REDAEP: Robust and Enhanced Denoising Autoencoding Prior for Sparse-View CT Reconstruction
Fengqin Zhang, Minghui Zhang, Binjie Qin, Yi Zhang, Zichen Xu, Dong Liang, Qiegen Liu
Abstract
In X-ray computed tomography, radiation doses are harmful but can be significantly reduced by intuitively decreasing the number of projections. However, less projection views usually lead to low-resolution images. To address this issue, we propose a robust and enhanced mechanism on the basis of denoising autoencoding prior, or robust EDAEP (REDAEP) for sparse-view computed tomography reconstruction. REDAEP can substantially improve the reconstruction quality with two novel contributions. First, by employing the variable augmentation technique, REDAEP learns higher-dimensional network with three-channel image and proceeds to the single-channel image reconstruction. Second, REDAEP replaces the L <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> regression loss function with a more robust L <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sup> (0 <; p <; 2) regression to preserve more texture details. The empirical results demonstrate that REDAEP can achieve better performance than state-of-the-arts, in terms of quantitative measures and subjective visual quality.