Clinical feasibility and image quality assessment of deep learning-based virtual contrast enhancement from photon-counting computed tomography
Julien G. Cohen, Joel Valentin Stadelmann, David Leite-Arada, Pierre-Alexandre Poletti · 2026
Read Clinical feasibility and image quality assessment of deep learning-based virtual contrast enhancement from photon-counting computed tomography by Julien G. Cohen, Joel Valentin Stadelmann, David Leite-Arada, Pierre-Alexandre Poletti (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-13633510.txt.
Description
Julien Cohen and co-authors test AI made contrast images for a new kind of CT scan. Contrast dye sharpens CT views, but it carries risks and costs. Photon counting scanners capture rich data that may let software fake the dye effect. The team trained a network on scans from forty patients, half held back for testing.
On paper scores, the fake images matched the real ones closely. Human readers were less kind, rating the fakes lower overall. Chest vessels and heart chambers often still passed as fit for diagnosis. Belly organs fared worse, with patchy fake enhancement. The authors call the method feasible, with the chest the promising front.
Catalog record
| CREATOR | Julien G. Cohen, Joel Valentin Stadelmann, David Leite-Arada, Pierre-Alexandre Poletti |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |