Glaucoma detection in myopic eyes using deep learning autoencoder-based regions of interest
The dual autoencoder model, which integrates reconstruction errors from both healthy and glaucomatous training data, demonstrated superior diagnostic accuracy compared to the single autoencoder model, global RNFL thickness and texture enface-based approaches. These findings suggest that deep learning models leveraging ROI-based reconstruction error from texture enface images may enhance glaucoma classification in myopic eyes, providing a robust alternative to conventional structural thickness metrics.
Authors
- Aiko Iwase (ORCID: https://orcid.org/0000-0001-5950-4260)
- Christopher Bowd (ORCID: https://orcid.org/0000-0001-9330-9987)
- Hitomi Saito (ORCID: https://orcid.org/0000-0002-8587-6081)
- Mark Christopher (ORCID: https://orcid.org/0000-0001-6165-6175)
- Toru Nakazawa (ORCID: https://orcid.org/0000-0002-5591-4155)
- Kyoko Ohno‐Matsui (ORCID: https://orcid.org/0000-0002-8375-6879)
- Robert Neal Weinreb (ORCID: https://orcid.org/0000-0001-9553-3202)
- Tsutomu Kikawa (ORCID: https://orcid.org/0000-0002-0144-096X)
- Makoto Aihara (ORCID: https://orcid.org/0000-0001-6810-0583)
- Linda M. Zangwill (ORCID: https://orcid.org/0000-0002-1143-5224)
- Makoto Araie (ORCID: https://orcid.org/0000-0001-9025-3973)
- Tomomi Higashide (ORCID: https://orcid.org/0000-0001-9566-4587)
- Christopher Kai-Shun Leung (ORCID: https://orcid.org/0000-0003-4862-777X)
- Tae‐Woo Kim (ORCID: https://orcid.org/0000-0002-5180-0978)
- Goji Tomita
- Kazuhisa Sugiyama
- Atsuya Miki
- Akram Belghith
- Hiroshi Murata (ORCID: https://orcid.org/0000-0001-8004-991X)
Institutions
- Kanazawa University (JP)
- Tokyo Medical and Dental University (JP)
- Fleet Science Center (US)
- Toho University (JP)
- Aichi Medical University (JP)
- Tohoku University (JP)
- Seoul National University Bundang Hospital (KR)
- Osaka City University (JP)
- Gifu Prefectural Tajimi Hospital (JP)
- Toho University Ohashi Medical Center (JP)
- National Center for Global Health and Medicine (JP)
- University of Tokyo Hospital (JP)
- Kanto Central Hospital (JP)
- Topcon (Japan) (JP)
- The University of Tokyo (JP)
- University of Hong Kong (HK)
Publication Details
- Journal
- Frontiers in Ophthalmology
- Published
- 2025-08-04
- DOI
- https://doi.org/10.3389/fopht.2025.1624015
- Citations
- 1
- Primary Topic
- Glaucoma and retinal disorders
- Type
- article
- Field-Weighted Citation Impact
- 1.71
Funders
- Council for Science, Technology and Innovation
- National Eye Institute