Clinical Evidence

SwiftMR® improves MR images across four dimensions: reduced noise, sharper resolution, accelerated scan time, and reduced artifacts. SwiftSight-Brain builds on those images to track MS lesions across follow-up exams. View before/after comparisons, case studies, and peer-reviewed studies from our clinical team.

Denoising

Improve SNR with well-preserved tissue contrast

Super-resolution

Sharper lesion and structural conspicuity

Acceleration

Shorter scan time, less motion artifact

Artifact reduction

Cleaner truncation and susceptibility artifacts

MS lesion tracking

New, enlarging, and stable lesions across exams

Improved SNR with well-preserved tissue contrast, revealing structures that noise obscures, without changing your scan protocol.

Deep learning improves quality of intracranial vessel wall MRI for better characterization of potentially culprit plaques

SwiftMR provided significant improvement in SNR and spatial resolution in vessel wall imaging, leading to detection of vessel wall lesions and intraplaque hemorrhage compared to conventional image.

Seo et al.. Scientific Reports. Aug 2024.

Improved lesion and structural conspicuity, enabling thin-slice imaging that would otherwise be limited by SNR constraints.

Improving diagnostic performance of MRI for temporal lobe epilepsy with deep learning-based image reconstruction in patients with suspected focal epilepsy

SwiftMR resulted in significantly improved resolution and structural conspicuity in hippocampal imaging compared to routine imaging. Hippocampal striation blurring was suspected on routine 3mm MRI, but became more obvious on 1.5mm MRI + SwiftMR.

Suh et al.. Korean Journal of Radiology. 2024;25(4):374-383.

Shorter scan time means less patient movement, minimizing chances of motion artifacts, directly improving image quality as a secondary benefit.

Deep learning-based reconstruction for acceleration of lumbar spine MRI: a prospective comparison with standard MRI

Prospective comparison showing 32.3% average acquisition time saving versus standard protocol, with no degradation in image quality or diagnostic performance.

Yoo et al.. Eur Radiol. 2023;33(12):8656-8668.

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

Prospective, multi-reader, multi-vendor study demonstrating average scan time reduction of 41% using SwiftMR, without degrading image quality or diagnostic performance across readers or scanner platforms.

Lee et al.. Sci Rep. 2023;13:17264. PMID: 37828048.

Artifact Reduction

Improve truncation and susceptibility artifacts, producing cleaner images from the same acquisition without reacquisition or protocol changes.

Susceptibility artifacts reduction

Geometric distortion improvement

Brain DWI b1000 · 2D EPI Diffusion · Same acquisition3.0T Siemens MAGNETOM Skyra

1:30 — Without SwiftMR · 1.5×1.9×3.0 mm

1:30 — With SwiftMR · 1.5×1.9×3.0 mm

Truncation artifact improvement

MS Lesion Tracking

MS follow-up depends on comparing each exam with the one before it, and those exams are often acquired on different scanners. A change in vendor, field strength, or protocol can alter noise and resolution, and automated measurements can shift even when the patient has not changed.

SwiftSight-Brain minimizes cross-scanner variation by normalizing image quality before it compares exams, then classifies each lesion as new, enlarging, or stable.

The examples below cover three kinds of scanner change between exams: scanner model, field strength, and vendor. In each, SwiftSight tracks the lesions consistently despite the change.

Cross-scanner variation in brain volumetry

Largest difference in hippocampal volume for one subject scanned on three scanners.

Tracking one patient over eight years

Retrospective case · Female patient, age 31–39Siemens MAGNETOM Skyra 3T and Vida 3T

Across eight years and a change of scanner, SwiftSight showed where the disease had progressed. The follow-up at age 39 had 32 lesions that were absent from the baseline at age 31, most of them in the deep white matter. Seven lesions that were already present, all periventricular, had grown, and their combined volume had more than tripled (+225.9%).

Across field strengths

Retrospective case · Female patient, age 38–39Siemens MAGNETOM Sola 1.5T and Vida 3T

This patient's annual follow-ups were acquired on two Siemens scanners of different field strengths. Most lesions remained stable, and the largest lesion, in the parietal lobe, grew slightly. SwiftSight classified that lesion as enlarging. The conventional solution classified it as stable.

Across vendors

Retrospective cases · Philips 3T baseline, Siemens 3T follow-up

Vendor differences in noise and resolution can degrade segmentation accuracy. In four more patients with a Philips baseline and a Siemens follow-up, 11 months to more than three years apart, SwiftSight lesion quantification held steady despite the change of vendor.

FemaleAge 42–43Feb 2019 – Nov 2020Coronal view

FemaleAge 24–27Jan 2020 – May 2023Axial view

MaleAge 26–27Jul 2020 – Jun 2021Sagittal view

MaleAge 47–48Feb 2020 – Jan 2021Axial view

Request a Clinical Review

Our clinical team can provide in-depth clinical and technical presentations on SwiftMR.

Select publications

In 86 patients scanned at 3T, accelerated T2-weighted liver imaging reconstructed with SwiftMR in a single breath-hold reached higher SNR and sharpness than the routine two-breath-hold protocol, and reduced spatial mismatch between slices.

This white paper details the reference population and statistical methodology behind SwiftSight Brain volumetric analysis, including a novel shifted-softplus normative model for age- and sex-adjusted assessment. The database draws on 3D T1-weighted MRI across major scanner vendors and field strengths to deliver stable, clinically interpretable percentile and z-score comparisons.

Across 173 patients, SwiftMR-reconstructed DCE series improved image noise, capsule sharpness, and lesion conspicuity for both readers, while PI-RADS diagnostic performance was preserved.

In this white paper, we compared SwiftMR-processed MR exams to the standard of care. We analyzed 184 MR exam pairs from 12 anatomical locations, considering various pathologies.

A two-institution prospective study of 70 patients found SwiftMR-enhanced accelerated lumbar spine MRI diagnostically interchangeable with conventional imaging at 80 to 86% shorter acquisition time, with higher SNR and CNR, and automated reporting agreeing closely with radiologist consensus.

This study explored the use of SwiftMR for detecting brain metastases. The findings showed significant improvements in both quantitative and qualitative metrics.

SwiftMR, an AI-powered MRI reconstruction software, offers clear economic benefits to imaging centers. In an economic model, we estimated that a typical imaging center using SwiftMR can see meaningful gains.

This study investigated the use of SwiftMR in 4D time-resolved contrast-enhanced MRA, showing measurable gains for ischemic stroke imaging.

“All-in-One Deep Learning Framework for MR Image Reconstruction” highlights a groundbreaking innovation in MRI technology that underpins SwiftMR.

Whitepaper by Geunu Jeong, MD, Head of SwiftMR Research at AIRS Medical. Introduces SwiftMR, a deep learning-based technology designed to enhance MRI quality across diverse applications.

Peer-reviewed review paper exploring existing literature on the diverse applications of deep learning reconstruction (DLR) techniques for fast MR neuroimaging.

This study explores the integration of SwiftMR in enhancing the diagnostic performance of MRI for temporal lobe epilepsy.

This study investigated the application of SwiftMR in enhancing the efficiency and quality of lumbar spine MRI scans.

AI applications can enhance imaging processes, reduce scan times, and improve image quality, increasing efficiency. Review of SwiftMR’s impact on revenue and operations.

This study evaluated the performance of SwiftMR in accelerating knee MRI without degrading image quality or diagnostic performance.

For a full list of publications, contact bd@airsmed.com.

Ready to see SwiftMR® at your institution?

Our clinical team can provide in-depth presentations on SwiftMR — including protocol-specific performance data for your scanner and field strength.