Single shot machine learning based phase retrieval for the X-ray phase imaging

The phase contrast image has higher sensitivity to materials with light elements than the conventional absorption contrast. The phase image is obtained by computer processing of the measured fringe image. The Fourier transform method is known as a method to obtain a phase image from a single fringe image. However, the method cannot produce images with high spatial resolution. In this study, we present a method to obtain phase images with high spatial resolution using machine learning.