Uncertainty of Vision Medical Foundation Models

Haoxu Huang, Narges Razavian

Keywords: Uncertainty, Foundation Model, Medical Imaging

TL;DR: We study uncertainty of recent vision medical foundation model via both uncertainty of point and region predictions. The result shows the importatnce of pre-training data/method over domain-specific pre-training.

Abstract:

Accurate uncertainty estimation is essential for machine learning systems deployed
in high-stakes domains such as medicine. Traditional approaches primarily
rely on probability outputs from trained models (point predictions), which provide
no formal guarantees on prediction coverage and often require additional calibration
techniques to improve reliability. In contrast, conformal prediction (region
prediction) offers a principled alternative by generating prediction sets with finitesample
validity guarantees, ensuring that the ground truth is contained within the
set at a specified confidence level.
In this study, we explore the impact of pre-training approach, dataset scale and
domain on both point and region-level uncertainty quantification, by studying
domain-specific vision medical foundation models vs. general domain vision
foundation models. We conduct a comprehensive evaluation across foundation
models trained on retinal, histopathological, and Chest X-Rays data, applying
various calibration techniques. Our results demonstrate that (1) pre-training on
higher-quality domain-specific datasets along with self-supervised learning leads
to better-calibrated point predictions than general domain pre-training, (2) standard
re-calibration methods alone cannot fully mitigate uncertainty discrepancies
across models trained on different data sources, (3) domain-specific foundation
model can lead to more efficient conformal prediction.
These findings highlight the importance of careful model selection and the integration
of both point and region prediction to enhance the reliability and trustworthiness
of medical AI systems. Our work underscores the need for a holistic
approach to uncertainty quantification in recent development of medical vision
foundation model, ensuring robust and interpretable AI-driven decision-making.

Submission Number: 13