Improved generative adversarial networks using the total gradient loss for the resolution enhancement of fluorescence images

Chong Zhang; Kun Wang; Yu An; Kunshan He; Tong Tong; Jie Tian

doi:10.1364/BOE.10.004742

Improved generative adversarial networks using the total gradient loss for the resolution enhancement of fluorescence images

Biomed Opt Express. 2019 Aug 22;10(9):4742-4756. doi: 10.1364/BOE.10.004742. eCollection 2019 Sep 1.

Authors

Chong Zhang^{1

2

3

4}, Kun Wang^{1

2

3

4

5}, Yu An^{1

2

3}, Kunshan He^{1

2

3}, Tong Tong^{1

2

3}, Jie Tian^{1

2

3

6}

Affiliations

¹ CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
² School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China.
³ Beijing Key Laboratory of Molecular Imaging, Beijing 100190, China.
⁴ Authors contributed equally to this article.
⁵ kun.wang@ia.ac.cn.
⁶ BUAA-CCMU Advanced Innovation Center for Big Data-Based Precision Medicine, Beijing 100083, China.

Abstract

Because of the optical properties of medical fluorescence images (FIs) and hardware limitations, light scattering and diffraction constrain the image quality and resolution. In contrast to device-based approaches, we developed a post-processing method for FI resolution enhancement by employing improved generative adversarial networks. To overcome the drawback of fake texture generation, we proposed total gradient loss for network training. Fine-tuning training procedure was applied to further improve the network architecture. Finally, a more agreeable network for resolution enhancement was applied to actual FIs to produce sharper and clearer boundaries than in the original images.