Comparison of MRI T2 FLAIR White Matter Hyperintensity Segmentation Algorithms in Clinical Trials

Norman Scheel, Josh Hubert, Joshua H. Baker, Zachary Fernandez, Pavel G. Yanev, Ann M Stowe, Wanpen Vongpatanasin, Rong Zhang, David C Zhu · 2025

Read Comparison of MRI T2 FLAIR White Matter Hyperintensity Segmentation Algorithms in Clinical Trials by Norman Scheel, Josh Hubert, Joshua H. Baker, Zachary Fernandez, Pavel G. Yanev, Ann M Stowe, Wanpen Vongpatanasin, Rong Zhang, David C Zhu (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-11716330.txt.

Description

Scheel and co-authors compare computer programs that outline bright scars in brain scans, a marker of small-vessel disease tied to stroke and memory loss. Hand tracing is slow and biased, so trials need trustworthy automation. The team ran four leading algorithms over more than 700 subjects from two trials and a public challenge set, then had blinded experts grade the results.

The challenge-trained programs beat the classic method, catching small lesions far from the ventricles, with one called PGS rated best. A scanning detail mattered: fat saturation changed image contrast and hurt accuracy, so settings must be reported. The authors note shape and change over time may prove better markers than volume alone.

Catalog record

CREATORNorman Scheel, Josh Hubert, Joshua H. Baker, Zachary Fernandez, Pavel G. Yanev, Ann M Stowe, Wanpen Vongpatanasin, Rong Zhang, David C Zhu
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE3 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11716330

Browse the full library · About the Tower of Babel