Keywords:
Not applicable, Image verification, Screening, CT-Quantitative, CT, Radiation physics, Liver, Abdomen
Authors:
K. Kitazawa, T. Kitamura, A. Matuda, K. Togashi; Kyoto/JP
DOI:
10.26044/ecr2020/C-01979
Purpose
Image reconstruction technologies of computed tomography (CT) have been rapidly progressing.
Model-based iterative reconstruction (MBIR) is an image reconstruction technique that accurately reproduces CT values without filtered back projection. While MBIR can improve the image quality, it usually requires higher computational power and longer computational time [1].
Recently, advanced intelligence clear-IQ engine (AiCE) that using deep learning technology was developed.
The teaching data used for deep learning reconstruction (DLR) training is high-quality CT images reconstructed with MBIR whose parameters are adjusted to obtain the best image quality. Unlike the conventional noise reduction methods, which involve a trade-off between spatial resolution and noise reduction, DLR lowers the image noise and increases spatial resolution simultaneously [2][3]. T Higaki et al. reported that AiCE could reduce at least 30% of radiation dose compared with conventional hybrid iterative reconstruction (hybrid IR) for over middle frequency range [4]. Low-contrast detectability with low dose was not verified.
The purpose of this study was to evaluate image quality of low dose CT images reconstructed with AiCE for low-contrast detectability.