Reducing Risk and Uncertainty of Deep Neural Networks on Diagnosing COVID-19 Infection
This addresses the unreliability of AI in medical screening for COVID-19, though it is incremental as it applies existing uncertainty methods to a new domain.
The paper tackles the problem of predictive uncertainty in deep neural networks for COVID-19 diagnosis, introducing uncertainty estimation to detect confusing cases for expert referral, with validation by medical professionals to ensure clinical viability.
Effective and reliable screening of patients via Computer-Aided Diagnosis can play a crucial part in the battle against COVID-19. Most of the existing works focus on developing sophisticated methods yielding high detection performance, yet not addressing the issue of predictive uncertainty. In this work, we introduce uncertainty estimation to detect confusing cases for expert referral to address the unreliability of state-of-the-art (SOTA) DNNs on COVID-19 detection. To the best of our knowledge, we are the first to address this issue on the COVID-19 detection problem. In this work, we investigate a number of SOTA uncertainty estimation methods on publicly available COVID dataset and present our experimental findings. In collaboration with medical professionals, we further validate the results to ensure the viability of the best performing method in clinical practice.