St-RegSeg: an unsupervised registration-based framework for multimodal magnetic resonance imaging stroke lesion segmentation

Chengzhi Gui, Xingwei An, Tingting Li, Shuang Liu, Dong Ming · 2024

Read St-RegSeg: an unsupervised registration-based framework for multimodal magnetic resonance imaging stroke lesion segmentation by Chengzhi Gui, Xingwei An, Tingting Li, Shuang Liu, Dong Ming (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-11651977.txt.

Description

Finding a stroke lesion on MRI quickly and precisely guides urgent treatment, but scans come in several modes that must be aligned before a computer can outline the damage. Chengzhi Gui and four co-authors build St-RegSeg, a framework that registers multimodal scans without supervision and then segments the lesion with a proven network.

On a three-center challenge dataset, their registration beat the standard tool combination clearly: overlap scores rose about 25 percent and image errors fell. Segmentation accuracy improved modestly, while the whole pipeline ran about 41 times faster than the standard pairing. Against a newer rival it still won on both accuracy and speed. The authors offer the framework as a practical step toward faster stroke imaging workflows. The study appears in 2024.

Catalog record

CREATORChengzhi Gui, Xingwei An, Tingting Li, Shuang Liu, Dong Ming
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE54 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11651977

Browse the full library · About the Tower of Babel