Multi-view attention-based deep learning for benign–malignant classification of pulmonary nodules
Lijun Zhang, Debing Zhuo, Xiaolu Wu, Yuchou He, Guodong Kang · 2026
Read Multi-view attention-based deep learning for benign–malignant classification of pulmonary nodules by Lijun Zhang, Debing Zhuo, Xiaolu Wu, Yuchou He, Guodong Kang (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-13577567.txt.
Description
Lijun Zhang and colleagues classify lung nodules from three viewing angles at once. Their deep learning study from twenty twenty-six targets early lung cancer detection. A single scan slice shows too little of a nodule shape. Multi-view methods help, but they often merge views clumsily.
The system reads axial, coronal, and sagittal slices together. A lesion-guided attention step sharpens features near the nodule. A weighted fusion step then learns each view value per case. Tests used a public lung image collection with hundreds of nodules. Accuracy and related scores beat standard comparison methods. Balanced benign and malignant cases make the test fair. Radiologists gain a second reader tuned to nodule shape.
Catalog record
| CREATOR | Lijun Zhang, Debing Zhuo, Xiaolu Wu, Yuchou He, Guodong Kang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |