Back Projection Tensor Domain Fusion Improves Cross-Domain Deep Reconstruction for Sparse-View CT

Sparse-view CT imaging can reduce radiation dose or shorten scanning time by reducing the number of projection views, thus methods for high-quality image reconstruction from under-sampled sinograms are actively sought after in the CT field. In this work, we present a BP-tensor domain fusion network (TensorFusion-Net) that can produce high-quality images from sparse-view sinograms using a cross-domain deep reconstruction framework. TensorFusion-Net holistically fuses the sparse-view BP-tensor derived from the sparse-view sinogram and the full-view BP-tensor calculated from the output image of a prior network (PriorNet). Furthermore, output from TensorFusion-Net can be used to update the full-view BP-tensor, which is fused again with the sparse-view BP-tensor iteratively. Our experimental results on AAPM Mayo datasets indicate that our algorithm performs better than several existing algorithms in artifact reduction and image detail preservation.

1. INTRODUCTION

Sparse-view CT offers the potential benefits of reduced radiation exposure and increased imaging speed. However, reconstructing high-quality images from sparsely sampled data is a challenging and ill-posed problem. Images reconstructed solely using filtered back projection (FBP) are frequently marred by streaking artifacts. The challenge of fully exploiting sparse-view projections without compromising image quality is a pressing issue.