Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer

Autor:	Sungjun Lim, Sunghoe Chang, Sangeun Lee, Jong Chul Ye
Rok vydání:	2019
Předmět:	Point spread function Blind deconvolution Artificial neural network Computer science Robustness (computer science) Microscopy ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Iterative reconstruction Deconvolution Algorithm
Zdroj:	Machine Learning for Medical Image Reconstruction ISBN: 9783030338428 MLMIR@MICCAI
DOI:	10.1007/978-3-030-33843-5_16
Popis:	Deconvolution microscopy has been extensively used to improve the resolution of the widefield fluorescent microscopy. Conventional approaches, which usually require the point spread function (PSF) measurement or blind estimation, are however computationally expensive. Recently, CNN based approaches have been explored as a fast and high performance alternative. In this paper, we present a novel unsupervised deep neural network for blind deconvolution based on cycle consistency and PSF modeling layers. In contrast to the recent CNN approaches for similar problem, the explicit PSF modeling layers improve the robustness of the algorithm. Experimental results confirm the efficacy of the algorithm.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::e5251cee5c73cef966fb16b827314f83 https://doi.org/10.1007/978-3-030-33843-5_16 Zobrazit plný text záznamu