GL-Net: A knowledge-guided Gaussian-gated and layered refinement network for 3D MRI segmentation of brain gliomas

Huimin Lu, Yilong Wang, Han Xue, Guizeng Wang, Jamshid Moradi Kurdestany, Songzhe Ma · 2026

Read GL-Net: A knowledge-guided Gaussian-gated and layered refinement network for 3D MRI segmentation of brain gliomas by Huimin Lu, Yilong Wang, Han Xue, Guizeng Wang, Jamshid Moradi Kurdestany, Songzhe Ma (2026) 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/plos-pone-0351953.txt.

Description

Huimin Lu and colleagues built a neural network to outline brain tumors in three-dimensional MRI scans. Surgeons and radiation teams plan from such maps. The tumor here is glioma, and glioblastoma is its most deadly form. Their model mixes two network styles. It adds a gate that focuses attention where tumors are likely to sit. A second part polishes each tumor region layer by layer. A special scoring rule punishes fuzzy borders.

On two public benchmark sets, the model scored near the top of current methods. It also cut border errors sharply. Border errors are the ones that matter most when a cut or a beam edge is planned. The outlines can also feed standard clinical scoring of tumor features.

Catalog record

CREATORHuimin Lu, Yilong Wang, Han Xue, Guizeng Wang, Jamshid Moradi Kurdestany, Songzhe Ma
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE55697
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0351953

Browse the full library · About the Tower of Babel