Who Does Your Algorithm Fail? Investigating Age and Ethnic Bias in the MAMA-MIA Dataset
This work addresses fairness gaps in medical image segmentation, which is crucial for equitable healthcare, though it is incremental as it focuses on auditing an existing dataset rather than proposing new methods.
The study audited fairness in automated breast cancer tumor segmentation using the MAMA-MIA dataset, revealing a persistent age-related bias against younger patients and showing how data aggregation affects ethnic biases.
Deep learning models aim to improve diagnostic workflows, but fairness evaluation remains underexplored beyond classification, e.g., in image segmentation. Unaddressed segmentation bias can lead to disparities in the quality of care for certain populations, potentially compounded across clinical decision points and amplified through iterative model development. Here, we audit the fairness of the automated segmentation labels provided in the breast cancer tumor segmentation dataset MAMA-MIA. We evaluate automated segmentation quality across age, ethnicity, and data source. Our analysis reveals an intrinsic age-related bias against younger patients that continues to persist even after controlling for confounding factors, such as data source. We hypothesize that this bias may be linked to physiological factors, a known challenge for both radiologists and automated systems. Finally, we show how aggregating data from multiple data sources influences site-specific ethnic biases, underscoring the necessity of investigating data at a granular level.