AVSeg-XAI: Deep learning framework for A/V segmentation with vascular features reveals retinal oculomics as biomarker for cardiovascular disease
Syed Abdullah Basit, Tanvir Alam · 2026
Read AVSeg-XAI: Deep learning framework for A/V segmentation with vascular features reveals retinal oculomics as biomarker for cardiovascular disease by Syed Abdullah Basit, Tanvir Alam (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/PMC13527959.txt.
Description
Syed Abdullah Basit and Tanvir Alam present a 2026 deep-learning system that reads retinal photographs to flag cardiovascular risk. The eye's tiny blood vessels mirror the health of vessels elsewhere in the body. Their pipeline first separates arteries from veins in fundus images. It then extracts 34 measures of vessel width, branching, and winding.
Those eye measures were combined with fifteen simple clinical values, such as age, body mass index, and blood pressure. No blood tests were needed. In a Qatar Biobank group the combined model reached an area under the curve of 0.81 for sorting risk. It worked best in women and in people aged 45 to 55. The authors present the tool as a proof of concept for community screening, pending outside validation.
Catalog record
| CREATOR | Syed Abdullah Basit, Tanvir Alam |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 87617 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |