Metric-Guided Conformal Bounds for Probabilistic Image Reconstruction

TL;DR

This paper introduces a conformal prediction framework that provides statistically valid bounds on clinical metrics derived from probabilistic image reconstructions, enhancing interpretability and reliability in medical imaging tasks.

Contribution

It presents a novel method to compute valid prediction bounds on reconstructed images using conformal prediction and clinical metrics, improving interpretability and outlier detection.

Findings

Bounds have better semantic interpretation than pixel-based methods.

Framework effectively flags outlier reconstructions.

Provides statistically valid confidence bounds for clinical metrics.

Abstract

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.