Fluorescence microscopy datasets for training deep neural networks

• Published in: Gigascience 2021-05, Vol.10 (5)
• Main Authors: Hagen, Guy M, Bendesky, Justin, Machado, Rosa, Nguyen, Tram-Anh, Kumar, Tanmay, Ventura, Jonathan
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Data Note; Datasets; Deep learning; Exposure; Fluorescence microscopy; Fluorescent Dyes; Fluorescent indicators; Image acquisition; Image Processing, Computer-Assisted; Learning algorithms; Machine Learning; Microscopy; Microscopy, Fluorescence; Neural networks; Neural Networks, Computer; Photobleaching; Photochemical reactions; Phototoxicity; Signal to noise ratio; Training
• ISSN: 2047-217X; 2047-217X
• DOI: 10.1093/gigascience/giab032

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.