Addressing fairness in artificial intelligence for medical imaging

Abstract

A plethora of work has shown that AI systems can systematically and unfairly be biased against certain populations in multiple scenarios. The field of medical imaging, where AI systems are beginning to be increasingly adopted, is no exception. Here we discuss the meaning of fairness in this area and comment on the potential sources of biases, as well as the strategies available to mitigate them. Finally, we analyze the current state of the field, identifying strengths and highlighting areas of vacancy, challenges and opportunities that lie ahead.

Fig. 1. Group-fairness metrics.

Here we include a toy-example in the context of disease classification, where two sub-populations characterized by different protected attributes (in red and blue) present different disease prevalence (40% and 20% for blue and red subjects respectively, top row, x marks positive cases). A model optimized for discriminative performance was assessed on a test set achieving 100% accuracy (bottom row left side, + marks positive predictions). Algorithm fairness was audited according to two common metric choices (bottom row, right side). In this case, as a consequence of the difference in disease frequency, the model would not fulfill the demographic parity criterion (bottom row, right side) since the positive prediction rates vary between sub-groups : 40% (8 positive predictions over 20 cases) for the blue sub-group vs. 20% (4 positive predictions over 20 cases) for the red sub-group. On the other hand, the model would fulfill the equal opportunity criterion, as true positive rates match for both sub-groups reaching the value of 100%: 8 true positives out of 8 positive ground truth cases for the blue sub-group and 4 true positives out of 4 positive ground truth cases for the red sub-group . FN false negatives, FP false positives, TN true negatives, TP true positives. See legend-box with symbols on the top right corner.

Fig. 2. Main potential sources of bias in AI systems for MIC.

The data being fed to the system during training (1), design choices for the model (2), and the people who develop those systems (3), may all contribute to biases in AI systems for MIC.