SwiftMR

AIRS Medical
SwiftMR aims to accelerate MRI scans by up to 50% by enhancing low-quality initial outputs from accelerated scans. The deep-learning model improves SNR and resolution of MRI inputs, irrespective of body part or vendor type.
Operating in DICOM format, SwiftMR receives assigned scans from connected MRIs and dispatches results to PACS. Installable via cloud or on-premise.
*Product coverage and supported types may vary by region depending on regulatory status.
Information source: Vendor
Last updated: Jan. 31, 2024

General Information

General
Product name SwiftMR
Company AIRS Medical
Subspeciality Neuro, Cardiac, MSK, Chest, Abdomen, Breast
Modality MR
Disease targeted Not applicable
Key-features MRI scan acceleration, MRI image enhancement
Suggested use

Technical Specifications

Data characteristics
Population All population
Input 2D, 3D, T1WI, T2WI, PDWI, FLAIR, T2*WI, contrast, MR Angiography, MR Arthrography, MR Myelography
Input format DICOM
Output Enhanced MR images
Output format DICOM
Technology
Integration Stand-alone third party application
Deployment Locally on dedicated hardware, Cloud-based, Hybrid solution
Trigger for analysis Automatically, right after the image acquisition
Processing time 1 - 10 minutes

Regulatory

Certification
CE
Certified, Class IIa , MDR
FDA 510(k) cleared , Class II
Intended Use Statements
Intended use (according to CE) SwiftMR is a stand-alone software solution intended to be used for acceptance, enhancement and transfer of brain, spine, knee, ankle, shoulder, and hip MR images in DICOM format. It can be used for noise reduction and increasing image sharpness for MR images. SwiftMR is not intended for use on mobile devices.

Market

Market presence
On market since 01-2022
Distribution channels
Countries present (clinical, non-research use) 15
Paying clinical customers (institutes) 175
Research/test users (institutes) 83
Pricing
Pricing model Pay-per-use, Subscription, One-time license fee
Based on Number of installations, Number of analyses

Evidence

Evidence
Peer reviewed papers on performance

  • Deep learning–based reconstruction for acceleration of lumbar spine MRI: a prospective comparison with standard MRI (read)

  • Highly accelerated knee magnetic resonance imaging using deep neural network (DNN)–based reconstruction: prospective, multi-reader, multi-vendor study (read)

Non-peer reviewed papers on performance
Other relevant papers