Guy M Hagen1, Justin Bendesky1, Rosa Machado1, Tram-Anh Nguyen2, Tanmay Kumar3, Jonathan Ventura3. 1. UCCS BioFrontiers Center, University of Colorado at Colorado Springs, 1420 Austin Bluffs Parkway, Colorado Springs, CO 80918, USA. 2. George Mason University, 4400 University Drive, Fairfax, VA 22030, USA. 3. Department of Computer Science and Software Engineering, California Polytechnic State University, San Luis Obispo, CA 93407, USA.
Abstract
BACKGROUND: Fluorescence microscopy is an important technique in many areas of biological research. Two factors that limit the usefulness and performance of fluorescence microscopy are photobleaching of fluorescent probes during imaging and, when imaging live cells, phototoxicity caused by light exposure. Recently developed methods in machine learning are able to greatly improve the signal-to-noise ratio of acquired images. This allows researchers to record images with much shorter exposure times, which in turn minimizes photobleaching and phototoxicity by reducing the dose of light reaching the sample. FINDINGS: To use deep learning methods, a large amount of data is needed to train the underlying convolutional neural network. One way to do this involves use of pairs of fluorescence microscopy images acquired with long and short exposure times. We provide high-quality datasets that can be used to train and evaluate deep learning methods under development. CONCLUSION: The availability of high-quality data is vital for training convolutional neural networks that are used in current machine learning approaches.
BACKGROUND: Fluorescence microscopy is an important technique in many areas of biological research. Two factors that limit the usefulness and performance of fluorescence microscopy are photobleaching of fluorescent probes during imaging and, when imaging live cells, phototoxicity caused by light exposure. Recently developed methods in machine learning are able to greatly improve the signal-to-noise ratio of acquired images. This allows researchers to record images with much shorter exposure times, which in turn minimizes photobleaching and phototoxicity by reducing the dose of light reaching the sample. FINDINGS: To use deep learning methods, a large amount of data is needed to train the underlying convolutional neural network. One way to do this involves use of pairs of fluorescence microscopy images acquired with long and short exposure times. We provide high-quality datasets that can be used to train and evaluate deep learning methods under development. CONCLUSION: The availability of high-quality data is vital for training convolutional neural networks that are used in current machine learning approaches.
Authors: R A Hoebe; C H Van Oven; T W J Gadella; P B Dhonukshe; C J F Van Noorden; E M M Manders Journal: Nat Biotechnol Date: 2007-01-21 Impact factor: 54.908
Authors: Alexey M Bogdanov; Ekaterina A Bogdanova; Dmitriy M Chudakov; Tatiana V Gorodnicheva; Sergey Lukyanov; Konstantin A Lukyanov Journal: Nat Methods Date: 2009-12 Impact factor: 28.547
Authors: Jérôme Boulanger; Charles Kervrann; Patrick Bouthemy; Peter Elbau; Jean-Baptiste Sibarita; Jean Salamero Journal: IEEE Trans Med Imaging Date: 2009-11-06 Impact factor: 10.048