Improved Generative Adversarial Networks Using the Total Gradient Loss for the Resolution Enhancement of Fluorescence Images
Overview
Authors
Affiliations
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.
Qiu W, Liu J, He K, Hu G, Mei S, Guan X Surg Endosc. 2024; 38(9):5446-5456.
PMID: 39090199 DOI: 10.1007/s00464-024-11085-2.
A review of the application of machine learning in molecular imaging.
Yin L, Cao Z, Wang K, Tian J, Yang X, Zhang J Ann Transl Med. 2021; 9(9):825.
PMID: 34268438 PMC: 8246214. DOI: 10.21037/atm-20-5877.
Pradhan P, Meyer T, Vieth M, Stallmach A, Waldner M, Schmitt M Biomed Opt Express. 2021; 12(4):2280-2298.
PMID: 33996229 PMC: 8086483. DOI: 10.1364/BOE.415962.