FDA Clears AI-Based MR Tool to Reduce Noise, Enhance Signal

MR image reconstruction could see a step forward.

Canon Medical Systems announced Wednesday it has received 510(k) clearance from the U.S. Food & Drug Administration for its Advanced intelligent Clear-IQ Engine (AiCE). This tool is designed for the Vantage Galan 3T MR system and expands access to the company’s Deep Learning Reconstruction (DLR) technology.

According to a company statement, the technology, which is also available across Canon Medical’s CT product portfolio, employs a deep learning algorithm to distinguish true MR signal from noise, suppressing the noise while simultaneously enhancing the signal.

“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,” said Jonathan Furuyama, managing director of Canon Medical Systems USA, Inc.’s MR business unit.

Trained on a significant amount of high-quality image data, AiCE has a deep learning neural network that can, potentially, reduce noise and boost the MR signal for quicker delivery of clear, distinct images. Based on the company statement, the technology offers these capabilities:

• High-quality images: By differentiating true signal from noise, AiCE can match the spatial resolution and low-noise properties of advanced scanning and reconstruction. The anatomy’s true structure remains.

• Seamless integration into routine practice: According to Canon, as the first-in-industry fully integrated deep learning reconstruction for MR, AiCE is built directly into scan protocols for seamless workflow.