FDA clears Canon Medical’s DCNN CT image reconstruction technology

Canon Medical Systems USA of Tustin, CA, announced that it has received 510(k) clearance from the U.S. Food and Drug Administration for its Advanced Intelligent Clear-IQ Engine (AiCE), new deep convolutional neural network (DCNN) image reconstruction technology for computed tomography (CT) images.

AiCE suppresses noise while enhancing signal by using a deep learning algorithm to differentiate signal from noise. It has the ability to learn from the high image quality of Model Based Iterative Reconstruction (MBIR) software to reconstruct CT images with improved spatial resolution three to five times faster than traditional MBIR.

A pre-trained DCNN is applied to enhance spatial resolution while noise is reduced simultaneously. The company stated that thousands of features learned during training help differentiate signal from noise with improved resolution using AiCE’s deep learning approach.

© Anderson Publishing, Ltd. 2024 All rights reserved. Reproduction in whole or part without express written permission Is strictly prohibited.