AmygdalaGo-BOLT for boundary-aware segmentation of the human amygdala
Quan Zhou, Bo Dong, Peng Gao, Jintao Wei, Jiale Xiao, Wei Wang, Peipeng Liang, Danhua Lin, Jie Lu, Xi-Nian Zuo, Hongjian He · 2026
Read AmygdalaGo-BOLT for boundary-aware segmentation of the human amygdala by Quan Zhou, Bo Dong, Peng Gao, Jintao Wei, Jiale Xiao, Wei Wang, Peipeng Liang, Danhua Lin, Jie Lu, Xi-Nian Zuo, Hongjian He (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/pmc-13390094.txt.
Description
Quan Zhou's team built AmygdalaGo-BOLT, a deep-learning model that traces the amygdala's boundaries in brain scans, a small and intricately shaped structure that manual tracing struggles to delineate, especially in children. Large developmental studies now collect thousands of scans, making manual segmentation impractical.
Trained and validated on 1,086 hand-labelled paediatric MRI scans, the compact encoder-decoder model blends multi-scale traits, spatial priors, and self-focus to sharpen boundary detection. It agreed strongly with expert tracings across centres and age groups while beating existing tools on hit rate and speed, enabling group-scale studies of amygdala development.
Catalog record
| CREATOR | Quan Zhou, Bo Dong, Peng Gao, Jintao Wei, Jiale Xiao, Wei Wang, Peipeng Liang, Danhua Lin, Jie Lu, Xi-Nian Zuo, Hongjian He |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 73 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |