3D Imaging Restoration of Spinning-Disk Confocal Microscopy Via Deep Learning
3D Imaging Restoration of Spinning-Disk Confocal Microscopy Via Deep Learning
复制标题
通过深度学习对转盘共焦显微镜进行 3D 成像恢复
DOI：
10.1109/lpt.2020.3014317
复制
发表时间：
2020
影响因子：
2.6
通讯作者：
Yao Baoli
中科院分区：
文献类型：
--
作者：
Bai Chen;Yu Xianghua;Peng Tong;Liu Chao;Min Junwei;Dan Dan;Yao Baoli
由于多点激发和同时检测策略的应用，旋转盘共聚焦显微镜（SDCM）的结果在增加成像速度相比，传统的共聚焦显微镜。此外，超分辨率径向波动（SRRF）方法可以进一步提高SDCM在3D成像中的成像分辨率，但由于大量的数据采集和由于多个激发而增加的光漂白和光毒性的风险，成像时间增加。在这里，我们提出了一种基于深度学习的3D SDCM方法，其中考虑了$z$扫描切片中的相邻像素进行3D重建。因此，高质量的成像切片可以直接从SDCM堆栈重建与单次扫描。使用这种SRRF-Deep方法可实现的图像质量与SRRF方法相当，而它使用少100倍的图像实现图像重建速度快约30倍。因此，SDCM系统在3D成像中的实用性可以显著提高。
Due to the multipoint excitation and simultaneous detection strategy applied, spinning-disk confocal microscopy (SDCM) results in an increased imaging speed compared to conventional confocal microscopy. Additionally, the super-resolution radial fluctuations (SRRF) approach can further improve the imaging resolution of SDCM in 3D imaging at the cost of imaging time due to the large amounts of data acquisition and the increased risk of photo-bleaching and photo-toxicity due to the multiple excitations. Here, we propose a deep learning-based method for 3D SDCM, where the neighboring pixels in $z$ -scanning slices are taken into account for 3D reconstruction. Consequently, high-quality imaging slices can be reconstructed directly from the SDCM stacks with a single scan. The image quality achievable with this SRRF-Deep method is comparable with the SRRF method, whereas it achieves image reconstruction about 30 times faster using 100 times fewer images. Thus, practicality of the SDCM system can be significantly improved in 3D imaging.