Towards Interpretable Foundation Models for Retinal Fundus Images
This addresses the need for interpretable AI in high-stakes medical domains like retinal imaging, offering a novel approach to enhance trust and usability.
The authors tackled the problem of limited interpretability in foundation models for medical imaging by proposing Dual-IFM, an interpretable-by-design model that provides local and global interpretability for retinal fundus images, achieving performance similar to state-of-the-art models with up to 16x fewer parameters.
Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL). However, many of these models rely on architectures that offer limited interpretability, which is a critical issue in high-stakes domains such as medical imaging. We propose Dual-IFM, a foundation model that is interpretable-by-design in two ways: First, it provides local interpretability for individual images through class evidence maps that are faithful to the decision-making process. Second, it provides global interpretability for entire datasets through a 2D projection layer that allows for direct visualization of the model's representation space. We trained our model on over 800,000 color fundus photography from various sources to learn generalizable, interpretable representations for different downstream tasks. Our results show that our model reaches a performance range similar to that of state-of-the-art foundation models with up to $16\times$ the number of parameters, while providing interpretable predictions on out-of-distribution data. Our results suggest that large-scale SSL pretraining paired with inherent interpretability can lead to robust representations for retinal imaging.