CT artifact correction for sparse and truncated projection data using generative adversarial networks

Abstract

Purpose: Computed tomography image reconstruction using truncated or sparsely acquired projection data to reduce radiation dose, iodine volume, and patient motion artifacts has been widely investigated. To continue these efforts, we investigated the use of machine learning-based reconstruction techniques using deep convolutional generative adversarial networks (DCGANs) and evaluated its effect using standard imaging metrics. Methods: Ten thousand head computed tomography (CT) scans were collected from the 2019 RSNA Intracranial Hemorrhage Detection and Classification Challenge dataset. Sinograms were simulated and then resampled in both a one-third truncated and one-third sparse manner. DCGANs were tasked with correcting the incomplete projection data, either in the sinogram domain where the full sinogram was recovered by the DCGAN and then reconstructed, or the reconstruction domain where the incomplete data were first reconstructed and the sparse or truncation artifacts were corrected by the DCGAN. Seventy-five hundred images were used for network training and 2500 were withheld for network assessment using mean absolute error (MAE), structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR) between results of different correction techniques. Image data from a quality-assurance phantom were also resampled in the two manners and corrected and reconstructed for network performance assessment using line profiles across high-contrast features, the modulation transfer function (MTF), noise power spectrum (NPS), and Hounsfield Unit (HU) linearity analysis. Results: Better agreement with the fully sampled reconstructions were achieved from sparse acquisition corrected in the sinogram domain and the truncated acquisition corrected in the reconstruction domain. MAE, SSIM, and PSNR showed quantitative improvement from the DCGAN correction techniques. HU linearity of the reconstructions was maintained by the correction techniques for the sparse and truncated acquisitions. MTF curves reached the 10% modulation cutoff frequency at 5.86 lp/cm for the truncated corrected reconstruction compared with 2.98 lp/cm for the truncated uncorrected reconstruction, and 5.36 lp/cm for the sparse corrected reconstruction compared with around 2.91 lp/cm for the sparse uncorrected reconstruction. NPS analyses yielded better agreement across a range of frequencies between the resampled corrected phantom and truth reconstructions. Conclusions: We demonstrated the use of DCGANs for CT-image correction from sparse and truncated simulated projection data, while preserving imaging quality of the fully sampled projection data.

A prior image constraint robust principal component analysis reconstruction method for sparse segmental multi-energy computed tomography

“…We do not exclude the possibilities to investigate more advanced algorithms that can reconstruct images more accurately. Especially, some deep-learning based approaches (36,38,39) have shown their superiority for such sparse and/or limited view CT reconstruction. One of our future work is to explore some more advanced reconstruction algorithms on our proposed sparse segmental multi-energy acquisition scheme.…”

“…Line profiles and HU linearity analysis (36) are also assessed on Catphan phantom for quantitative evaluation.…”

Efficient Strike Artifact Reduction Based on 3D-Morphological Structure Operators from Filtered Back-Projection PET Images

“…Table 6 shows the comparisons among published literatures with the presented methods. Recently, the deep learning methods have been popularly applied to medical and molecular images to reduce noise [24,25] and enhance quality of images [26][27][28][29][30][31][32] including deep learning methods and generative adversarial networks algorithms (GAN). Meanwhile, the classical methods include patch-based regularization algorithms (PBRA) [24,25] and Bayesian penalized likelihood reconstruction algorithm (BSREMA) [26], and 2D and 3D MSO with ORC are applied to perform noise reduction with acceptable results.…”

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

“…In recent years, generative adversarial networks (GAN) have been extensively developed in the field of low-dose CT reconstruction [71,73,109,118,123,127,132,134,[146][147][148][149][150][151][152][153][154][155]. In contrast to convolutional neural networks (CNNs) in patches, [147] proposed denoising networks which are FCN-based using images in full size for training, and because they reused the underlying feature maps, the computational efficiency was very high.…”