Self-Reflective Chest X-Ray Report Generation with Clinical-Aware Detection and Multilevel Readability

Juhyuk Han, Minjae Kim, Yeonwoo Kim, Won Hee Lee · 2025

Read Self-Reflective Chest X-Ray Report Generation with Clinical-Aware Detection and Multilevel Readability by Juhyuk Han, Minjae Kim, Yeonwoo Kim, Won Hee Lee (2025) 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-12743066.txt.

Description

Chest X-ray reports must be exact for doctors yet readable for patients, and one system now drafts them at several reading levels. Juhyuk Han and co-authors built and tested that system in this 2025 paper. Their framework first finds and locates problems on the scan, then writes the report, then checks its own work.

A detection method pairs a finding classifier with heat maps that show where each finding sits. A large vision-language model turns those results into report text. A self-check step then adjusts the wording for the target reader while keeping the medical facts intact. The authors also propose scoring methods that weigh accuracy and readability together, a balance hospitals will need as auto-written reports spread.

Catalog record

CREATORJuhyuk Han, Minjae Kim, Yeonwoo Kim, Won Hee Lee
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE60 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12743066

Browse the full library · About the Tower of Babel