Interpretation of Disease Evidence for Medical Images Using Adversarial Deformation Fields
This addresses the need for more precise and interpretable deep learning explanations in medical imaging to build trust and identify biases, though it is incremental as it builds on existing visualization techniques.
The authors tackled the problem of interpreting disease evidence in medical images by proposing DeFI-GAN, a method that uses adversarial deformation fields to modify diseased images to resemble healthy ones, showing compelling results against baselines and highlighting previously undetected biomarkers and biases.
The high complexity of deep learning models is associated with the difficulty of explaining what evidence they recognize as correlating with specific disease labels. This information is critical for building trust in models and finding their biases. Until now, automated deep learning visualization solutions have identified regions of images used by classifiers, but these solutions are too coarse, too noisy, or have a limited representation of the way images can change. We propose a novel method for formulating and presenting spatial explanations of disease evidence, called deformation field interpretation with generative adversarial networks (DeFI-GAN). An adversarially trained generator produces deformation fields that modify images of diseased patients to resemble images of healthy patients. We validate the method studying chronic obstructive pulmonary disease (COPD) evidence in chest x-rays (CXRs) and Alzheimer's disease (AD) evidence in brain MRIs. When extracting disease evidence in longitudinal data, we show compelling results against a baseline producing difference maps. DeFI-GAN also highlights disease biomarkers not found by previous methods and potential biases that may help in investigations of the dataset and of the adopted learning methods.