PERSPECTIVE
Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives
Dilermando Queiroz, Anderson Carlos, André Anjos and Lilian Berton — February 2025
read paperDilermandoQueiroz
drag to flip
I'm a Research Engineer and PhD candidate working on fairness in medical imaging foundation models. My research asks whether models pre-trained on vast unlabeled data perform equitably across demographic groups — and what has to change in the pipeline when they don't. Previously at IBM Research, where I contributed to the IBM–NASA Prithvi geospatial foundation model.
Papers
see all on Scholar
- August 2024Does Data-Efficient Generalization Exacerbate Bias in Foundation Models?
- August 2024Using Backbone Foundation Model for Evaluating Fairness in Chest Radiography Without Demographic Data
- November 2023Direct Sampling for Spatially Variable Extreme Event Generation in Resampling-Based Stochastic Weather Generators
- July 2022Practical Skills Demand Forecasting via Representation Learning of Temporal Dynamics