Deep learning-driven multi-view multi-task image quality assessment method for chest CT image

Jialin Su, Meifang Li, Yongping Lin, Liu Xiong, Caixing Yuan, Zhimin Zhou, Kunlong Yan · 2023

Read Deep learning-driven multi-view multi-task image quality assessment method for chest CT image by Jialin Su, Meifang Li, Yongping Lin, Liu Xiong, Caixing Yuan, Zhimin Zhou, Kunlong Yan (2023) 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-10701985.txt.

Description

Jialin Su and co-authors present a 2023 method that grades chest scan quality with deep learning before doctors read the scans. Poor scan quality can skew a diagnosis, yet hand grading is slow and can drift with tiredness or bias. A sound auto grader could flag bad scans early and save staff time.

The method fuses three view planes of each scan and grades four points: breath hold, body pose, shielding from rays, and flaws. Four custom tools each fit one grading task. In a held-out test set from 41 patients, the method hit 87 in 100 precision and a high score on a joint quality mark. Side tests showed each tool helped and that the method held up across tasks.

Catalog record

CREATORJialin Su, Meifang Li, Yongping Lin, Liu Xiong, Caixing Yuan, Zhimin Zhou, Kunlong Yan
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE116 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10701985

Browse the full library · About the Tower of Babel