US Patent Issued to University of Virginia Patent Foundation on Jan. 13 for "Method and system for low-field MRI denoising with a deep complex-valued convolutional neural network" (Virginia Inventors)

ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,521,033, issued on Jan. 13, was assigned to University of Virginia Patent Foundation (Charlottesville, Va.).

"Method and system for low-field MRI denoising with a deep complex-valued convolutional neural network" was invented by Quan Dou (Charlottesville, Va.), Zhixing Wang (Charlottesville, Va.), Xue Feng (Zion Crossroads, Va.) and Craig H. Meyer (Charlottesville, Va.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Blurring and noise artifacts in magnetic resonance (MR) images caused by off-resonant image components may be corrected with convolutional neural networks, particularly feed forward networks with skip connections. Demodulating complex blurred...