Reconstruct high-resolution multi-focal plane images from a single 2D wide field image

摘要: High-resolution 3D medical images are important for analysis and diagnosis, but axial scanning to acquire them is very time-consuming. In this paper, we propose a fast end-to-end multi-focal plane imaging network (MFPINet) reconstruct high-resolution from single 2D low-resolution wild filed image without relying on scanning. To realistic MFP fast, the proposed MFPINet adopts generative adversarial framework strategies of post-sampling refocusing all focal planes at one time. We conduct series experiments cytology microscopy demonstrate that performs well both horizontal super resolution. Furthermore, approximately 24 times faster than current methods reconstructing same volume images. The method has potential greatly increase speed expand application wide-field