Do CNNs solve the CT inverse problem?

TL;DR

This study critically evaluates whether CNNs can accurately solve the sparse-view CT inverse problem, finding that CNNs fail under tested conditions where traditional methods succeed, thus challenging claims of CNN effectiveness in this context.

Contribution

The paper provides a direct comparison between CNN-based reconstruction and traditional TV minimization, demonstrating CNNs' limitations in solving the sparse-view CT inverse problem for specific models.

Findings

CNNs do not accurately reconstruct images from sparse-view CT data.

Total variation minimization successfully reconstructs images under the same conditions.

CNNs' failure questions their claimed capability to solve inverse problems in medical imaging.

Abstract

Objective: This work examines the claim made in the literature that the inverse problem associated with image reconstruction in sparse-view computed tomography (CT) can be solved with a convolutional neural network (CNN). Methods: Training and testing image/data pairs are generated in a dedicated breast CT simulation for sparse-view sampling, using two different object models. The trained CNN is tested to see if images can be accurately recovered from their corresponding sparse-view data. For reference, the same sparse-view CT data is reconstructed by the use of constrained total-variation (TV) minimization (TVmin), which exploits sparsity in the gradient magnitude image (GMI). Results: Using sparse-view data from images either in the training or testing set, there is a significant discrepancy between the image obtained with the CNN and the image that generated the data. For the same simulated scanning conditions, TVmin is able to accurately reconstruct the test image. Conclusion: We find that the sparse-view CT inverse problem cannot be solved for the particular published CNN-based methodology that we chose and the particular object model that we tested. Furthermore, this negative result is obtained for conditions where TVmin is able to recover the test images. Significance: The inability of the CNN to solve the inverse problem associated with sparse-view CT, for the specific conditions of the presented simulation, draws into question similar unsupported claims being made for the use of CNNs to solve inverse problems in medical imaging.