Robust Automated Mouse Micro-CT Segmentation Using Swin UNEt TRansformers

Lu Jiang, Di Xu, Qifan Xu, Arion Chatziioannou, Keisuke S Iwamoto, Susanta Hui, Ke Sheng, Muneer Ahmad · 2024

Read Robust Automated Mouse Micro-CT Segmentation Using Swin UNEt TRansformers by Lu Jiang, Di Xu, Qifan Xu, Arion Chatziioannou, Keisuke S Iwamoto, Susanta Hui, Ke Sheng, Muneer Ahmad (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-11673508.txt.

Description

Before radiation treatments reach patients, they are tested in mice, and researchers must outline mouse organs on scans by hand unless software can do it. Lu Jiang and co-authors test a transformer-based model for that outlining job in this 2024 paper. The model reads small-animal CT scans and draws the organs, on both plain scans and scans with contrast dye.

The model, a Swin transformer design, was trained on public mouse data sets split by individual mouse. It beat two rival methods on overlap and border accuracy in nearly every organ tested. A second test used scans from a different machine with more noise, the kind of shift that often breaks such tools. The model held up best there too, which the authors say makes it fit for routine lab contouring work.

Catalog record

CREATORLu Jiang, Di Xu, Qifan Xu, Arion Chatziioannou, Keisuke S Iwamoto, Susanta Hui, Ke Sheng, Muneer Ahmad
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE39 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11673508

Browse the full library · About the Tower of Babel