Extended Data Fig. 6: Comparison of RL-DFN with its variant architectures. | Nature Methods

Extended Data Fig. 6: Comparison of RL-DFN with its variant architectures.

From: Fast-adaptive super-resolution lattice light-sheet microscopy for rapid, long-term, near-isotropic subcellular imaging

Extended Data Fig. 6

a–c, Schematic of three compared network architectures, that is, RL-DFN (a), DFN (b), and RLN-DFN (c). Details of the RL deconvolution module and rotation sectioning module are schematically illustrated. d-g, Reconstruction results of F-actin images using multi-view RL deconvolution (d), RLN-DFN (e), DFN (f), and RL-DFN (g). x-y MIPs and two different x-z slices along the dashed arrows are shown. Scale bars, 3 μm (full FOV images in d-g) and 1 μm (magnified regions in d-g).

Back to article page