An explainable dual-branch transformer–ConvNeXt framework for robust lung histopathology classification
G. Sunitha, J. Vellingiri · 2026
Read An explainable dual-branch transformer–ConvNeXt framework for robust lung histopathology classification by G. Sunitha, J. Vellingiri (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-13613273.txt.
Description
Sunitha and Vellingiri present a dual-branch deep learning system for lung tissue classification. Their 2026 paper addresses a hard task in histopathology. Lung adenocarcinoma and squamous cell carcinoma look alike under the microscope. Even trained pathologists can confuse the two subtypes. The system aims to tell them apart from benign tissue.
One branch uses a vision transformer to capture broad context in stained tissue images. The other uses a convolutional network to capture fine local texture. A gating module joins the two views before classification. The team tested the system on 15,000 lung images in three classes. Accuracy passed ninety-four percent, with benign tissue sorted almost perfectly. Most errors fell between the two cancer subtypes, as expected.
Catalog record
| CREATOR | G. Sunitha, J. Vellingiri |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 82 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |