Using deep learning to identify inherited retinal diseases based on wide-field retinal imaging data
Leo Joskowicz, Tim Buchbinder, Eldan Chodorov, Assaf Hoogi, Katherine Matos, Antonio Rivera, Dror Sharon, Eyal Banin · 2026
Read Using deep learning to identify inherited retinal diseases based on wide-field retinal imaging data by Leo Joskowicz, Tim Buchbinder, Eldan Chodorov, Assaf Hoogi, Katherine Matos, Antonio Rivera, Dror Sharon, Eyal Banin (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0348866.txt.
Description
Leo Joskowicz and co-workers train deep learning models to spot inherited eye diseases from wide pictures of the retina. These diseases, passed through families, can be slow to diagnose. Their 2026 study uses records from an Israeli medical center covering just over four hundred patients, pairing two kinds of eye images with genetic test results.
Models given both image types did best at telling diseased eyes from healthy ones. They also sorted patients into groups of likely faulty genes with good accuracy. Results held up across repeated rounds of checking. Image-based screening of this kind could point patients toward the right genetic tests sooner, saving time in clinics that lack eye-genetics experts.
Catalog record
| CREATOR | Leo Joskowicz, Tim Buchbinder, Eldan Chodorov, Assaf Hoogi, Katherine Matos, Antonio Rivera, Dror Sharon, Eyal Banin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35132 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |