AortaSeg-60: an open real-world CT-angiography dataset of the aorta with automated segmentation masks and pathological variability
Dania El Rahal, David C. Rotzinger, Guillaume Fahrni, Guillaume Fahrni, Guillaume Fahrni · 2026
Read AortaSeg-60: an open real-world CT-angiography dataset of the aorta with automated segmentation masks and pathological variability by Dania El Rahal, David C. Rotzinger, Guillaume Fahrni, Guillaume Fahrni, Guillaume Fahrni (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/pmc-13219735.txt.
Description
Dania El Rahal and co-authors release an open scan dataset of the aorta for AI research in a 2026 paper. Sixty real world CT angiography scans cover normal and diseased aortas. Six balanced groups span young and old normals, aneurysms, tears, and varied scan types. Auto generated masks label the aorta in every scan with no hand fixes.
Two radiologists checked group labels and curation quality. Files ship in a standard format under an open license. Uncorrected auto labels let teams test error patterns and refinement tools. Small size and single center origin mark the stated limits. Shared data like this speeds fair comparison of vessel tracing algorithms.
Catalog record
| CREATOR | Dania El Rahal, David C. Rotzinger, Guillaume Fahrni, Guillaume Fahrni, Guillaume Fahrni |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 23 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |