Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT
- 457 Downloads
Deep learning reconstruction (DLR) is a new reconstruction method; it introduces deep convolutional neural networks into the reconstruction flow. This study was conducted in order to examine the clinical applicability of abdominal ultra-high-resolution CT (U-HRCT) exams reconstructed with a new DLR in comparison to hybrid and model-based iterative reconstruction (hybrid-IR, MBIR).
Our retrospective study included 46 patients seen between December 2017 and April 2018. A radiologist recorded the standard deviation of attenuation in the paraspinal muscle as the image noise and calculated the contrast-to-noise ratio (CNR) for the aorta, portal vein, and liver. The overall image quality was assessed by two other radiologists and graded on a 5-point confidence scale ranging from 1 (unacceptable) to 5 (excellent). The difference between CT images subjected to hybrid-IR, MBIR, and DLR was compared.
The image noise was significantly lower and the CNR was significantly higher on DLR than hybrid-IR and MBIR images (p < 0.01). DLR images received the highest and MBIR images the lowest scores for overall image quality.
DLR improved the quality of abdominal U-HRCT images.
• The potential degradation due to increased noise may prevent implementation of ultra-high-resolution CT in the abdomen.
• Image noise and overall image quality for hepatic ultra-high-resolution CT images improved with deep learning reconstruction as compared to hybrid- and model-based iterative reconstruction.
KeywordsLiver Neural networks (computer) X-ray computed tomography Machine learning Artificial intelligence
Advanced Intelligent Clear-IQ Engine
Adaptive iterative dose reduction 3-dimensional
CT dose index
Deep convolutional neural networks
Digital Imaging and Communications in Medicine
Deep learning reconstruction
Forward-projected model-based iterative reconstruction solution
Hepatic arterial phase
Hybrid iterative reconstruction
Model-based iterative reconstruction
Portal venous phase
Region of interest
Size-specific dose estimate
Ultra-high-resolution computed tomography
Dr. Kazuo Awai received a research funding from Canon Medical Systems Co. Ltd.
Compliance with ethical standards
The scientific guarantor of this publication is Dr. Kazuo Awai.
Conflict of interest
The authors of this manuscript declare relationships with the following companies: Canon Medical Systems Co. Ltd. for Kazuo Awai and Naruomi Akino and Canon Medical Research USA for Jian Zhou and Zhou Yu. Naruomi Akino, Jian Zhou, and Zhou Yu contributed to this study for manuscript editing regarding the description of deep learning reconstruction (DLR) algorithm. The authors who are not employees of Canon Medical Systems had control of inclusion of any data and information that might present a conflict of interest for those authors who are employees of Canon Medical Systems. The other authors declare that they have no conflict of interest.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Written informed consent was not required for this study because this study used existing CT images including raw data.
Institutional Review Board approval was obtained.
• diagnostic study
• performed at one institution
- 2.Motoyama S, Ito H, Sarai M et al (2018) Ultra-high-resolution computed tomography angiography for assessment of coronary artery stenosis. Circ J. https://doi.org/10.1253/circj.CJ-17-1281
- 3.Tanaka R, Yoshioka K, Takagi H, Schuijf JD, Arakita K (2018) Novel developments in non-invasive imaging of peripheral arterial disease with CT: experience with state-of-the-art, ultra-high-resolution CT and subtraction imaging. Clin Radiol. https://doi.org/10.1016/j.crad.2018.03.002
- 4.Yanagawa M, Hata A, Honda O et al (2018) Subjective and objective comparisons of image quality between ultra-high-resolution CT and conventional area detector CT in phantoms and cadaveric human lungs. Eur Radiol. https://doi.org/10.1007/s00330-018-5491-2
- 10.Euler A, Stieltjes B, Szucs-Farkas Z et al (2017) Impact of model-based iterative reconstruction on low-contrast lesion detection and image quality in abdominal CT: a 12-reader-based comparative phantom study with filtered back projection at different tube voltages. Eur Radiol 27:5252–5259CrossRefGoogle Scholar
- 14.Nakamoto A, Kim T, Hori M et al (2015) Clinical evaluation of image quality and radiation dose reduction in upper abdominal computed tomography using model-based iterative reconstruction; comparison with filtered back projection and adaptive statistical iterative reconstruction. Eur J Radiol 84:1715–1723CrossRefGoogle Scholar
- 17.Cohen J (1988) Statistical power analysis for the behavior sciences (2nd ed.) Lawrence Erlbaum Associates, Hillsdale, NJGoogle Scholar
- 21.American College of Radiology (2018) CT/MRI LI-RADS v2018 CORE. https://www.acr.org/Clinical-Resources/Reporting-and-Data-Systems/LI-RADS/CT-MRI-LI-RADS-v2018
- 24.American Association of Physicists in Medicine (2011) Size-specific dose estimates (SSDE) in pediatric and adult body CT examinations (Task Group 204). American Association of Physicists in Medicine, College Park. Available via https://www.aapm.org/pubs/reports/RPT_204.pdf. Accessed on 22 February 2019
- 27.Likert R (1932) A technique for the measurement of attitudes. Arch Psychol 140:55Google Scholar
- 29.Japan Association on Radiological Protection in Medicine (2015) Diagnostic reference levels based on latest surveys in Japan: Japan DRLs 2015. Available via http://www.radher.jp/J-RIME/report/DRLhoukokusyoEng.pdf. Accessed on 22 February 2019