News | Artificial Intelligence | May 29, 2020

Deep Learning-Based MR Image Reconstruction Tech From GE Healthcare Now FDA Cleared

With COVID-19 postponing up to 5,000,000 U.S. patients’ MR scans to date, AIR Recon DL can help providers process the backlog faster without compromising image quality

AIR Recon DL delivers shorter scans and better image quality (Photo: Business Wire)

AIR Recon DL delivers shorter scans and better image quality (Photo: Business Wire).

May 29, 2020 — GE Healthcare announced U.S. FDA 510(k) clearance of AIR Recon DL. This pioneering technology, using a deep learning-based neural network, improves the patient experience through shorter scan times while also increasing diagnostic confidence with better image quality across all anatomies. AIR Recon DL, developed on GE Healthcare’s Edison intelligence platform, seamlessly integrates into the clinical workflow to generate AIR Recon DL images in real-time at the operator’s console.

Until now, there was an inherent compromise in MR between image quality and scan time. Better image quality achieved through higher signal-to-noise (SNR) and/or spatial resolution needed to show anatomical detail necessitated long scan times. Shorter scans, aimed to improve patient comfort and productivity, compromised image quality and diagnostic confidence. Now with AIR Recon DL, clinicians and technologists will no longer have to choose between image quality and scan time.

“In our experience, [AIR Recon DL] enables us to back off on the number of [signal] averages or achieve a higher matrix, to either save on scan time or achieve a higher resolution image,” said Hollis Potter, M.D., chairman of the department of radiology and imaging at Hospital for Special Surgery in New York City.

Unlike conventional post processing-based approaches that can obscure image detail, AIR Recon DL is a deep learning-based reconstruction engine making full use of raw data for maximum image quality. In addition to improving SNR, this technology features a unique intelligent ringing suppression that preserves fine image details, helping address two common pain points for radiologists and technologists—image noise and ringing.

AIR Recon DL was developed in partnership with global institutions and has been evaluated on thousands of cases across a wide range of anatomies and patient demographics. Feedback from clinical users has been overwhelmingly positive, including users noticing sharper and less noisy images enabling shorter scan times, increased reader confidence, reducing the need for repeat scans, and more scan-to-scan consistency.

“We are proud to bring the next generation of MR image reconstruction to the industry leveraging the latest technological revolution in artificial intelligence,” said Jie Xue, president and CEO of GE Healthcare MR. “AIR Recon DL benefits clinicians, technologists and patients alike. As we transition to a post-COVID world, MR providers face a significant backlog of patient exams. AIR Recon DL can not only help providers scan more patients per day, but also allows more time to disinfect equipment between patients.”

Partners in the development and clinical validation of AIR Recon DL included Hospital for Special Surgery, University of California San Francisco, RadNet, University of Wisconsin-Madison, MD Anderson Cancer Center, Medical College of Wisconsin, Centre Cardiologique du Nord in France, Erasmus Medical Center in the Netherlands, Centro Cardiologico Monzino in Italy, University of Yamanashi and Keio University in Japan, and Asan Medical Center and Haeundae Paik Hospital in Korea.

AIR Recon DL was developed on GE Healthcare’s Edison intelligence platform, which helps GE and strategic partners design, develop, manage, secure and distribute advanced applications and AI algorithms quickly.

AIR Recon DL is available as an upgrade or with new system purchases. It is currently available on GE Healthcare’s 3.0T MR systems.

For more information: www.ge.com

 

Related Content

Single-slice of the chest CT showing the abnormalities. Arrows indicate the location of the breast mass (red arrow), lymphadenopathy (blue arrow), and a lung nodule (yellow arrow). Arrows not present in experimental display. Image courtesy of Psychonomic Bulletin & Review

Single-slice of the chest CT showing the abnormalities. Arrows indicate the location of the breast mass (red arrow), lymphadenopathy (blue arrow), and a lung nodule (yellow arrow). Arrows not present in experimental display. Image courtesy of Psychonomic Bulletin & Review

Feature | Radiology Imaging | November 20, 2020
There’s a classic video demonstrating how our brains process information and allocate attention in which people bounc
Ziehm Imaging will showcase its leading portfolio of mobile C-arms and advanced pre- and intraoperative image-based decision support solutions on its virtual RSNA 2020 booth
News | Mobile C-Arms | November 20, 2020
November 20, 2020 — Ziehm Imaging will showcase its leading portfolio of...
Densitas Inc., a global provider of A.I. technologies for digital mammography and breast screening, announced its partnership with Mammography Educators to offer the first artificial intelligence powered telehealth technologist training platform to support business continuity in mammography facilities.
News | Mammography | November 20, 2020
November 20, 2020 — Densitas Inc., a global provider of A.I.
1H-MR spectra of 3 consecutive patients with COVID-19. Upper row: Axial FLAIR images at the corona radiata level show representative MRS voxels (black squares) from sampled periventricular regions. Lower row: Corresponding spectrum (black) and LCModel fit (red) from each patient acquired at TE = 30 ms (upper row) and TE = 288 ms (lower row). A, A patient with COVID-19-associated multifocal necrotizing leukoencephalopathy shows diffuse patchy WM lesions with markedly increased Cho and decreased NAA, as well

1H-MR spectra of 3 consecutive patients with COVID-19. Upper row: Axial FLAIR images at the corona radiata level show representative MRS voxels (black squares) from sampled periventricular regions. Lower row: Corresponding spectrum (black) and LCModel fit (red) from each patient acquired at TE = 30 ms (upper row) and TE = 288 ms (lower row). A, A patient with COVID-19-associated multifocal necrotizing leukoencephalopathy shows diffuse patchy WM lesions with markedly increased Cho and decreased NAA, as well as elevated Lac. B, A patient with COVID-19 after recent PEA cardiac arrest with subtle FLAIR hyperintense white matter changes also shows elevated Cho/Cr and decreased NAA/Cr ratios. However, these derangements are less severe than in the patient in A. There is no clear elevation of Lac. C, A patient with COVID-19 without encephalopathy or recent severe hypoxia has normal Cho/Cr, with mildly decreased NAA/Cr and no lactate elevation. Cho, Choline; NAA, N-Acetyl-Aspartate; mI, Myo-Inositol; Lac, Lactate; Glx, Glutamate + Glutamine. Image courtesy of AJNR

News | Coronavirus (COVID-19) | November 19, 2020
November 19, 2020 — One of the first spectroscopic imaging-based studies of neurological injury in...