Principled Confidence Estimation for Deep Computed Tomography

TL;DR

This paper introduces a theoretical framework for confidence estimation in deep CT reconstructions, providing guarantees and practical tools for uncertainty quantification in medical imaging.

Contribution

It develops a general confidence estimation framework applicable to both classical and deep learning CT methods, with theoretical guarantees and empirical validation.

Findings

Deep methods produce tighter confidence regions than classical ones.

The framework detects hallucinations in reconstructed images.

Provides interpretable visualizations of confidence regions.

Abstract

We present a principled framework for confidence estimation in computed tomography (CT) reconstruction. Based on the sequential likelihood mixing framework (Kirschner et al., 2025), we establish confidence regions with theoretical coverage guarantees for deep-learning-based CT reconstructions. We consider a realistic forward model following the Beer-Lambert law, i.e., a log-linear forward model with Poisson noise, closely reflecting clinical and scientific imaging conditions. The framework is general and applies to both classical algorithms and deep learning reconstruction methods, including U-Nets, U-Net ensembles, and generative Diffusion models. Empirically, we demonstrate that deep reconstruction methods yield substantially tighter confidence regions than classical reconstructions, without sacrificing theoretical coverage guarantees. Our approach allows the detection of hallucinations in reconstructed images and provides interpretable visualizations of confidence regions. This establishes deep models not only as powerful estimators, but also as reliable tools for uncertainty-aware medical imaging.