Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement: An overview from a signal processing perspective.
Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement: An overview from a signal processing perspective.
复制标题
生物图像重建和增强的无监督深度学习方法：从信号处理的角度综述。
DOI：
10.1109/msp.2021.3119273
复制
发表时间：
2022-03
影响因子：
14.9
通讯作者：
Ye, Jong Chul
中科院分区：
文献类型：
--
作者：
Akcakaya, Mehmet;Yaman, Burhaneddin;Chung, Hyungjin;Ye, Jong Chul
关键词：
近年来，深度学习方法因其高性能和超快的推理时间而成为生物图像重建和增强问题的主要研究前沿。然而，由于监督学习很难获得匹配的参考数据，人们对不需要配对参考数据的无监督学习方法越来越感兴趣。特别是，自监督学习和生成模型已成功用于各种生物成像应用。在本文中，我们在经典逆问题的背景下从连贯的角度概述了这些方法，并讨论了它们在生物成像中的应用，包括电子、荧光和反卷积显微镜、光学衍射断层扫描和功能神经成像。
Recently, deep learning approaches have become the main research frontier for biological image reconstruction and enhancement problems thanks to their high performance, along with their ultra-fast inference times. However, due to the difficulty of obtaining matched reference data for supervised learning, there has been increasing interest in unsupervised learning approaches that do not need paired reference data. In particular, self-supervised learning and generative models have been successfully used for various biological imaging applications. In this paper, we overview these approaches from a coherent perspective in the context of classical inverse problems, and discuss their applications to biological imaging, including electron, fluorescence and deconvolution microscopy, optical diffraction tomography and functional neuroimaging.
登录
查看更多内容
影响因子：
2.6
作者：
Krull, Alexander;Vicar, Tomas;Jug, Florian
通讯作者：
Jug, Florian
DOI：
10.1109/jstsp.2020.2998402
发表时间：
2020-10-01
影响因子：
7.5
作者：
Liu, Jiaming;Sun, Yu;Kamilov, Ulugbek S.
通讯作者：
Kamilov, Ulugbek S.
影响因子：
5.4
作者：
Gupta, Harshit;McCann, Michael T.;Unser, Michael
通讯作者：
Unser, Michael
影响因子：
10.4
作者：
Nehme, Elias;Weiss, Lucien E.;Shechtman, Yoav
通讯作者：
Shechtman, Yoav
影响因子：
10.4
作者：
Bostan, Emrah;Heckel, Reinhard;Waller, Laura
通讯作者：
Waller, Laura