SUREMap: Predicting Uncertainty in CNN-based Image Reconstruction Using Stein's Unbiased Risk Estimate

Abstract

Convolutional neural networks (CNN) have emerged as a powerful tool for solving computational imaging reconstruction problems. However, CNNs are generally difficult-to-understand black-boxes. Accordingly, it is challenging to know when they will work and, more importantly, when they will fail. This limitation is a major barrier to their use in safety-critical applications like medical imaging: Is that blob in the reconstruction an artifact or a tumor? In this work we use Stein's unbiased risk estimate (SURE) to develop per-pixel confidence intervals, in the form of heatmaps, for compressive sensing reconstruction using the approximate message passing (AMP) framework with CNN-based denoisers. These heatmaps tell end-users how much to trust an image formed by a CNN, which could greatly improve the utility of CNNs in various computational imaging applications.

References in corpus (10)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Message Passing Algorithms for Compressed Sensing
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• Generalized SURE for Exponential Families: Applications to Regularization
• Compressed Sensing using Generative Models
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• Near optimal compressed sensing without priors: Parametric SURE Approximate Message Passing
• Unsupervised Learning with Stein's Unbiased Risk Estimator
• Parameterless Optimal Approximate Message Passing
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement