Search papers, labs, and topics across Lattice.
This study systematically evaluates uncertainty maps generated from a diffusion model-based quantitative MRI (qMRI) framework, focusing on their reliability in mapping tissue parameters. The authors found that while diffusion model-derived uncertainty correlates with mapping error, the raw uncertainty lacks proper calibration for quantitative interpretation. By implementing a post-hoc calibration procedure, they significantly improved the interpretability of uncertainty intervals, demonstrating that calibrated uncertainty can enhance reliability assessment and selective prediction in qMRI applications.
Uncalibrated uncertainty in diffusion model-derived qMRI can mislead interpretations, but effective calibration transforms it into a powerful tool for reliability assessment.
Quantitative MRI (qMRI) provides standardised tissue parameter maps, but the reliability of deep learning-based qMRI mapping methods is often not explicitly characterised. In this work we systematically evaluate uncertainty maps for quantitative MRI derived from multiple inferences of a data-consistent diffusion model-based qMRI framework. Evaluation on synthetic test data assessed error-awareness, high-error detection, selective prediction, and Gaussian interval calibration. Diffusion model-derived uncertainty was positively associated with the mapping error, while risk-coverage analysis showed that excluding high-uncertainty voxels reduced the retained error. However, the raw uncertainty was poorly calibrated for quantitative interval interpretation. Calibration was substantially improved using a post-hoc procedure combining prediction-value-dependent bias correction with scalar uncertainty scaling. Qualitative evaluation on a healthy volunteer showed spatially meaningful uncertainty patterns. These results indicate that diffusion model-derived uncertainty is informative for reliability assessment and selective prediction, but requires calibration for quantitative interval interpretation.
