Spatial resolution enhancement using deep learning improves chest disease diagnosis based on thick slice CT

Pengxin Yu, Haoyue Zhang, Dawei Wang, Rongguo Zhang, Mei Deng, Haoyu Yang, Lijun Wu, Xiaoxu Liu, Andrea S Oh, Fereidoun G Abtin, Ashley E Prosper, Kathleen Ruchalski, Nana Wang, Huairong Zhang, Ye Li, Xinna Lv, Min Liu, Shaohong Zhao, Dasheng Li, John M Hoffman, Denise R Aberle, Chaoyang Liang, Shou · 2024

Read Spatial resolution enhancement using deep learning improves chest disease diagnosis based on thick slice CT by Pengxin Yu, Haoyue Zhang, Dawei Wang, Rongguo Zhang, Mei Deng, Haoyu Yang, Lijun Wu, Xiaoxu Liu, Andrea S Oh, Fereidoun G Abtin, Ashley E Prosper, Kathleen Ruchalski, Nana Wang, Huairong Zhang, Ye Li, Xinna Lv, Min Liu, Shaohong Zhao, Dasheng Li, John M Hoffman, Denise R Aberle, Chaoyang Liang, Shou (2024) 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-11585608.txt.

Description

Pengxin Yu and a large team of colleagues trained a deep learning system that turns thick-slice chest CT scans into thin-slice ones. Thick slices are cheaper and common, but their coarse detail can hide disease. Writing in twenty twenty-four, the team built a hybrid network mixing convolution and transformer parts, trained it at one center on well over a thousand participants. It then tested the synthetic scans at three other centers on more than a thousand more. Radiologists then read cases with the different scan types.

Judged image quality of synthetic thin slices matched real thin slices. For pneumonia diagnosis, radiologists using synthetic scans beat thick slices and matched real thin slices. For finding lung nodules, synthetic scans also beat thick slices and matched the real thing. The authors present the model as a practical stand-in when true thin slices are unavailable.

Catalog record

CREATORPengxin Yu, Haoyue Zhang, Dawei Wang, Rongguo Zhang, Mei Deng, Haoyu Yang, Lijun Wu, Xiaoxu Liu, Andrea S Oh, Fereidoun G Abtin, Ashley E Prosper, Kathleen Ruchalski, Nana Wang, Huairong Zhang, Ye Li, Xinna Lv, Min Liu, Shaohong Zhao, Dasheng Li, John M Hoffman, Denise R Aberle, Chaoyang Liang, Shou
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE52 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11585608

Browse the full library · About the Tower of Babel