1 code implementation • 27 Apr 2020 • Fangliang Bai, Jinchao Liu, Xiaojuan Liu, Margarita Osadchy, Chao Wang, Stuart J. Gibson
However, to date, there have been two major drawbacks: (1) the high-precision real-valued sensing patterns proposed in the majority of existing works can prove problematic when used with computational imaging hardware such as a digital micromirror sampling device and (2) the network structures for image reconstruction involve intensive computation, which is also not suitable for hardware deployment.
no code implementations • 15 Sep 2017 • Fangliang Bai, Manuel J. Marques, Stuart J. Gibson
As a first step, the framework trains the FCN model to extract features from retinal layers in OCT images, which exhibit CME, and then segments CME regions using the trained model.