Fuminari Tatsugami1, Toru Higaki2, Yuko Nakamura2, Zhou Yu3, Jian Zhou3, Yujie Lu3, Chikako Fujioka4, Toshiro Kitagawa5, Yasuki Kihara5, Makoto Iida2, Kazuo Awai2. 1. Department of Diagnostic Radiology, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima, 734-8551, Japan. sa104@rg8.so-net.ne.jp. 2. Department of Diagnostic Radiology, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima, 734-8551, Japan. 3. Canon Medical Research USA, Inc., 706 N Deerpath Drive, Vernon Hills, IL, 60061, USA. 4. Department of Radiology, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima, 734-8551, Japan. 5. Department of Cardiovascular Medicine, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima, 734-8551, Japan.
Abstract
OBJECTIVES: The purpose of this study was to compare the image quality of coronary computed tomography angiography (CTA) subjected to deep learning-based image restoration (DLR) method with images subjected to hybrid iterative reconstruction (IR). METHODS: We enrolled 30 patients (22 men, 8 women) who underwent coronary CTA on a 320-slice CT scanner. The images were reconstructed with hybrid IR and with DLR. The image noise in the ascending aorta, left atrium, and septal wall of the ventricle was measured on all images and the contrast-to-noise ratio (CNR) in the proximal coronary arteries was calculated. We also generated CT attenuation profiles across the proximal coronary arteries and measured the width of the edge rise distance (ERD) and the edge rise slope (ERS). Two observers visually evaluated the overall image quality using a 4-point scale (1 = poor, 4 = excellent). RESULTS: On DLR images, the mean image noise was lower than that on hybrid IR images (18.5 ± 2.8 HU vs. 23.0 ± 4.6 HU, p < 0.01) and the CNR was significantly higher (p < 0.01). The mean ERD was significantly shorter on DLR than on hybrid IR images, whereas the mean ERS was steeper on DLR than on hybrid IR images. The mean image quality score for hybrid IR and DLR images was 2.96 and 3.58, respectively (p < 0.01). CONCLUSIONS: DLR reduces the image noise and improves the image quality at coronary CTA. KEY POINTS: • Deep learning-based image restoration is a new technique that employs the deep convolutional neural network for image quality improvement. • Deep learning-based restoration reduces the image noise and improves image quality at coronary CT angiography. • This method may allow for a reduction in radiation exposure.
OBJECTIVES: The purpose of this study was to compare the image quality of coronary computed tomography angiography (CTA) subjected to deep learning-based image restoration (DLR) method with images subjected to hybrid iterative reconstruction (IR). METHODS: We enrolled 30 patients (22 men, 8 women) who underwent coronary CTA on a 320-slice CT scanner. The images were reconstructed with hybrid IR and with DLR. The image noise in the ascending aorta, left atrium, and septal wall of the ventricle was measured on all images and the contrast-to-noise ratio (CNR) in the proximal coronary arteries was calculated. We also generated CT attenuation profiles across the proximal coronary arteries and measured the width of the edge rise distance (ERD) and the edge rise slope (ERS). Two observers visually evaluated the overall image quality using a 4-point scale (1 = poor, 4 = excellent). RESULTS: On DLR images, the mean image noise was lower than that on hybrid IR images (18.5 ± 2.8 HU vs. 23.0 ± 4.6 HU, p < 0.01) and the CNR was significantly higher (p < 0.01). The mean ERD was significantly shorter on DLR than on hybrid IR images, whereas the mean ERS was steeper on DLR than on hybrid IR images. The mean image quality score for hybrid IR and DLR images was 2.96 and 3.58, respectively (p < 0.01). CONCLUSIONS: DLR reduces the image noise and improves the image quality at coronary CTA. KEY POINTS: • Deep learning-based image restoration is a new technique that employs the deep convolutional neural network for image quality improvement. • Deep learning-based restoration reduces the image noise and improves image quality at coronary CT angiography. • This method may allow for a reduction in radiation exposure.
Authors: Alexander Lembcke; Till H Wiese; Joerg Schnorr; Susanne Wagner; Juergen Mews; Thomas J Kroencke; Christian N H Enzweiler; Bernd Hamm; Matthias Taupitz Journal: Invest Radiol Date: 2004-06 Impact factor: 6.016
Authors: Fuminari Tatsugami; Lars Husmann; Bernhard A Herzog; Nina Burkhard; Ines Valenta; Oliver Gaemperli; Philipp A Kaufmann Journal: AJR Am J Roentgenol Date: 2009-03 Impact factor: 3.959
Authors: Jörg Hausleiter; Tanja Meyer; Franziska Hermann; Martin Hadamitzky; Markus Krebs; Thomas C Gerber; Cynthia McCollough; Stefan Martinoff; Adnan Kastrati; Albert Schömig; Stephan Achenbach Journal: JAMA Date: 2009-02-04 Impact factor: 56.272
Authors: Samjhana Thapaliya; Samuel L Brady; Elanchezhian Somasundaram; Christopher G Anton; Brian D Coley; Alexander J Towbin; Bin Zhang; Jonathan R Dillman; Andrew T Trout Journal: Abdom Radiol (NY) Date: 2021-10-04
Authors: Thomas Weikert; Marco Francone; Suhny Abbara; Bettina Baessler; Byoung Wook Choi; Matthias Gutberlet; Elizabeth M Hecht; Christian Loewe; Elie Mousseaux; Luigi Natale; Konstantin Nikolaou; Karen G Ordovas; Charles Peebles; Claudia Prieto; Rodrigo Salgado; Birgitta Velthuis; Rozemarijn Vliegenthart; Jens Bremerich; Tim Leiner Journal: Eur Radiol Date: 2020-11-19 Impact factor: 5.315
Authors: Luuk J Oostveen; Frederick J A Meijer; Frank de Lange; Ewoud J Smit; Sjoert A Pegge; Stefan C A Steens; Martin J van Amerongen; Mathias Prokop; Ioannis Sechopoulos Journal: Eur Radiol Date: 2021-03-10 Impact factor: 5.315