Deep Learning Image Reconstruction for Gemstone Spectral Imaging

K201745

GE Medical Systems, LLC · cleared 2020-12-10 · product code JAK · Radiology

Premarket evidence — what FDA accepted

Device typehardware with ml

source quote (p.4)

“The Deep Learning Image Reconstruction for Gemstone Spectral Imaging option is a deep learning based CT reconstruction method intended to produce cross-sectional images by computer reconstruction of dual energy X-ray transmission data acquired with Gemstone Spectral Imaging, for all ages.”

Algorithmdedicated Convolution Neural Network (CNN)

source quote (p.6)

“DLIR-GSI is an image reconstruction method that uses a dedicated Convolution Neural Network (CNN) that has been designed and trained specifically to reconstruct CT GSI Images to give an image appearance similar to traditional FBP images while maintaining or improving the performance of ASiR-V.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (3)

Bench

sample size not stated

endpoints: Low contrast detectability (LCD); Image noise (pixel standard deviation); High contrast spatial resolution (MTF); Contrast to noise ratio (CNR); CT Number accuracy; CT Number uniformity; Material Decomposition accuracy; Iodine detection; Metal artifact reduction; Pediatric test with anthropomorphic phantom

standards: 21CFR 820, ISO 13485

Retrospective clinical

n=40 cases

endpoints: assessment of image quality related to diagnostic use according to a 5-point Likert scale; compare directly the ASiR-V and Deep Learning Image Reconstruction for Gemstone Spectral Imaging images according to the key metric of image noise texture

Retrospective clinical

n=7 cases

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

recalls in product code, 24mo

192

MAUDE reports in code, 12mo

-22%

vs code's own 3-yr baseline

drift signals on this device

recall_reason_pattern
Software/algorithm-related recall in product code JAK (GE Medical Systems, LLC, initiated 2026-03-26): "GE HealthCare has become aware of a potential security vulnerability impacting AW Server deployed via Edison Health Link (EHL) based CT Smart Subscription used in conjunction with " Recalling firm matches this device's applicant.
first seen 2026-07-08 · recall res_event_number:98738
recall_reason_pattern
Software/algorithm-related recall in product code JAK (PHILIPS MEDICAL SYSTEMS, initiated 2026-03-07): "Philips has identified three software issues: 1. During a continuous CT (CCT) scan, there is the potential that the Gantry could remain at the current scan position after pressing" Recalling firm matches this device's applicant.
first seen 2026-07-08 · recall res_event_number:98588
recall_reason_pattern
Software/algorithm-related recall in product code JAK (PHILIPS MEDICAL SYSTEMS, initiated 2025-09-25): "Issue 1: The potential for unintentional continued gantry/couch movement when a specific button series is used requiring use of manual stop. Issue 2. When performing a helical/Axia" Recalling firm matches this device's applicant.
first seen 2026-07-08 · recall res_event_number:97699
recall_reason_pattern
Software/algorithm-related recall in product code JAK (Philips Medical Systems Nederland B.V. Veenpluis, initiated 2025-02-28): "Multiple problems identified with the software version leading to various scanning and image issues, and unintended device movement." Recalling firm matches this device's applicant.
first seen 2026-07-08 · recall res_event_number:96423
re_clearance
The FDA AI/ML device list shows a newer 510(k) K213999 (decision 2022-02-18) from GE Medical Systems, LLC. for a matching device line ("Deep Learning Image Reconstruction") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K213999
recall_reason_pattern
Software/algorithm-related recall in product code JAK (Siemens Medical Solutions USA, Inc, initiated 2025-12-19): "To remove the software applications from certain CT systems as the applications have not received FDA 510(k) clearance." Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:98206
…and 4 more.

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).