Journal of Innovative Optical Health Sciences, Volume. 17, Issue 3, 2350026(2024)

Deep learning-based inpainting of saturation artifacts in optical coherence tomography images

Muyun Hu1,§... Zhuoqun Yuan1,§, Di Yang1, Jingzhu Zhao2 and Yanmei Liang1,* |Show fewer author(s)
Author Affiliations
  • 1Institute of Modern Optics, Nankai University, Tianjin Key Laboratory of Micro-scale Optical Information Science and Technology, Tianjin 300350, China
  • 2Department of Thyroid and Neck Tumor, Tianjin Medical University Cancer Institute and Hospital National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin 300060, China
  • show less

    Limited by the dynamic range of the detector, saturation artifacts usually occur in optical coherence tomography (OCT) imaging for high scattering media. The available methods are difficult to remove saturation artifacts and restore texture completely in OCT images. We proposed a deep learning-based inpainting method of saturation artifacts in this paper. The generation mechanism of saturation artifacts was analyzed, and experimental and simulated datasets were built based on the mechanism. Enhanced super-resolution generative adversarial networks were trained by the clear–saturated phantom image pairs. The perfect reconstructed results of experimental zebrafish and thyroid OCT images proved its feasibility, strong generalization, and robustness.

    Tools

    Get Citation

    Copy Citation Text

    Muyun Hu, Zhuoqun Yuan, Di Yang, Jingzhu Zhao, Yanmei Liang. Deep learning-based inpainting of saturation artifacts in optical coherence tomography images[J]. Journal of Innovative Optical Health Sciences, 2024, 17(3): 2350026

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Research Articles

    Received: Aug. 17, 2023

    Accepted: Oct. 4, 2023

    Published Online: Apr. 26, 2024

    The Author Email: Liang Yanmei (ymliang@nankai.edu.cn)

    DOI:10.1142/S1793545823500268

    Topics