Abstract
Fluorescence microscopy typically suffers from aberration induced by system and sample, which could be circumvented by image deconvolution. We proposed a novel, to the best of our knowledge, Richardson–Lucy (RL) model-driven deconvolution framework to improve reconstruction performance and speed. Two kinds of neural networks within this framework were devised, which are partially interpretable compared with previous deep learning methods. We first introduce RL into deep feature space, which has superior generalizability to the convolutional neural networks (CNN). We further accelerate it with an unmatched backprojector, providing a five times faster reconstruction speed than classic RL. Our deconvolution approaches outperform both CNN and traditional methods regarding image quality for blurred images caused by out-of-focus or imaging system aberration.
© 2023 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Chenfei Jin, Jiaheng Xie, Siqi Zhang, ZiJing Zhang, and Yuan Zhao
Opt. Lett. 43(23) 5885-5888 (2018)
Rongshuai Zhang, Fanjiao Tan, Qingyu Hou, Zongling Li, Zaiwu Sun, Changjian Yang, and Xiangyang Gao
Opt. Lett. 48(3) 522-525 (2023)
Chuhui Wang, Jiachen Wan, Jiaju Chen, Ijaz Gul, Chenyao Jiang, Xiaoyun Zhong, Zhenglin Chen, Zhengyang Lei, Shuyue Ma, Tsz Kwan Lam, Dongmei Yu, and Peiwu Qin
Opt. Lett. 48(7) 1894-1897 (2023)