Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection
This work addresses the robustness problem for medical imaging systems, particularly in COVID-19 diagnosis, but it is incremental as it builds on existing adversarial defense techniques with domain-specific adaptations.
The paper tackles the vulnerability of AI diagnostic systems for COVID-19 detection in CT images to adversarial perturbations, proposing a Contour Attention Preserving method that achieves state-of-the-art performance in adversarial defense and generalization tasks.
As the COVID-19 pandemic puts pressure on healthcare systems worldwide, the computed tomography image based AI diagnostic system has become a sustainable solution for early diagnosis. However, the model-wise vulnerability under adversarial perturbation hinders its deployment in practical situation. The existing adversarial training strategies are difficult to generalized into medical imaging field challenged by complex medical texture features. To overcome this challenge, we propose a Contour Attention Preserving (CAP) method based on lung cavity edge extraction. The contour prior features are injected to attention layer via a parameter regularization and we optimize the robust empirical risk with hybrid distance metric. We then introduce a new cross-nation CT scan dataset to evaluate the generalization capability of the adversarial robustness under distribution shift. Experimental results indicate that the proposed method achieves state-of-the-art performance in multiple adversarial defense and generalization tasks. The code and dataset are available at https://github.com/Quinn777/CAP.