哈尔滨工业大学赵唯淞团队发现，自启发学习可用于去噪活细胞超分辨率显微镜。这一研究成果于2024年9月11日在线发表在国际学术期刊《自然—方法学》上。

研究人员描述了一种高效利用数据的深度学习去噪解决方案，以改进多种超分辨率（SR）成像模式。该方法（SN2N）是一种自启发的Noise2Noise模块，具有自监督数据生成和自约束学习过程。

SN2N与监督学习方法完全具备竞争力，并且无需大型训练集和干净的真实数据，只需单个噪声帧即可进行训练。

研究人员展示了SN2N能够将光子效率提高一至两个数量级，并且兼容多种成像模式，用于体积、彩色和时间推移的SR显微镜。

研究人员还将SN2N整合到不同的SR重建算法中，有效减轻了图像伪影。研究人员预计SN2N将改善活细胞SR成像，并激发进一步的技术进步。

据了解，在活细胞SR显微镜中，每个收集到的光子都至关重要。

附：英文原文

Title: Self-inspired learning for denoising live-cell super-resolution microscopy

Author: Qu, Liying, Zhao, Shiqun, Huang, Yuanyuan, Ye, Xianxin, Wang, Kunhao, Liu, Yuzhen, Liu, Xianming, Mao, Heng, Hu, Guangwei, Chen, Wei, Guo, Changliang, He, Jiaye, Tan, Jiubin, Li, Haoyu, Chen, Liangyi, Zhao, Weisong

Issue&Volume: 2024-09-11

Abstract: Every collected photon is precious in live-cell super-resolution (SR) microscopy. Here, we describe a data-efficient, deep learning-based denoising solution to improve diverse SR imaging modalities. The method, SN2N, is a Self-inspired Noise2Noise module with self-supervised data generation and self-constrained learning process. SN2N is fully competitive with supervised learning methods and circumvents the need for large training set and clean ground truth, requiring only a single noisy frame for training. We show that SN2N improves photon efficiency by one-to-two orders of magnitude and is compatible with multiple imaging modalities for volumetric, multicolor, time-lapse SR microscopy. We further integrated SN2N into different SR reconstruction algorithms to effectively mitigate image artifacts. We anticipate SN2N will enable improved live-SR imaging and inspire further advances.

DOI: 10.1038/s41592-024-02400-9

Source: https://www.nature.com/articles/s41592-024-02400-9