Literature DB >> 30976831

Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT.

Motonori Akagi1, Yuko Nakamura2, Toru Higaki1, Keigo Narita1, Yukiko Honda1, Jian Zhou3, Zhou Yu3, Naruomi Akino4, Kazuo Awai1.   

Abstract

OBJECTIVES: 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).
METHODS: 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.
RESULTS: 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.
CONCLUSIONS: DLR improved the quality of abdominal U-HRCT images. KEY POINTS: • 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.

Entities:  

Keywords:  Artificial intelligence; Liver; Machine learning; Neural networks (computer); X-ray computed tomography

Mesh:

Year:  2019        PMID: 30976831     DOI: 10.1007/s00330-019-06170-3

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  58 in total

1.  Deep learning-based image reconstruction for brain CT: improved image quality compared with adaptive statistical iterative reconstruction-Veo (ASIR-V).

Authors:  Injoong Kim; Hyunkoo Kang; Hyun Jung Yoon; Bo Mi Chung; Na-Young Shin
Journal:  Neuroradiology       Date:  2020-10-10       Impact factor: 2.804

2.  Low-dose CT angiography using ASiR-V for potential living renal donors: a prospective analysis of image quality and diagnostic accuracy.

Authors:  Woong Kyu Han; Joon Chae Na; Sung Yoon Park
Journal:  Eur Radiol       Date:  2019-08-30       Impact factor: 5.315

Review 3.  Artificial Intelligence: reshaping the practice of radiological sciences in the 21st century.

Authors:  Issam El Naqa; Masoom A Haider; Maryellen L Giger; Randall K Ten Haken
Journal:  Br J Radiol       Date:  2020-02-01       Impact factor: 3.039

4.  CT iterative reconstruction algorithms: a task-based image quality assessment.

Authors:  J Greffier; J Frandon; A Larbi; J P Beregi; F Pereira
Journal:  Eur Radiol       Date:  2019-07-29       Impact factor: 5.315

Review 5.  Advanced CT techniques for assessing hepatocellular carcinoma.

Authors:  Yuko Nakamura; Toru Higaki; Yukiko Honda; Fuminari Tatsugami; Chihiro Tani; Wataru Fukumoto; Keigo Narita; Shota Kondo; Motonori Akagi; Kazuo Awai
Journal:  Radiol Med       Date:  2021-05-05       Impact factor: 3.469

6.  Performance of clinically available deep learning image reconstruction in computed tomography: a phantom study.

Authors:  Hiroki Kawashima; Katsuhiro Ichikawa; Tadanori Takata; Wataru Mitsui; Hiroshi Ueta; Norihide Yoneda; Satoshi Kobayashi
Journal:  J Med Imaging (Bellingham)       Date:  2020-12-16

7.  Deep learning reconstruction versus iterative reconstruction for cardiac CT angiography in a stroke imaging protocol: reduced radiation dose and improved image quality.

Authors:  Angélique Bernard; Pierre-Olivier Comby; Brivaël Lemogne; Karim Haioun; Frédéric Ricolfi; Olivier Chevallier; Romaric Loffroy
Journal:  Quant Imaging Med Surg       Date:  2021-01

8.  Influence of a novel deep-learning based reconstruction software on the objective and subjective image quality in low-dose abdominal computed tomography.

Authors:  Andrea Steuwe; Marie Weber; Oliver Thomas Bethge; Christin Rademacher; Matthias Boschheidgen; Lino Morris Sawicki; Gerald Antoch; Joel Aissa
Journal:  Br J Radiol       Date:  2020-10-23       Impact factor: 3.039

9.  Low-dose CT urography using deep learning image reconstruction: a prospective study for comparison with conventional CT urography.

Authors:  Yannan Cheng; Yangyang Han; Jianying Li; Ganglian Fan; Le Cao; Junjun Li; Xiaoqian Jia; Jian Yang; Jianxin Guo
Journal:  Br J Radiol       Date:  2021-02-24       Impact factor: 3.039

10.  Advantages and disadvantages of single-source dual-energy whole-body CT angiography with 50% reduced iodine dose at 40 keV reconstruction.

Authors:  Yoshifumi Noda; Fumihiko Nakamura; Noriyuki Yasuda; Toshiharu Miyoshi; Nobuyuki Kawai; Hiroshi Kawada; Fuminori Hyodo; Masayuki Matsuo
Journal:  Br J Radiol       Date:  2021-02-22       Impact factor: 3.039

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.