Incorporating the image formation process into deep learning improves network performance in deconvolution applications
Y. Li, Y. Su, M. Guo, X. Han, J. Liu, H. Vishwasrao, X. Li, R. Christensen, T. Sengupta, M. Moyle, J. Chen, T. B. Usdin, D. Colon-Ramos, H. Liu, Y. Wu, H. Shroff
This paper introduces RLN, a deep learning method for 3D fluorescence microscopy deconvolution that improves speed, performance, and generalizability compared to existing methods.
bioRxiv · Mar 5, 2022 · PreprintBiophysics