Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT
This work addresses the need for theoretical justification and better high-frequency edge recovery in sparse-view CT, which is crucial for reducing radiation dose in medical imaging, though it is incremental as it builds on existing U-Net variants.
The paper tackled the problem of streaking artifacts in sparse-view CT reconstruction by proposing new multi-resolution deep learning architectures, demonstrating improved reconstruction performance on real patient data.
X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using large receptive field neural networks such as U-Net have demonstrated impressive performance for sparse- view CT reconstruction. However, theoretical justification is still lacking. Inspired by the recent theory of deep convolutional framelets, the main goal of this paper is, therefore, to reveal the limitation of U-Net and propose new multi-resolution deep learning schemes. In particular, we show that the alternative U- Net variants such as dual frame and the tight frame U-Nets satisfy the so-called frame condition which make them better for effective recovery of high frequency edges in sparse view- CT. Using extensive experiments with real patient data set, we demonstrate that the new network architectures provide better reconstruction performance.