Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction

Abstract

Image reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the reconstruction. In this work we propose a scalable and efficient framework to simultaneously quantify aleatoric and epistemic uncertainties in learned iterative image reconstruction. We build on a Bayesian deep gradient descent method for quantifying epistemic uncertainty, and incorporate the heteroscedastic variance of the noise to account for the aleatoric uncertainty. We show that our method exhibits competitive performance against conventional benchmarks for computed tomography with both sparse view and limited angle data. The estimated uncertainty captures the variability in the reconstructions, caused by the restricted measurement model, and by missing information, due to the limited angle geometry.

References in corpus (8)

• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Model based learning for accelerated, limited-view 3D photoacoustic tomography
• Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
• Recurrent Inference Machines for Solving Inverse Problems
• Deep Bayesian Inversion
• Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration
• Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent

Cited by in corpus (2)

• Unsupervised Knowledge-Transfer for Learned Image Reconstruction
• Conditional Variational Autoencoder for Learned Image Reconstruction