Canon Medical Systems USA has secured 510(k) clearance from the US Food and Drug Administration (FDA) for Advanced intelligent Clear-IQ Engine (AiCE).

Designed for Vantage Galan 3T MR system, the AiCE is expected to further expand access to its deep learning reconstruction (DLR) technology.

Canon Medical claims that the Vantage Galan 3T is the first system in its MR product portfolio with access to AiCE.

Majority of Canon Medical’s CT product portfolio comprises DLR technology

A majority of the company’s CT product portfolio feature the DLR technology, which employs a deep learning algorithm to differentiate true MR signal from noise and suppress the noise while enhancing signal, building new frontier for MR image reconstruction standard.

Canon Medical Systems USA MR business unit managing director Jonathan Furuyama said: “AiCE utilises a next generation approach to MR image reconstruction, further proving Canon Medical’s leadership and commitment to innovation in diagnostic imaging.

“With the expansion of this unique DLR method across modalities and into MR, we’re elevating diagnostic imaging capabilities for our customers by bringing the power of AI to routine imaging to provide more possibilities in improving patient care than ever before.”

Trained on a significant amount of high-quality image data, AiCE has a deep learning neural network that can possibly decrease noise and boost the MR signal for quicker delivery of sharp, clear and distinct images.

By distinguishing true signal from noise, AiCE can match the spatial resolution and low-noise properties of advanced scanning and reconstruction. The tool also helps in maintaining the anatomy’s true structure.

According to the company, physicians stated their preference for AiCE images for clarity and resolution following a blinded image comparison of AiCE DLR reconstructed images with images reconstructed with conventional methods without AiCE.

In February, Canon Medical Systems USA has secured 510(k) clearance from the US FDA for its Aquilion ONE / PRISM Edition, which helps advance deep learning spectral capabilities for routine spectral imaging.