Iterative quality enhancement via residual-artifact learning networks for low-dose CT

Abstract

Radiation exposure and the associated risk of cancer for patients in computed tomography (CT) scans have been major clinical concerns. The radiation exposure can be reduced effectively via lowering the x-ray tube current (mA). However, this strategy may lead to excessive noise and streak artifacts in the conventional filtered back-projection reconstructed images. To address this issue, some deep convolutional neural network (ConvNet) based approaches have been developed for low-dose CT imaging inspired by the recent development of machine learning. Nevertheless, some of the image textures reconstructed by the ConvNet could be corrupted by the severe streaks, especially in ultra-low-dose cases, which could be close to prostheses and hamper diagnosis. Therefore, in this work, we propose an iterative residual-artifact learning ConvNet (IRLNet) approach to improve the reconstruction performance over the ConvNet based approaches. Specifically, the proposed IRLNet estimates the high-frequency details within the noise and then removes them iteratively; after eliminating severe streaks in the low-dose CT images, the residual low-frequency details can be processed through the conventional network. Moreover, the proposed IRLNet scheme can be extended for robust handling of quantitative dual energy CT/cerebral perfusion CT imaging, and statistical iterative reconstruction. Real patient data are used to evaluate the proposed IRLNet, and the experimental results demonstrate that the proposed IRLNet approach outperforms the previous ConvNet based approaches in reducing the image noise and streak artifacts efficiently at the same time as preserving edge details well, suggesting that the proposed IRLNet approach can be used to improve the CT image quality, especially in ultra-low-dose cases.

Computed tomographic evaluation of myocardial ischemia

“…Recently, artificial intelligence was used to improve CT image reconstruction [75]. These techniques have the potential to optimize the quality of low-dose myocardial CTP images with shortening of reconstruction times [76,77].…”

A review on Deep Learning approaches for low-dose Computed Tomography restoration

“…Apart from the noise, the LDCT images are degraded by blurring [ 13 , 60 , 73 ] and streaking artifacts [ 28 , 34 , 50 , 71 , 75 , 81 , 91 ]. Lack of X-ray photons during the CT scanning and patient motion cause blurring.…”

Helical CT Reconstruction from Sparse-view Data through Exploiting the 3D Anatomical Structure Sparsity

“…The low-rank priors are also explored to constrain the correlation between different image frames, e.g., between multi-energy-bin images in energy-resolved CT and time sequence images in perfusion CT [12], [21]. Recently, the deep neural networks (DNN) also have been incorporated as a regularization term into the IR [27], [28], [29]. For example, Chen et al presented a learned expertsąŕ assessment-based reconstruction network (LEARN) for SCT reconstruction, which can be trained by a sparse sinogram and the corresponding full-view images, and the learned regularization terms and balancing parameters are specific to each iteration [29].…”