Canon showcases CT image reconstruction tech and software upgrade at ECR

by John R. Fischer, Senior Reporter | March 05, 2019
Artificial Intelligence CT Health IT X-Ray
AiCE (Advanced Intelligent
Clear-IQ Engine)
Canon Medical Systems showcased, for the first time, its deep convolutional neural network (DCNN) image reconstruction technology for CT imaging at the 2019 European Congress of Radiology last week in Vienna.

Named AiCE (Advanced Intelligent Clear-IQ Engine), the solution applies deep learning to remove noise while preserving true signals in clinical images of any part of the human body scanned by Canon’s premium scanner, Aquilion ONE GENESIS.

“By removing that noise very effectively with the AI technology, we can reduce dose further by a reduction of 20 to 40 percent, depending on the body region; reduce dose at the same image quality; further improve image quality at the same dose; or calculate very thin slices at very high image quality with still very low dose,” Joerg Schlegel, senior product marketing manager for Canon Medical Systems Europe, told HCB News.
DOTmed text ad

New Fully Configured 80-slice CT in 2 weeks with Software Upgrades for Life

For those who need to move fast and expand clinical capabilities -- and would love new equipment -- the uCT 550 Advance offers a new fully configured 80-slice CT in up to 2 weeks with routine maintenance and parts and Software Upgrades for Life™ included.


Such qualities emphasize the importance of this technology for scanners such as Aquilion Precision, which possesses 0.25 millimeter-sized elements, compared to the standard element size of 0.5 for conventional scanners. Because of this quarter difference, the Aquilion Precision either must be very sensitive or require a greater dose in order to produce suitable images.

The addition of AiCE, however, eliminates this challenge, allowing the system to produce high-resolution images at the same dose of a conventional scanner but on a smaller scale of resolution.

The program is trained on high-quality target data from real-patient data sets, extensively processed with advanced Model-Based Iterative Reconstruction (MBIR) for optimal image quality and improved spatial background. It is then validated and implemented on to scanners to provide reconstruction speeds fast enough for busy clinical environments.

In addition to AiCE’s official debut, the Japanese healthcare giant used the event as an opportunity to introduce its new Global Illumination functionality for its existing Vitrea Advanced Visualization modular viewing platform, which provides a range of advanced multi-vendor applications for all modalities.

Global Illumination

The feature enables the delivery of photorealistic 3D renderings of the human anatomy, allowing users to see smaller details such as tendons more clearly, and enhances communication between clinicians and medical professionals such as oncologists and surgeons. It also improves the ability to help patients better understand their anatomy and pathology, and provides support to post-mortem examinations and forensics.

“3D requires a very trained eye to read the 3D images. The communication with other professionals and patients is not so easy, and this new software, or the new way of rendering, helps to improve this way of communication,” said Schlegel. “We need technology like this to communicate among specialties, especially in sharing information with those who are not trained in reading MR and CT images.”

AiCE technology is currently available on Aquilion Precision and Aquilion ONE GENESIS. Global Illumination has been built into standard Vitrea Advanced Visualization platforms that are on sale now and can be bought as an upgrade by providers already equipped with the solution.

You Must Be Logged In To Post A Comment