Fenqiang Zhao

TL;DR: Using deep learning to augment SIM, a five-fold reduction in the number of raw images required for super-resolution SIM is obtained, and images under extreme low light conditions are generated.

TL;DR: Evaluating tool annotation algorithms based on deep learning for cataract surgery finds that the quality of their annotations are compared to that of human interpretations, and it is expected that they will guide the design of efficient surgery monitoring tools in the near future.

TL;DR: By leveraging the regular and consistent geometric structure of the resampled cortical surface mapped onto the spherical space, a novel convolution filter analogous to the standard convolution on the image grid is proposed, and corresponding operations for convolution, pooling, and transposed convolution for spherical surface data are developed and constructed.

TL;DR: Quantitative evaluation on both synthesized and real infant cortical data demonstrates the superior ability of the proposed cycle-consistent adversarial networks based on spherical cortical surface in removing unwanted scanner effects and preserving individual differences simultaneously, compared to the state-of-the-art methods.

TL;DR: Wang et al. as mentioned in this paper proposed the Spherical Deformable U-Net (SDU-Net) to deform the 1-ring filter on the sphere to adaptively localize cortical structures with different sizes and shapes.