anthocyanin. The FTIR spectra of human normal lung epithelial cells (BEAS-2B cells) and human lung adenocarcinoma cells (A549 cells) were collected. After the data is cleaned, a feature selection algorithm is used to select important wavelengths, and then, the classification models of support vector machine (SVM) and the grid search method are used to select the optimal model parameters (accuracy: 96.89% on the training set and 88.57% on the test set). The optimal model is used to classify all samples, and the accuracy is 94.37%. Moreover, the anthocyanin was prepared and used for the intracellular absorbance and fluorescence, and the optimized algorithm was used for classification (accuracy: 91.38% on the training set and 80.77% on the test set). Most importantly, the in vivo cancer imaging can be performed using anthocyanin. The results show that there are differences between lung adenocarcinoma and normal lung tissues at the molecular level, reflecting the accuracy, intuitiveness, and feasibility of this algorithm-assistant anthocyanin imaging in lung cancer diagnosis, thus showing the potential to become an accurate and effective technical means for basic research and clinical diagnosis.

Stimulated Raman scattering (SRS) microscopy has the ability of noninvasive imaging of specific chemical bonds and been increasingly used in biomedicine in recent years. Two pulsed Gaussian beams are used in traditional SRS microscopes, providing with high lateral and axial spatial resolution. Because of the tight focus of the Gaussian beam, such an SRS microscopy is difficult to be used for imaging deep targets in scattering tissues. The SRS microscopy based on Bessel beams can solve the imaging problem to a certain extent. Here, we establish a theoretical model to calculate the SRS signal excited by two Bessel beams by integrating the SRS signal generation theory with the fractal propagation method. The fractal model of refractive index turbulence is employed to generate the scattering tissues where the light transport is modeled by the beam propagation method. We model the scattering tissues containing chemicals, calculate the SRS signals stimulated by two Bessel beams, discuss the influence of the fractal model parameters on signal generation, and compare them with those generated by the Gaussian beams. The results show that, even though the modeling parameters have great influence on SRS signal generation, the Bessel beams-based SRS can generate signals in deeper scattering tissues.