Detection of cystoid macular edema in patients with retinitis pigmentosa based on deep learning
This study was the first to apply DL algorithms to diagnose and manage CME in RP patients using OCT images. Pretrained ResNet models, particularly ResNet-34 with 99.25% accuracy, outperformed non-pretrained ResNet-34 with 80.64% accuracy. These results underscore the potential of pretrained models to aid in detection CME and supporting remote healthcare services.
Authors
- Hamid Ahmadieh (ORCID: https://orcid.org/0000-0002-8139-2661)
- Farshad Hosseini
- Sahba Fekri (ORCID: https://orcid.org/0000-0002-7388-6725)
- Hamideh Sabbaghi
- Reza Rabiei (ORCID: https://orcid.org/0000-0003-0771-7306)
- Firouze Hatami (ORCID: https://orcid.org/0000-0003-0450-0961)
- Farkhondeh Asadi (ORCID: https://orcid.org/0000-0003-0939-7983)
- Arash Roshanpoor (ORCID: https://orcid.org/0000-0001-6698-715X)
- Morteza Naderan (ORCID: https://orcid.org/0000-0003-4409-1533)
- Fatemeh Rostami (ORCID: https://orcid.org/0000-0002-0992-6227)
- Rayan Ebnali Harari
- Mahdi Yazdanpanah
Institutions
- Islamic Azad University, Tehran (IR)
- Harvard University (US)
- Amirkabir University of Technology (IR)
- Harvard University Press (US)
- Research Institute for Endocrine Sciences (IR)
- Mass General Brigham (US)
- Shahid Beheshti University of Medical Sciences (IR)
Publication Details
- Journal
- International Journal of Retina and Vitreous
- Published
- 2025-12-24
- DOI
- https://doi.org/10.1186/s40942-025-00762-6
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00