Deep Resolve
MRI – Faster than ever before
Sacrificing high image quality for acquisition speed is a thing of the past. Our Deep Resolve Knowledge Hub provides a deep dive into the usability of our deep learning reconstruction technology and clinical examples that demonstrate excellent image quality and acquisition speed. In addition, you will hear from clinical users on how Deep Resolve redefined MRI in their practice.
Deep Resolve has multiple techniques to increase scan speed and improve image quality, including the AI-powered Deep Resolve Sharp with Deep Resolve Boost, that take advantage of convolutional neural networks to accelerate MR scans, e.g., 70% for brain imaging, making them faster than ever before. Faster scans boost workflow efficiency while improving the patient experience. Deep Resolve’s raw data-to-image reconstruction and very fast acquisition are game changers in MRI, helping generate actionable insights for patients' diagnoses.
Deep Resolve Gain
Deep Resolve Gain is a smart targeted denoising method to increase the SNR of MR images. It uses the acquired MRI data to generate a noise map which reflects spatial noise variations. This noise map is used as input for an iterative process, reducing noise in a targeted manner, thus addressing local variations in image noise, e.g., due to coil array geometry.
Deep Resolve Boost
Deep Resolve Boost is our raw data-to-image deep learning reconstruction technology. It enables accelerated image acquisition with high signal-to-noise (SNR) scans. Deep Resolve Boost is applicable from head-to-toe and can be combined with our Simultaneous Multi-Slice (SMS) technique for even higher acceleration. A total knee exam can be completed in under two minutes scan time without compromising image resolution.
Deep Resolve Sharp
The neural network at the heart of Deep Resolve Sharp improves image sharpness and resolution. Deep Resolve Sharp has been trained on a large amount of pairs of low-res and high-res MR data, enabling it to reconstruct a sharp image from low resolution data. While doing this, the consistency with the acquired raw data is ensured until the final image reconstruction for robust results.
Deep Resolve Swift Brain is a neuro acquisition solution that employs a multi-shot echo planar imaging (EPI) approach to enable a total neuro exam in two minutes scan time without compromising image quality. A novel static field correction method reduces geometric distortions inherent in EPI imaging. The deep learning reconstruction enables consistent high-resolution images with fast acquisition, achieving all relevant contrasts in just one go.
MR scanning has not been established as safe for imaging fetuses and infants less than two years of age. The responsible physician must evaluate the benefits of the MR examination compared to those of other imaging procedures.
