Deep learning models have shown promise in medical imaging analysis, but concerns exist regarding biases leading to performance disparities among protected groups (e.g., age, race, gender). It has been shown that AI models can learn race on medical images, leading to algorithmic bias. In this talk, I will go through our recent approaches to enhance the fairness of medical image models by eliminating bias related to race, age, and gender. We hypothesize models may be learning patients' demographics via shortcut learning and combat this using self-supervised learning, image augmentation, siamese networks and adversarial learning.

線上視訊請點選連結