Explainable ensemble transfer learning for skin lesion classification with multi-method explainability validation
Nemili Sravani, Srinivas Koppu · 2026
Read Explainable ensemble transfer learning for skin lesion classification with multi-method explainability validation by Nemili Sravani, Srinivas Koppu (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-13582516.txt.
Description
Nemili Sravani and Srinivas Koppu build an explainable AI system that sorts skin lesions from photographs. Skin cancer is common and deadly when caught late, and dermoscopic images hold the clues. Automated sorting is hard: classes are uneven, look-alike lesions confuse models, and doctors distrust answers they cannot inspect. Their 2026 study blends three deep networks, pre-trained on general images and tuned on a public set of ten thousand lesion photos. Votes are weighted by each model's strength.
Several explanation methods then show which image parts drove each call, and the explanations themselves are cross-checked for agreement. A system that shows its reasons can earn a place beside clinicians. The authors target both accuracy and the trust needed for real use.
Catalog record
| CREATOR | Nemili Sravani, Srinivas Koppu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 98 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |