Science and Technology Production

Proceedings of the MICCAI FAIMI Workshop - Unsupervised bias discovery in medical image segmentation

Congress

Authorship:

Rafael Nicolas Gaggión Zulpo ; Rodrigo Echeveste ; Mansilla, Lucas ; Diego Milone ; FERRANTE, ENZO

Date:

2023

Publishing House and Editing Place:

Springer Nature

Summary *

It has recently been shown that deep learning models for anatomical segmentation in medical images can exhibit biases against certain sub-populations defined in terms of protected attributes like sex or ethnicity. In this context, auditing fairness of deep segmentation models becomes crucial. However, such audit process generally requires access to ground-truth segmentation masks for the target population, which may not always be available, especially when going from development to deployment. Here we propose a new method to anticipate model biases in biomedical image segmentation in the absence of ground-truth annotations. Our unsupervised bias discovery method leverages the reverse classification accuracy framework to estimate segmentation quality. Through numerical experiments in synthetic and realistic scenarios we show how our method is able to successfully anticipate fairness issues in the absence of ground-truth labels, constituting a novel and valuable tool in this field. Information provided by the agent in SIGEVA

Key Words

unsupervised bias discoveryfairnessimage segmentationxray