TrueFidelity

Pushing the science of image reconstruction further, TrueFidelity™ CT Images are a radical, next-generation improvement. This leap in image reconstruction elevates the vision of what you can achieve and offers unparalleled benefits for patients, along with the radiologists and technologists dedicated to their care.

At a glance

Vision that pushes radiology further

TrueFidelity CT Images elevate what you can achieve with Deep Learning Image Reconstruction (DLIR).

Where Deep Learning does its learning matters

Our proprietary DLIR training reflects unmatched understanding of what successful DLIR requires.

Confidence. Not compromise

Experience that can help improve scan read times and fight radiologist fatigue.

TrueFidelity for GSI now brings the potential to substantially reduce the image noise in all spectral image types

From virtual monochromatic images to material image pairs and virtual non-contrast images, with and without metal artifact reduction. Specifically, reducing the image noise inherent with low keV images resolves one of the traditional technical challenges in adopting more dual-energy protocols across the full patient population.

TrueFidelity Deep Learning Image Reconstruction | GE HealthCare

TrueFidelity Deep Learning Image Reconstruction | GE HealthCare

Image gallery

Reconstruction technology comparison

TrueFidelity for GSI: Revolution™ apex arterial phase abdomen

TrueFidelity for GSI: Revolution apex arterial phase abdomen

TrueFidelity for GSI: Revolution apex arterial phase pancreas

TrueFidelity for GSI: Revolution apex metastatic gastric carcinoma BMI 33

TrueFidelity for GSI: Revolution apex rectal cancer with liver mets

Features

Where deep learning does its learning matters.

A deep learning image reconstruction application is only as good as the training it receives. GE HealthCare trained its reconstruction engine using a library of thousands of low noise, filtered back projection (FBP) images considered the gold standard of image quality.

Designing

Creating layers of mathematical equations, a Deep Neural Network (DNN) that can handle millions of parameters.

Training

Inputting a high noise sinogram through the DNN and comparing the output image to a low noise version of the same image. These two images are compared across multiple parameters such as image noise, low contrast resolution, low contrast detectability, noise texture etc. The output image reports the differences to the network via back propagation, which trains and strengthens the DNN based on the desired output.

Verifying

The network is required to reconstruct clinical and phantom cases it has never seen before, including extremely rare cases designed to push the network to its limits, confirming its robustness.

"The sharpness of the images is a breakthrough development in image reconstruction algorithms. We see details that we have never seen before. Abdominal, Lung and Cardiac Imaging benefits most from this technology. I am mainly interested in cardiac and cardiovascular imaging. We found much better image quality, depiction of details, and image sharpness for cardiac valves, sclerotic and soft plaque in cardiac and extracardiac vessels, as well as fewer artifacts around stents and stent-grafts. DECT for pulmonary embolism easily convinced everybody in our Department."

Prof. Klaus Hergan

University Hospital Salzburg, Austria Department of Radiology of the 1200-bed University Hospital Salzburg