RT Journal Article
SR Electronic
T1 Three-dimensional residual channel attention networks denoise and sharpen fluorescence microscopy image volumes
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.08.27.270439
DO 10.1101/2020.08.27.270439
A1 Jiji Chen
A1 Hideki Sasaki
A1 Hoyin Lai
A1 Yijun Su
A1 Jiamin Liu
A1 Yicong Wu
A1 Alexander Zhovmer
A1 Christian A. Combs
A1 Ivan Rey-Suarez
A1 Hungyu Chang
A1 Chi Chou Huang
A1 Xuesong Li
A1 Min Guo
A1 Srineil Nizambad
A1 Arpita Upadhyaya
A1 Shih-Jong J. Lee
A1 Luciano A.G. Lucas
A1 Hari Shroff
YR 2020
UL http://biorxiv.org/content/early/2020/08/28/2020.08.27.270439.abstract
AB We demonstrate residual channel attention networks (RCAN) for restoring and enhancing volumetric time-lapse (4D) fluorescence microscopy data. First, we modify RCAN to handle image volumes, showing that our network enables denoising competitive with three other state-of-the-art neural networks. We use RCAN to restore noisy 4D super-resolution data, enabling image capture over tens of thousands of images (thousands of volumes) without apparent photobleaching. Second, using simulations we show that RCAN enables class-leading resolution enhancement, superior to other networks. Third, we exploit RCAN for denoising and resolution improvement in confocal microscopy, enabling ∼2.5-fold lateral resolution enhancement using stimulated emission depletion (STED) microscopy ground truth. Fourth, we develop methods to improve spatial resolution in structured illumination microscopy using expansion microscopy ground truth, achieving improvements of ∼1.4-fold laterally and ∼3.4-fold axially. Finally, we characterize the limits of denoising and resolution enhancement, suggesting practical benchmarks for evaluating and further enhancing network performance.Competing Interest StatementH.Sasaki, H.L., H.C., C.C.H., S-J J.L., L.A.G.L. are employees of DRVISION, LLC, a machine vision company. They have developed Aivia (a commercial software platform) that offers the 3D RCAN developed here.