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

TL;DR

This paper introduces MFPINet, a fast deep learning model that reconstructs high-resolution multi-focal plane images from a single low-resolution 2D image, significantly accelerating 3D medical imaging.

Contribution

The paper presents a novel end-to-end generative adversarial network that reconstructs multi-focal plane images without scanning, achieving high speed and quality.

Findings

MFPINet performs well on cytology microscopy images.

It is approximately 24 times faster than existing methods.

It effectively refocuses and enhances resolution in 3D images.

Abstract

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