Metric-Guided Conformal Bounds for Probabilistic Image Reconstruction
This addresses the need for interpretable and reliable uncertainty quantification in medical imaging, particularly for tasks like fat mass quantification and radiotherapy planning, though it is incremental as it builds on conformal prediction for a specific domain.
The study tackled the problem of providing statistically guaranteed claims about the true state of a subject from scans reconstructed by deep learning algorithms, by proposing a framework for computing provably valid prediction bounds on derived clinical metrics, resulting in bounds with better semantical interpretation than pixel-based approaches and the ability to flag dangerous outlier reconstructions.
Modern deep learning reconstruction algorithms generate impressively realistic scans from sparse inputs, but can often produce significant inaccuracies. This makes it difficult to provide statistically guaranteed claims about the true state of a subject from scans reconstructed by these algorithms. In this study, we propose a framework for computing provably valid prediction bounds on claims derived from probabilistic black-box image reconstruction algorithms. The key insights behind our framework are to represent reconstructed scans with a derived clinical metric of interest, and to calibrate bounds on the ground truth metric with conformal prediction (CP) using a prior calibration dataset. These bounds convey interpretable feedback about the subject's state, and can also be used to retrieve nearest-neighbor reconstructed scans for visual inspection. We demonstrate the utility of this framework on sparse-view computed tomography (CT) for fat mass quantification and radiotherapy planning tasks. Results show that our framework produces bounds with better semantical interpretation than conventional pixel-based bounding approaches. Furthermore, we can flag dangerous outlier reconstructions that look plausible but have statistically unlikely metric values.