RadioGuide-DCN: A Radiomics-Guided Decorrelated Network for Medical Image Classification
Lifeng Guo, Ying Fu, Shi Tan, Qi Wang, Yangan Zhang, Xiaohong Huang, Xueguang Yuan · 2025
Read RadioGuide-DCN: A Radiomics-Guided Decorrelated Network for Medical Image Classification by Lifeng Guo, Ying Fu, Shi Tan, Qi Wang, Yangan Zhang, Xiaohong Huang, Xueguang Yuan (2025) 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-12838146.txt.
Description
Lifeng Guo and six co-authors build a network that classifies medical images by mixing two styles of analysis. Their paper is from two thousand twenty-five. Deep networks learn rich features but can overfit small data sets. Older hand-crafted features, drawn from radiology practice, are stable but can miss subtle signs of disease.
Their model feeds the hand-crafted features in as a guide for the network. A special loss pushes the learned features apart, so they carry less repeated information. A fusion step then blends local detail with the global picture while muting distractions. On one breast image data set, the model reached about ninety-four percent accuracy. It beat both plain radiology features and standard deep networks on several tasks.
Catalog record
| CREATOR | Lifeng Guo, Ying Fu, Shi Tan, Qi Wang, Yangan Zhang, Xiaohong Huang, Xueguang Yuan |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |