An automatic approach to detect skin cancer utilizing active infrared thermography
Ricardo F. Soto, Sebastián E. Godoy · 2024
Read An automatic approach to detect skin cancer utilizing active infrared thermography by Ricardo F. Soto, Sebastián E. Godoy (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-11647852.txt.
Description
Ricardo Soto and Sebastián Godoy automate skin cancer screening with heat cameras, removing the expert hand that earlier versions needed. In active thermography, a lesion's cooling pattern betrays malignancy. Their previous work classified lesions from such patterns but required someone to outline the lesion manually.
A U-Net network now finds and segments the lesion itself, beating a semi-automatic method's overlap with dermatologist outlines by seventeen percent. New spatial and temporal features from the thermal sequence feed a support-vector machine that judges malignancy. At a fixed sensitivity, expert outlines still gave the best specificity, with automated routes close behind. The full pipeline, camera to verdict, is the contribution.
Catalog record
| CREATOR | Ricardo F. Soto, Sebastián E. Godoy |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |