Suremap: Predicting Uncertainty in Cnn-Based Image Reconstructions Using Stein's Unbiased Risk Estimate

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...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1385 - 1389
Main Authors Kitichotkul, Ruangrawee, Metzler, Christopher A., Ong, Frank, Wetzstein, Gordon
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.06.2021
Subjects
Approximate Message Passing
CNN
Compressive Sensing
Heating systems
Image coding
Message passing
MRI
Sensors
Signal processing
Uncertainty
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2379-190X
DOI:10.1109/ICASSP39728.2021.9414306