SOURCE-LINKED INTELLIGENCE

Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Concepts

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Cancer segmentation models can fail silently, generating plausible but incorrect masks that risk missed findings or unnecessary biopsies. A critical question arises: Do AI models "know" when they are wrong, and if so, can we use the signal to predict their own failures? Humans do have a "Feeling of Error" (FOE): a spontaneous sense of unease that flags a potential error during thinking. We investigate whether cancer segmentation models exhibit an analogous internal signal. Unlike output-level cues (e.g., prediction confidence or uncertainty), which offer no insight into why a failure occurs an

Read original source ↗ Open in workspace

recordType

paper

region

Global