One of the main challenges in MRI is finding the optimal balance between the signal-to-noise ratio (SNR) and image resolution. A higher spatial resolution could improve visualization of structures, but when spatial resolution is increased, SNR drops. To regain SNR, typically scan times need to be increased, reducing patient comfort and decreasing throughput.
Canon Medical found a solution in artificial intelligence: AiCE. AiCE is a deep-learning based solution trained on vast amounts of low and high signal-to-noise MR images to detect noise and remove it from the MR images. By removing noise, AiCE contributes to the increase in spatial resolution or reduction in acquisition time.
AiCE expands diagnostic capabilities, enriches radiologist’s confidence and reduces examination times and thus improves patient comfort. With AiCE we enter a new era in MRI. //
“I’m impressed by the ease-of-use, how it maintains image contrast and structural detail, while at the same time eliminating noise.”
Prof. Garry E. Gold,
Clinical radiologist and researcher, Past president of the International Society for Magnetic Resonance in Medicine (ISMRM) and the Society of Computed Body Tomography and Magnetic Resonance (SCBT/MR)
The content reflects information available at the time of publication and may differ from current information.