Liver tumor segmentation method combining multi-axis attention and conditional generative adversarial networks
Jiahao Liao, Hongyuan Wang, Hanjie Gu, Yinghui Cai · 2024
Read Liver tumor segmentation method combining multi-axis attention and conditional generative adversarial networks by Jiahao Liao, Hongyuan Wang, Hanjie Gu, Yinghui Cai (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-11614272.txt.
Description
Jiahao Liao, Hongyuan Wang, Hanjie Gu, and Yinghui Cai present in a 2024 paper a method to outline liver tumors on CT scans. Hand drawn outlines are slow and often off, while auto methods face three clear flaws. Tumors are tiny next to healthy tissue, broad context gets lost, and faint edges are missed.
Their network blends a multi axis attention step with a contest style generator design. The attention step views the 3D scan along each axis and fuses the views with learned weights. That fusion keeps key facts from each direction in play at once. Class balance tricks aim the model at the small tumor zone it used to skip. The design targets sharper outlines of small and fuzzy tumors for therapy planning.
Catalog record
| CREATOR | Jiahao Liao, Hongyuan Wang, Hanjie Gu, Yinghui Cai |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |