SUREMap: Predicting Uncertainty in CNN-based Image Reconstruction Using Stein's Unbiased Risk Estimate
This addresses the need for reliability in CNN-based reconstructions for end-users in computational imaging, though it is incremental as it builds on existing AMP and SURE frameworks.
The paper tackled the problem of uncertainty quantification in CNN-based image reconstruction for safety-critical applications like medical imaging, by developing per-pixel confidence intervals using Stein's unbiased risk estimate (SURE) to produce trust heatmaps.
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.