Abstract
Machine learning-enabled medical imaging analysis has become a vital
part of the automatic diagnosis system. However, machine learning,
especially deep learning models have been shown to demonstrate a
systematic bias towards certain subgroups of people. For instance, they
yield a preferential predictive performance to males over females, which
is unfair and potentially harmful especially in healthcare scenarios. In
this literature survey, we give a comprehensive review of the current
progress of fairness studies in medical image analysis (MedIA) and
healthcare. Specifically, we first discuss the definitions of fairness,
the source of unfairness and potential solutions. Then, we discuss
current research on fairness for MedIA categorized by fairness
evaluation and unfairness mitigation. Furthermore, we conduct extensive
experiments to evaluate the fairness of different medical imaging tasks.
Finally, we discuss the challenges and future directions in developing
fair MedIA and healthcare applications.