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:
  • Our best low-contrast resolution, ever. 1,3
  • Dose neutral industry-leading ultra-high resolution2
  • Improved low-contrast detectability, noise and spatial resolution relative to hybrid iterative reconstruction
  • Image noise texture more similar to FBP compared to MBIR reconstruction3
  • Fast reconstruction
  • Easy workflow

1 1.5mm @ 0.3%, 22 mGy
2 Aquilion Precision, Dose neutral between ultra-high resolution mode with AiCE and normal resolution mode with hybrid iterative reconstruction
3 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 SizeCTDIvol
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
CTP344, Phantom Labs

*Aquilion ONE / GENESIS Edition


AiCE Deep Learning Reconstruction:
Bringing the power of Ultra-High Resolution CT to routine imaging

Senior Manager, Medical Physics
Kirsten Boedeker, PhD, DABR

Canon Medical Systems Corporation

Click to read


[AiCE] enables phenomenal patient dose reduction, up to 90% below the National Diagnostic Reference Levels.”

Dr. Richard Hawkins,
Consultant Radiologist,
Mid Cheshire Hospitals NHS Foundation Trust,
United Kingdom

Click to read


Chuluunbaatar et. al | Deep learning reconstruction allows for usage of contrast agent of lower concentration for coronary CTA than filtered back projection and hybrid iterative reconstruction | Acta Radiol. (2023)

Goto et al. | Lung-Optimized Deep-Learning-Based Reconstruction for Ultralow-Dose CT |Acad Radiol. (2023)

Ludes et al. | Impact of a reduced iodine load with deep learning reconstruction on abdominal MDCT | Medicine (Baltimore). (2023)

Zhang et al. | Image quality comparison of lower extremity CTA between CT routine reconstruction algorithms and deep learning reconstruction | BMC Med Imaging (2023)

Chuluunbaatar et al. | Improvement in Image Quality and Visibility of Coronary Arteries, Stents, and Valve Structures on CT Angiography by Deep Learning Reconstruction | J Radiol. (2022)

Greffer et al. | Effect of a new deep learning image reconstruction algorithm for abdominal computed tomography imaging on image quality and dose reduction compared with two iterative reconstruction algorithms: A phantom study | Quantitative Imaging in Medicine and Surgery (2022)

Michallek et al. | Deep learning reconstruction improves radiomics feature stability and discriminative power in abdominal CT imaging: a phantom study | Eur Radiol. (2022)

Mikayama et al. | Deep-learning reconstruction for ultra-low-dose lung CT: Volumetric measurement accuracy and reproducibility of artificial ground-glass nodules in a phantom study | Br J Radiol. (2022)

Takafuji et al. | Deep-learning reconstruction to improve image quality of myocardial dynamic CT perfusion: comparison with hybrid iterative reconstruction | Clin Radiol. (2022)

Tanabe et al. |Deep learning-based reconstruction of chest ultra-high-resolution computed tomography and quantitative evaluations of smaller airways | Respir Investig. (2022)

Zhang et al. | Value of deep learning reconstruction at ultra-low-dose CT for evaluation of urolithiasis | European Radiology (2022)

Bernard et al. | Deep learning reconstruction versus iterative reconstruction for cardiac CT angiography in a stroke imaging protocol: reduced radiation dose and improved image quality | Quant Imaging Med Surg. (2021)

Chuluunbaatar et al. | Improvement of depiction of the intracranial arteries on brain CT angiography using deep learning reconstruction | J Integr Neurosci. (2021)

McLeavy et al. | The future of CT: deep learning reconstruction | Clin Radiol. (2021)

Tamura et al. | Superior objective and subjective image quality of deep learning reconstruction for low-dose abdominal CT imaging in comparison with model-based iterative reconstruction and filtered back projection | Br J Radiol. (2021)

Lenfant et al. | Deep Learning Versus Iterative Reconstruction for CT Pulmonary Angiography in the Emergency Setting: Improved Image Quality and Reduced Radiation Dose | Diagnostics (2020)

Nakamura et al. | Possibility of Deep Learning in Medical Imaging Focusing Improvement of Computed Tomography Image Quality | J Comput Assist Tomogr (2019)

Higaki et al. | Improvement of image quality at CT and MRI using deep learning | Japanese Journal of Radiology (2019)

Akagi et al. | Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT | European Radiology (2019)
Contact Us