Open access
Show Me the Polyp!
Silvie Opolka
Oleksandr Pometun
Krishnendu Bose
Srishti Pandey
Yu N. Terekhova
Franziska Tietze
Sarmad Shoaib Baig
Lukas Niehaus
Oct 2026 · Current Directions in Biomedical Engineering · Vol 12, pp. 367 - 370 · 0 citations
· 15 references
Abstract
Abstract We adapted two explainability methods commonly used in image classification, KernelSHAP and Grad-CAM, to colonoscopy video classification.We evaluated their plausibility by measuring how well their approximation of EndoFMLV’s visual focus for polyp class predictions aligned with the visible polyp region. Both methods showed low plausibility, and plausibility alone could not reveal model faults reliably.