Prediction of pancreatic neuroendocrine tumor grading using an artificial intelligence–based video analysis model (GradAINet) applied to contrast-enhanced EUS videos
Matteo Tacelli, Adrien Meyer, Gaetano Lauri, Armine Vardazaryan, Paolo Biamonte, Bastien Andlauer, Rubino Nunziata, Gabriele Capurso, Leonardo Sosa-Valencia, Nicolas Padoy, Paolo Giorgio Arcidiacono · 2026
Read Prediction of pancreatic neuroendocrine tumor grading using an artificial intelligence–based video analysis model (GradAINet) applied to contrast-enhanced EUS videos by Matteo Tacelli, Adrien Meyer, Gaetano Lauri, Armine Vardazaryan, Paolo Biamonte, Bastien Andlauer, Rubino Nunziata, Gabriele Capurso, Leonardo Sosa-Valencia, Nicolas Padoy, Paolo Giorgio Arcidiacono (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-13400049.txt.
Description
Matteo Tacelli and nine co-authors built an AI model in two thousand twenty-six to grade pancreatic neuroendocrine tumours from ultrasound video. Grade, set by cell division counts, drives care choices, yet needle sampling misgrades up to a quarter of cases. Their model, GradAINet, reads contrast-enhanced endoscopic ultrasound recordings instead.
The study drew one hundred fifteen patients from a Milan centre of excellence. More than two hundred fifty thousand video frames were split into training, validation, and test sets. The model reached a sensitivity of zero point eight for spotting higher-grade tumours in the reported results. The team presents video AI as a support for grading, not a swap for tissue proof.
Catalog record
| CREATOR | Matteo Tacelli, Adrien Meyer, Gaetano Lauri, Armine Vardazaryan, Paolo Biamonte, Bastien Andlauer, Rubino Nunziata, Gabriele Capurso, Leonardo Sosa-Valencia, Nicolas Padoy, Paolo Giorgio Arcidiacono |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 26 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |