Background and purpose: The use of AI in the process of CT image reconstruction may improve image quality of resultant images and therefore facilitate low-dose CT examinations.
Methods: Articles in this review were gathered from multiple databases (Google Scholar, Ovid and Monash University Library Database). A total of 17 articles regarding AI use in CT image reconstruction was reviewed, including 1 white paper from GE Healthcare.
Results: DLR algorithms performed better in terms of noise reduction abilities, and image quality preservation at low doses when compared to other reconstruction techniques.
Conclusion: Further research is required to discuss clinical application and diagnostic accuracy of DLR algorithms, but AI is a promising dose-reduction technique with future computational advances.
Keywords: Convolutional neural networks; Deep learning; Dose reduction; Generative adversarial networks; Machine learning.
Copyright © 2020. Published by Elsevier Inc.