Qingjie Zhu1, Yi Shao1, Zhicheng Wang1,2, Xingjun Chen1,2, Chunqiong Li1, Zihan Liang3, Mingyue Jia1, Qingchun Guo1, Hu Zhao4, Lei Kong5, Li Zhang1. 1. Chinese Institute for Brain Research, Beijing (CIBR), 102206, CN. 2. Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, 100871, CN. 3. Southwest Jiaotong University, Chengdu, Sichuan, 611756, CN. 4. Department of Comprehensive Dentistry, Texas A&M University, Dallas, TX, 75246, US. 5. Center for Bioinformatics, State Key Laboratory of Protein and Plant Gene Research, School of Life Sciences, Peking University, Beijing, 100871, CN.
Abstract
MOTIVATION: Microscopy technology plays important roles in many biological research fields. Solvent-cleared brain high-resolution (HR) 3 D image reconstruction is an important microscopy application. However, 3 D microscopy image generation is time-consuming and expensive. Therefore, we have developed a deep learning framework (DeepS) for both image optical sectioning and super resolution microscopy. RESULTS: Using DeepS to perform super resolution solvent-cleared mouse brain microscopy 3 D image yields improved performance in comparison with the standard image processing workflow. We have also developed a web server to allow online usage of DeepS. Users can train their own models with only one pair of training images using the transfer learning function of the web server. AVAILABILITY: http://deeps.cibr.ac.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
MOTIVATION: Microscopy technology plays important roles in many biological research fields. Solvent-cleared brain high-resolution (HR) 3 D image reconstruction is an important microscopy application. However, 3 D microscopy image generation is time-consuming and expensive. Therefore, we have developed a deep learning framework (DeepS) for both image optical sectioning and super resolution microscopy. RESULTS: Using DeepS to perform super resolution solvent-cleared mouse brain microscopy 3 D image yields improved performance in comparison with the standard image processing workflow. We have also developed a web server to allow online usage of DeepS. Users can train their own models with only one pair of training images using the transfer learning function of the web server. AVAILABILITY: http://deeps.cibr.ac.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.