Achieve high SNR images with Deep Learning Reconstruction

Deep Learning

The deep learning methods of the Deep Convolutional Neural Network (DCNN) are able to process enormous amounts of data through an network of decision making nodes, or neurons, and are well regarded for their excellent performance in image recognition-based applications.

Deep Learning Reconstruction (DLR)

AiCE was trained on vast amounts of high-SNR MRI images reconstructed with an advanced algorithm that is too computationally intensive for clinical use. This training taught AiCE to distinguish true signal from noise. The results were validated by a team of radiologists, medical physicists, AI scientists, and clinical researchers, producing a fast, fully-trained reconstruction algorithm ready for clinical use.

Intelligently removes noise

Following images demonstrates noise subtraction from the same original image utilizing a conventional filter compared to AiCE. With the conventional filter some necessary anatomical information has been removed along with the noise, AiCE intelligently identifies noise from the original image due to the deep learning algorithms.

PIQE is high resolution Deep Learning Reconstruction for MRI

PIQE increases matrix size, removes noise, and delivers sharp anatomical images to take MR imaging to the next level.
Learn more about PIQE