The FDA has given Canon Medical Systems USA the go-ahead to commence distribution of its deep convolutional neural network (DCNN) image reconstruction technology for CT.

Advanced Intelligent Clear-IQ Engine (AiCE) is capable of suppressing noise and enhancing signal with its deep learning algorithm for sharper images scanned on Canon’s premium imager, Aquilion ONE GENESIS.

“Our AiCE technology utilizes a next-generation approach to CT image reconstruction, further proving Canon Medical’s leadership and commitment to innovation in diagnostic imaging,” said Dominic Smith, senior director of CT, PET/CT, and MR Business Units at Canon Medical Systems USA, in a statement. “This technology doesn’t just meet our customers’ evolving needs, it exceeds them, opening doors to clearer, more precise images to help optimize patient care.”
Learning from the high image quality of model-based iterative reconstruction (MBIR), the algorithm reconstructs CT images with improved spatial resolution and at a rate that is three to five times faster than conventional MBIR. It utilizes thousands of features learned during training to distinguish signal from noise for improved resolution, and applies a pre-trained DCNN to enhance spatial resolution and reduce noise at the same time. This allows for reconstruction to take place at a pace fast enough for busy clinical environments.

In the U.S., AiCE is only cleared for the Aquilion ONE / GENESIS.

CT Homepage