Producción CyT

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

Congreso

Autoría:

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

Fecha:

2023

Editorial y Lugar de Edición:

Springer Nature

Resumen *

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. Información suministrada por el agente en SIGEVA

Palabras Clave

unsupervised bias discoveryfairnessimage segmentationxray