SkinSage XAI: An explainable deep learning solution for skin lesion diagnosis
Geetika Munjal, Paarth Bhardwaj, Vaibhav Bhargava, Shivendra Singh, Nimish Nagpal · 2024
Read SkinSage XAI: An explainable deep learning solution for skin lesion diagnosis by Geetika Munjal, Paarth Bhardwaj, Vaibhav Bhargava, Shivendra Singh, Nimish Nagpal (2024) 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-11671215.txt.
Description
Geetika Munjal and four co-authors present a 2024 paper on a deep learning system for skin lesions that explains its own answers. Early skin cancer detection saves lives, but black-box models leave dermatologists unable to check the reasoning. Their system, SkinSage XAI, classifies lesions with a proven image network and adds two explanation tools that highlight the regions driving each call. It trained on about fifty thousand curated images.
Across seven lesion types, from moles to melanoma, the system scored about ninety-six percent accuracy, with matching precision and recall and a near-perfect ranking score. The authors frame explainability as the advance, not just accuracy: a doctor can see why the model spoke. They argue such transparency can speed adoption in clinics and improve decisions. The work targets the trust gap in medical AI.
Catalog record
| CREATOR | Geetika Munjal, Paarth Bhardwaj, Vaibhav Bhargava, Shivendra Singh, Nimish Nagpal |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |