Sonic DL

K243667

GE Medical Systems, LLC · cleared 2025-06-05 · product code LNH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“Sonic DL is a software feature intended for use with GE HealthCare MR systems.”

Algorithmdeep learning convolutional neural networks

source quote (p.6)

“The predicate device used deep learning convolutional neural networks to reconstruct MR images from highly under-sampled 2D cardiac cine acquisitions (also known as "Sonic DL Cine"). The proposed Sonic DL feature has been extended to include a new deep learning convolutional neural network for use with 3D Cartesian acquisitions (“Sonic DL 3D").”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (6)

Bench

sample size not stated

endpoints: Comparative image quality metrics (Peak-Signal-to-Noise (PSNR), Root-Mean-Square Error (RMSE), and Structural Similarity Index Measure (SSIM)), resolution, and low contrast detectability were measured at varied acceleration factors, contrasts, and noise levels.

Bench

sample size not stated

endpoints: quantify the low contrast detectability of Sonic DL 3D

Retrospective clinical

n=15 cases · 1 site(s)

endpoints: Volumetric measurements of key brain tissues; assess whether Sonic DL 3D images have similar quantitative analysis results

Reader study (MRMC)

n=120 cases · 7 site(s)

endpoints: evaluate the diagnostic quality of images; comment on the presence of any pathology in the images

Reader study (MRMC)

n=120 cases · 1 site(s)

endpoints: evaluated clinically relevant anatomic structures; received diagnostic scores in all anatomic structures

Retrospective clinical

sample size not stated

endpoints: retaining relevant anatomical details without structural losses or concerning artifacts.

Reported performance (0 observations)

FDA source did not state a quantitative performance metric — non-reporting is itself the signal.

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

100

recalls in product code, 24mo

510

MAUDE reports in code, 12mo

+5%

vs code's own 3-yr baseline

drift signals on this device

recall_reason_pattern
Software/algorithm-related recall in product code LNH (Philips North America, initiated 2026-04-14): "The potential for stiffness value errors when a specific range of image reconstruction parameters is used in combination with Resoundant's algorithm, leading to the reconstruction " Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:98779
recall_reason_pattern
Software/algorithm-related recall in product code LNH (Philips North America, initiated 2025-12-03): "The potential for stiffness value errors when viewing exported MR Elastography (MRE) stiffness maps to viewer Picture Archiving and Communication System (PACS)." Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:98111

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).