DWARF: Disease-weighted network for attention map refinement
This addresses the 'human out of the loop' issue for healthcare professionals, aiming to improve patient outcomes, but it is incremental as it refines existing attention map methods.
The study tackled the problem of interpretability and trustworthiness in medical imaging models by proposing DWARF, a disease-weighted attention map refinement network that integrates expert feedback, resulting in significant improvements in interpretability and diagnostic accuracy across multiple datasets.
The interpretability of deep learning is crucial for evaluating the reliability of medical imaging models and reducing the risks of inaccurate patient recommendations. This study addresses the "human out of the loop" and "trustworthiness" issues in medical image analysis by integrating medical professionals into the interpretability process. We propose a disease-weighted attention map refinement network (DWARF) that leverages expert feedback to enhance model relevance and accuracy. Our method employs cyclic training to iteratively improve diagnostic performance, generating precise and interpretable feature maps. Experimental results demonstrate significant improvements in interpretability and diagnostic accuracy across multiple medical imaging datasets. This approach fosters effective collaboration between AI systems and healthcare professionals, ultimately aiming to improve patient outcomes