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

Abstract

Conventional reconstruction techniques, such as filtered back projection (FBP) and iterative reconstruction (IR), which have been utilised widely in the image reconstruction process of computed tomography (CT) are not suitable in the case of low-dose CT applications, because of the unsatisfying quality of the reconstructed image and inefficient reconstruction time. Therefore, as the demand for CT radiation dose reduction continues to increase, the use of artificial intelligence (AI) in image reconstruction has become a trend that attracts more and more attention. This systematic review examined various deep learning methods to determine their characteristics, availability, intended use and expected outputs concerning low-dose CT image reconstruction. Utilising the methodology of Kitchenham and Charter, we performed a systematic search of the literature from 2016 to 2021 in Springer, Science Direct, arXiv, PubMed, ACM, IEEE, and Scopus. This review showed that algorithms using deep learning technology are superior to traditional IR methods in noise suppression, artifact reduction and structure preservation, in terms of improving the image quality of low-dose reconstructed images. In conclusion, we provided an overview of the use of deep learning approaches in low-dose CT image reconstruction together with their benefits, limitations, and opportunities for improvement.

Artifact Reduction in 3D and 4D Cone-Beam Computed Tomography Images With Deep Learning: A Review

“…Ref. [6] discusses supervised, selfsupervised, and unsupervised techniques for artifact reduction in CT scans, and it covers unrolling the reconstruction, as well as optimization methods in both the projection (raw 2D X-ray images) and volume (reconstructed 3D images) domains. However, it is essential to note that Ref.…”

“…However, it is essential to note that Ref. [6] primarily focuses on CT scans, which differs from the main focus of this work, namely CBCT scans. The third survey [7] provides an in-depth literature analysis, considering criteria such as anatomy, loss functions, model architectures, and training methods for supervised learning specifically applied to CBCT scans.…”

A neural network reconstruction approach for obtaining parallax-free X-ray powder diffraction computed tomography data from large samples

“…One of the key areas that deep learning has made a significant impact is in the field of tomographic image reconstruction [7][8][9] . Traditionally, tomographic image reconstruction has relied on either direct methods, like the filtered back projection (FBP) algorithm 10 , or iterative methods that depend on prior knowledge and fine-tuning.…”

Deep image prior with sparsity constraint for limited-angle computed tomography reconstruction

“…Recently, CT reconstruction methods that include deep learning techniques have been proposed [7,24,37,43,53]. This can be achieved in the image domain, the sinogram domain, or hybrid domains [54]. End-to-end transformations from the sinograms to the tomographic images using artificial neural networks are possible and do not require an explicit forward model A [54].…”

“…This can be achieved in the image domain, the sinogram domain, or hybrid domains [54]. End-to-end transformations from the sinograms to the tomographic images using artificial neural networks are possible and do not require an explicit forward model A [54]. Applications include CBCT [22], CBCT with sparse sampling [32], and limited-angle CBCT [52].…”