Literature DB >> 33693996

Deep learning-based reconstruction may improve non-contrast cerebral CT imaging compared to other current reconstruction algorithms.

Luuk J Oostveen1, Frederick J A Meijer2, Frank de Lange2, Ewoud J Smit2, Sjoert A Pegge2, Stefan C A Steens2, Martin J van Amerongen2, Mathias Prokop2, Ioannis Sechopoulos2.   

Abstract

OBJECTIVES: To evaluate image quality and reconstruction times of a commercial deep learning reconstruction algorithm (DLR) compared to hybrid-iterative reconstruction (Hybrid-IR) and model-based iterative reconstruction (MBIR) algorithms for cerebral non-contrast CT (NCCT).
METHODS: Cerebral NCCT acquisitions of 50 consecutive patients were reconstructed using DLR, Hybrid-IR and MBIR with a clinical CT system. Image quality, in terms of six subjective characteristics (noise, sharpness, grey-white matter differentiation, artefacts, natural appearance and overall image quality), was scored by five observers. As objective metrics of image quality, the noise magnitude and signal-difference-to-noise ratio (SDNR) of the grey and white matter were calculated. Mean values for the image quality characteristics scored by the observers were estimated using a general linear model to account for multiple readers. The estimated means for the reconstruction methods were pairwise compared. Calculated measures were compared using paired t tests.
RESULTS: For all image quality characteristics, DLR images were scored significantly higher than MBIR images. Compared to Hybrid-IR, perceived noise and grey-white matter differentiation were better with DLR, while no difference was detected for other image quality characteristics. Noise magnitude was lower for DLR compared to Hybrid-IR and MBIR (5.6, 6.4 and 6.2, respectively) and SDNR higher (2.4, 1.9 and 2.0, respectively). Reconstruction times were 27 s, 44 s and 176 s for Hybrid-IR, DLR and MBIR respectively.
CONCLUSIONS: With a slight increase in reconstruction time, DLR results in lower noise and improved tissue differentiation compared to Hybrid-IR. Image quality of MBIR is significantly lower compared to DLR with much longer reconstruction times. KEY POINTS: • Deep learning reconstruction of cerebral non-contrast CT results in lower noise and improved tissue differentiation compared to hybrid-iterative reconstruction. • Deep learning reconstruction of cerebral non-contrast CT results in better image quality in all aspects evaluated compared to model-based iterative reconstruction. • Deep learning reconstruction only needs a slight increase in reconstruction time compared to hybrid-iterative reconstruction, while model-based iterative reconstruction requires considerably longer processing time.
© 2021. The Author(s).

Entities:  

Keywords:  Brain; Deep learning; Tomography, X-ray computed

Mesh:

Year:  2021        PMID: 33693996     DOI: 10.1007/s00330-020-07668-x

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


  10 in total

1.  Coronary artery plaques: cardiac CT with model-based and adaptive-statistical iterative reconstruction technique.

Authors:  Hans Scheffel; Paul Stolzmann; Christopher L Schlett; Leif-Christopher Engel; Gyöngi Petra Major; Mihály Károlyi; Synho Do; Pál Maurovich-Horvat; Udo Hoffmann
Journal:  Eur J Radiol       Date:  2011-12-23       Impact factor: 3.528

2.  Comparison of image quality and lens dose in helical and sequentially acquired head CT.

Authors:  N Abdeen; S Chakraborty; T Nguyen; M P dos Santos; M Donaldson; G Heddon; B A Schwarz
Journal:  Clin Radiol       Date:  2010-08-06       Impact factor: 2.350

3.  Deep learning-based image restoration algorithm for coronary CT angiography.

Authors:  Fuminari Tatsugami; Toru Higaki; Yuko Nakamura; Zhou Yu; Jian Zhou; Yujie Lu; Chikako Fujioka; Toshiro Kitagawa; Yasuki Kihara; Makoto Iida; Kazuo Awai
Journal:  Eur Radiol       Date:  2019-04-08       Impact factor: 5.315

4.  Wide-volume versus helical acquisition in unenhanced chest CT: prospective intra-patient comparison of diagnostic accuracy and radiation dose in an ultra-low-dose setting.

Authors:  Elsa Meyer; Aissam Labani; Mickaël Schaeffer; Mi-Young Jeung; Claire Ludes; Alain Meyer; Catherine Roy; Pierre Leyendecker; Mickaël Ohana
Journal:  Eur Radiol       Date:  2019-06-07       Impact factor: 5.315

5.  Evaluation of Low-Contrast Detectability of Iterative Reconstruction across Multiple Institutions, CT Scanner Manufacturers, and Radiation Exposure Levels.

Authors:  Ganesh Saiprasad; James Filliben; Adele Peskin; Eliot Siegel; Joseph Chen; Christopher Trimble; Zhitong Yang; Olav Christianson; Ehsan Samei; Elizabeth Krupinski; Alden Dima
Journal:  Radiology       Date:  2015-05-19       Impact factor: 11.105

Review 6.  Basics of iterative reconstruction methods in computed tomography: A vendor-independent overview.

Authors:  Wolfram Stiller
Journal:  Eur J Radiol       Date:  2018-10-26       Impact factor: 3.528

7.  Iterative reconstruction techniques for computed tomography part 2: initial results in dose reduction and image quality.

Authors:  Martin J Willemink; Tim Leiner; Pim A de Jong; Linda M de Heer; Rutger A J Nievelstein; Arnold M R Schilham; Ricardo P J Budde
Journal:  Eur Radiol       Date:  2013-01-16       Impact factor: 5.315

8.  Iterative reconstruction techniques for computed tomography Part 1: technical principles.

Authors:  Martin J Willemink; Pim A de Jong; Tim Leiner; Linda M de Heer; Rutger A J Nievelstein; Ricardo P J Budde; Arnold M R Schilham
Journal:  Eur Radiol       Date:  2013-01-12       Impact factor: 5.315

9.  Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and x-ray photography.

Authors:  R Gordon; R Bender; G T Herman
Journal:  J Theor Biol       Date:  1970-12       Impact factor: 2.691

10.  Deep Learning Reconstruction at CT: Phantom Study of the Image Characteristics.

Authors:  Toru Higaki; Yuko Nakamura; Jian Zhou; Zhou Yu; Takuya Nemoto; Fuminari Tatsugami; Kazuo Awai
Journal:  Acad Radiol       Date:  2020-01       Impact factor: 3.173

  10 in total
  2 in total

1.  Deep learning versus iterative image reconstruction algorithm for head CT in trauma.

Authors:  Zlatan Alagic; Jacqueline Diaz Cardenas; Kolbeinn Halldorsson; Vitali Grozman; Stig Wallgren; Chikako Suzuki; Johan Helmenkamp; Seppo K Koskinen
Journal:  Emerg Radiol       Date:  2022-01-05

2.  Deep Learning-Based Reconstruction vs. Iterative Reconstruction for Quality of Low-Dose Head-and-Neck CT Angiography with Different Tube-Voltage Protocols in Emergency-Department Patients.

Authors:  Marc Lenfant; Pierre-Olivier Comby; Kevin Guillen; Felix Galissot; Karim Haioun; Anthony Thay; Olivier Chevallier; Frédéric Ricolfi; Romaric Loffroy
Journal:  Diagnostics (Basel)       Date:  2022-05-21
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.