Principled Confidence Estimation for Deep Computed Tomography
This provides uncertainty-aware tools for medical imaging, enabling detection of hallucinations and interpretable visualizations, though it is incremental as it builds on existing likelihood mixing frameworks.
The paper tackled the problem of estimating confidence in computed tomography (CT) reconstructions by developing a principled framework with theoretical coverage guarantees, demonstrating that deep learning methods yield substantially tighter confidence regions than classical approaches without sacrificing coverage.
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.