AI RESEARCH
Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification
arXiv CS.CV
•
ArXi:2604.08502v1 Announce Type: new Class Activation Mapping (CAM) methods are widely used to generate visual explanations for deep learning classifiers in medical imaging. However, existing evaluation frameworks assess whether explanations are correct, measured by localisation fidelity against radiologist annotations, rather than whether they are consistent: whether the model applies the same spatial reasoning strategy across different patients with the same pathology.