DD-Net: a dual-domain progressive fusion network enhanced by high–low frequency separation for lung nodule segmentation
Xiangsuo Fan, Lihong Deng, Jiachen Hou, Zhougui Ling · 2026
Read DD-Net: a dual-domain progressive fusion network enhanced by high–low frequency separation for lung nodule segmentation by Xiangsuo Fan, Lihong Deng, Jiachen Hou, Zhougui Ling (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-13518582.txt.
Description
Xiangsuo Fan and co-authors present DD-Net for outlining lung nodules in scans in this 2026 paper. Exact nodule borders help doctors judge whether a growth is benign or malignant. Nodules vary so much in size and texture that outlines often overrun or fall short.
The network reads each scan in two domains at once, space and frequency. A split step treats fine edge detail and broad shape apart, then recombines them. Attention stages align the two views step by step across channels and positions. A frequency self-attention path boosts the key responses further. Tests on a public chest scan set and a private set checked the design's accuracy.
Catalog record
| CREATOR | Xiangsuo Fan, Lihong Deng, Jiachen Hou, Zhougui Ling |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |