DDANet: A deep dilated attention network for intracerebral haemorrhage segmentation
Haiyan Liu, Yu Zeng, Hao Li, Fuxin Wang, Jianjun Chang, Huaping Guo, Jian Zhang · 2024
Read DDANet: A deep dilated attention network for intracerebral haemorrhage segmentation by Haiyan Liu, Yu Zeng, Hao Li, Fuxin Wang, Jianjun Chang, Huaping Guo, Jian Zhang (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-11665844.txt.
Description
Haiyan Liu and co-authors build a neural net to outline brain bleeds on CT scans in a 2024 paper. Intracerebral haemorrhage can kill fast, and small bleeds are easy to miss. Their model, DDANet, stacks dilated convolutions and attention tricks to catch both faint and large bleeds.
A pooling block widens the view of mid layers, while self attention lets high level sense guide fine detail work. Residual links and channel plus spatial attention fight the heavy tilt toward healthy pixels. Test scores on overlap and catch rates beat current rivals. Code is posted in public.
Catalog record
| CREATOR | Haiyan Liu, Yu Zeng, Hao Li, Fuxin Wang, Jianjun Chang, Huaping Guo, Jian Zhang |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |