AIR Recon DL, a deep learning-based image reconstruction software, will now be available with 3D sequences as well as PROPELLER motion-insensitive sequences on magnetic resonance imaging (MRI) scanners from GE Healthcare.
The Food and Drug Administration (FDA) has expanded the 510(k) clearance for GE Healthcare’s AIR Recon DL, enabling radiologists to apply the adjunctive deep learning-based technology to 3D sequences as well as the company’s PROPELLER motion-insensitive sequences for magnetic resonance imaging (MRI).
Noting enhanced image sharpness and an improved signal-to-noise (SNR) ratio, GE Healthcare said the compatibility of AIR Recon DL with 3D MRI imaging reduces the need for repeat 2D scans and may facilitate quick imaging results.
For pediatric, neurodegenerative, geriatric, and claustrophobic patients who may have trouble staying still for MRI exams, GE Healthcare noted the combination of PROPELLER sequencing and AIR Recon DL should lead to shorter exam times, faster patient throughput and an enhanced patient experience.
“By expanding AIR Recon DL to 3D and PROPELLER, GE Healthcare has closed the gaps in our ability to provide improved image quality and patient experience to all our patients across exam types, particularly for brain imaging where we rely heavily on 3D sequences and musculoskeletal imaging where PROPELLER is important for reducing image quality variability and eliminating repeat sequences due to motion,” noted Tiron Pechet, MD, an assistant professor of radiology at the University of Massachusettes Medical School and an assistant medical director with Shields Health Care Group.
In addition to being available on the GE Healthcare’s new MRI scanners, the expanded applications of AIR Recon DL to 3D and PROPELLER sequences will be available as upgrades for previously installed 1.5T and 3.0T MRI systems from the company, according to GE Healthcare.
Considering Breast- and Lesion-Level Assessments with Mammography AI: What New Research Reveals
June 27th 2025While there was a decline of AUC for mammography AI software from breast-level assessments to lesion-level evaluation, the authors of a new study, involving 1,200 women, found that AI offered over a seven percent higher AUC for lesion-level interpretation in comparison to unassisted expert readers.
Can CT-Based Deep Learning Bolster Prognostic Assessments of Ground-Glass Nodules?
June 19th 2025Emerging research shows that a multiple time-series deep learning model assessment of CT images provides 20 percent higher sensitivity than a delta radiomic model and 56 percent higher sensitivity than a clinical model for prognostic evaluation of ground-glass nodules.
FDA Clears Ultrasound AI Detection for Pleural Effusion and Consolidation
June 18th 2025The 14th FDA-cleared AI software embedded in the Exo Iris ultrasound device reportedly enables automated detection of key pulmonary findings that may facilitate detection of pneumonia and tuberculosis in seconds.