Pulmonary ventilation images from planning CT images using deep learning on locally‐advanced NSCLC patients

Yoshiyuki Katsuta, Taichi Hoshino, Takaya Yamamoto, Noriyuki Kadoya, Shohei Tanaka, Kazuhiro Arai, Rei Umezawa, Noriyoshi Takahashi, Keiichi Jingu · 2026

Read Pulmonary ventilation images from planning CT images using deep learning on locally‐advanced NSCLC patients by Yoshiyuki Katsuta, Taichi Hoshino, Takaya Yamamoto, Noriyuki Kadoya, Shohei Tanaka, Kazuhiro Arai, Rei Umezawa, Noriyoshi Takahashi, Keiichi Jingu (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-13525193.txt.

Description

Yoshiyuki Katsuta and co-authors generate lung ventilation images from standard planning scans with deep learning in a 2026 study. Ventilation maps guide lung sparing radiation plans that steer dose away from working lung regions. Standard maps need extra four dimensional scans, so the team asked whether a network could infer them from the planning scan alone.

The cohort held 102 patients with locally advanced lung cancer treated from 2014 to 2023. A tuned U-net model was trained with cross validation and compared with maps built from the full scan set. Scores averaged a rank correlation of 0.77, with region overlap measures also reported. The approach could cut imaging burden in daily planning.

Catalog record

CREATORYoshiyuki Katsuta, Taichi Hoshino, Takaya Yamamoto, Noriyuki Kadoya, Shohei Tanaka, Kazuhiro Arai, Rei Umezawa, Noriyoshi Takahashi, Keiichi Jingu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE29 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13525193

Browse the full library · About the Tower of Babel