Domain Generalization in Restoration of Cataract Fundus Images Via High-Frequency Components

Haofeng Liu, Heng Li, Mingyang Ou, Yitian Zhao, Hong Qi, Yan Hu, Jiang Liu

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Cataracts are the most common blinding disease, and also impact the observation of the fundus. To boost the fundus examination of cataract patients, restoration algorithms have been proposed to address the degradation of fundus images caused by cataracts. However, it is impractical in clinics to collect paired or annotated fundus images for developing restoration models. In this paper, a restoration algorithm is designed for cataractous images without paired or annotated data. Domain generalization (DG) is applied to learn domain-invariant features (DIFs) from synthesized data, and the high-frequency components (HFCs) are extracted to conduct domain alignment. The proposed algorithm is used on unseen target data in the experiments. The effectiveness of the algorithm is demonstrated in the ablation study and compared with state-of-the-art methods. The code of this paper will be released at https://github.com/HeverLaw/Restoration-of-Cataract-Images-via-Domain-Generalization.

Original languageEnglish
Title of host publicationISBI 2022 - Proceedings
Subtitle of host publication2022 IEEE International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
ISBN (Electronic)9781665429238
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 - Kolkata, India
Duration: 28 Mar 202231 Mar 2022

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2022-March
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference19th IEEE International Symposium on Biomedical Imaging, ISBI 2022
Country/TerritoryIndia
CityKolkata
Period28/03/2231/03/22

Keywords

  • Cataract
  • domain generalization
  • domain-invariant features
  • image restoration

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Domain Generalization in Restoration of Cataract Fundus Images Via High-Frequency Components'. Together they form a unique fingerprint.

Cite this