Three-dimensional C-scan-based generation adversarial network with synthetic input to improve optical coherence tomography angiography
It demonstrates that the proposed 3DCS-GAN can greatly improve vascular visualization in the deep layer, provide better image quality than the multiple averaged OCTA images, and achieve superior image enhancement for volumetric OCTA data.
Authors
- Gangyong Jia (ORCID: https://orcid.org/0000-0002-2944-4006)
- Gongpu Lan (ORCID: https://orcid.org/0000-0002-6928-2398)
- Haixia Qiu (ORCID: https://orcid.org/0000-0002-6556-4523)
- Kai Gao (ORCID: https://orcid.org/0000-0002-6638-0793)
- Zhongwu Feng
- Yanping Huang
- Q. M. Jonathan Wu (ORCID: https://orcid.org/0000-0002-5208-7975)
- Peijun Tang (ORCID: https://orcid.org/0000-0003-2647-9913)
- Jingjiang Xu (ORCID: https://orcid.org/0000-0002-0016-5791)
- Jia Qin (ORCID: https://orcid.org/0000-0001-7621-1056)
- Lin An (ORCID: https://orcid.org/0000-0002-4839-0410)
Institutions
- Foshan University (CN)
- Sun Yat-sen University (CN)
- South China Normal University (CN)
- Chinese PLA General Hospital (CN)
- Zhongshan Ophthalmic Center, Sun Yat-sen University
- Hangzhou Dianzi University (CN)
Publication Details
- Journal
- Journal of Biomedical Optics
- Published
- 2025-05-09
- DOI
- https://doi.org/10.1117/1.jbo.30.5.056006
- Primary Topic
- Optical Coherence Tomography Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Basic and Applied Basic Research Foundation of Guangdong Province