Abstract: Ensuring equitable Artificial Intelligence (AI) in healthcare demands systems that make unbiased decisions across all demographic groups, bridging technical innovation with ethical principles. Foundation Models (FMs), trained on vast datasets through self-supervised learning, enable efficient adaptation across medical imaging tasks while reducing dependency on labeled data. These models demonstrate potential for enhancing fairness, though significant challenges remain in achieving consistent performance across demographic groups. Our review indicates that effective bias mitigation in FMs requires systematic interventions throughout all stages of development. While previous approaches focused primarily on model-level bias mitigation, our analysis reveals that fairness in FMs requires integrated interventions throughout the development pipeline, from data documentation to deployment protocols. This comprehensive framework advances current knowledge by demonstrating how systematic bias mitigation, combined with policy engagement, can effectively address both technical and institutional barriers to equitable AI in healthcare. The development of equitable FMs represents a critical step toward democratizing advanced healthcare technologies, particularly for underserved populations and regions with limited medical infrastructure and computational resources.
Challenge: How can we ensure Foundation Models in medical imaging become truly democratized tools that serve all populations equitably, when their development requires massive computational resources, diverse datasets, and specialized expertise that are currently concentrated in just a few regions of the world?
Foundation Models are models trained on massive datasets through self-supervised learning that can be adapted to multiple tasks with minimal fine-tuning, reducing the need for large labeled datasets while capturing broad patterns across domains.
Fairness in AI refers to ensuring systems make unbiased decisions across all demographic groups, creating equitable outcomes regardless of characteristics like race, gender, or age, which requires systematic interventions throughout the entire development pipeline from data collection to deployment.