Enhancing resolution and image quality in musculoskeletal MRI using deep learning reconstruction
Marco Porta, Giuseppe Agresti, Maria Marcella Laganà, Stefano Orofino, Sara Pangaro, Nicola Carapella, Pietro Andrea Bonaffini, Paolo Bernasconi, Eugenio Annibale Genovese, Sandro Sironi, Alberto Aliprandi · 2026
Read Enhancing resolution and image quality in musculoskeletal MRI using deep learning reconstruction by Marco Porta, Giuseppe Agresti, Maria Marcella Laganà, Stefano Orofino, Sara Pangaro, Nicola Carapella, Pietro Andrea Bonaffini, Paolo Bernasconi, Eugenio Annibale Genovese, Sandro Sironi, Alberto Aliprandi (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-13219709.txt.
Description
Marco Porta and colleagues test whether deep learning reconstruction can sharpen musculoskeletal MRI while shortening the scan in a 2026 study. MRI faces a trade-off among speed, sharpness, and noise, and reconstruction promises to break it by cleaning images. The team built the method into a 1.5-tesla scanner protocol for joints.
Thirty-nine examinations of knees, shoulders, ankles, and hips were analyzed twice: once as sequences and once as higher-resolution sequences rebuilt with deep learning. Three readers, blinded to the version, rated the visibility of structures, and a fourth measured signal and contrast in bone and muscle. The deep learning versions used smaller pixels and finished faster, readers agreed more when scoring them, and every structure was rated visible or better. Measured signal and contrast held steady rather than dropping. The authors conclude the reconstruction buys resolution and time in joint imaging without paying for them in quality.
Catalog record
| CREATOR | Marco Porta, Giuseppe Agresti, Maria Marcella Laganà, Stefano Orofino, Sara Pangaro, Nicola Carapella, Pietro Andrea Bonaffini, Paolo Bernasconi, Eugenio Annibale Genovese, Sandro Sironi, Alberto Aliprandi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |