Sharp, clear and distinct images. At low dose.
Harnessing the enormous computational power of a Deep Convolutional Neural Network (DCNN), Advanced intelligent Clear-IQ Engine (AiCE) is trained to differentiate signal from noise, so that the algorithm can suppress noise while enhancing signal. Because it is trained with advanced MBIR, it exhibits high spatial resolution. But unlike MBIR, AiCE deep learning reconstruction overcomes the challenges (image appearance and/or reconstruction speed) in clinical adoption.
AiCE deep learning reconstruction features:
AiCE deep learning reconstruction features:
- Our best low-contrast resolution, ever. 1,2
- Improved low-contrast detectability, noise and spatial resolution relative to hybrid iterative reconstruction
- Image noise texture more similar to FBP compared to MBIR reconstruction2
- Fast reconstruction
- Easy workflow
1 1.5mm @ 0.3%, 22 mGy
2 Aquilion ONE / GENESIS Edition
Redefining the balance of IQ, speed and dose.
Fast reconstruction speed:
- 3-5x faster than MBIR1
High image quality:
- Improved spatial resolution compared to AIDR 3D
- Improved low contrast detectability compared to AIDR 3D
- Image noise appearance more similar to filtered back projection1
1 As compared to MBIR, only applicable to AiCE on Aquilion ONE / GENESIS Edition
Low Contrast Detectability*
Body, Lung and Cardiac
| Object Size | CTDIvol |
| 3 mm at 0.3% | 5.3 mGy |
| 2 mm at 0.3% | 10.5 mGy |
| 1.5mm at 0.3% | 22.6 mGy |
| Scan Parameters | |
| 10mm with AiCE Body | |
| Phantom | |
| CTP344, Phantom Labs | |
*Aquilion ONE / GENESIS Edition
Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT
Authors: Motonori Akagi et al.
Journal: European Radiology
Published: 11/04/2019
Copyright: European Society of Radiology 2019
