Deep learning enables stochastic optical reconstruction microscopy-like superresolution image reconstruction from conventional microscopy

Lei Xu; Shichao Kan; Xiying Yu; Ye Liu; Yuxia Fu; Yiqiang Peng; Yanhui Liang; Yigang Cen; Changjun Zhu; Wei Jiang

doi:10.1016/j.isci.2023.108145

Deep learning enables stochastic optical reconstruction microscopy-like superresolution image reconstruction from conventional microscopy

iScience. 2023 Oct 4;26(11):108145. doi: 10.1016/j.isci.2023.108145. eCollection 2023 Nov 17.

Authors

Lei Xu^{1

2}, Shichao Kan³, Xiying Yu¹, Ye Liu⁴, Yuxia Fu¹, Yiqiang Peng⁴, Yanhui Liang⁴, Yigang Cen⁵, Changjun Zhu², Wei Jiang¹

Affiliations

¹ Department of Etiology and Carcinogenesis and State Key Laboratory of Molecular Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.
² Key Laboratory of Molecular and Cellular Systems Biology, College of Life Sciences, Tianjin Normal University, Tianjin 300387, China.
³ School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China.
⁴ HAMD (Ningbo) Intelligent Medical Technology Co., Ltd, Ningbo 315194, China.
⁵ Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China.

Abstract

Despite its remarkable potential for transforming low-resolution images, deep learning faces significant challenges in achieving high-quality superresolution microscopy imaging from wide-field (conventional) microscopy. Here, we present X-Microscopy, a computational tool comprising two deep learning subnets, UR-Net-8 and X-Net, which enables STORM-like superresolution microscopy image reconstruction from wide-field images with input-size flexibility. X-Microscopy was trained using samples of various subcellular structures, including cytoskeletal filaments, dot-like, beehive-like, and nanocluster-like structures, to generate prediction models capable of producing images of comparable quality to STORM-like images. In addition to enabling multicolour superresolution image reconstructions, X-Microscopy also facilitates superresolution image reconstruction from different conventional microscopic systems. The capabilities of X-Microscopy offer promising prospects for making superresolution microscopy accessible to a broader range of users, going beyond the confines of well-equipped laboratories.

Keywords: Machine learning; Medical imaging; Optical imaging.