Deep Learning Image Reconstruction
K183202GE Medical Systems, LLC. · cleared 2019-04-12 · product code JAK · Radiology
Premarket evidence — what FDA accepted
source quote (p.5)
“Deep Learning Image Reconstruction is an image reconstruction method that uses a dedicated Deep Neural Network (DNN) that has been designed and trained specifically to generate CT Images”
source quote (p.5)
“Deep Learning Image Reconstruction is an image reconstruction method that uses a dedicated Deep Neural Network (DNN) that has been designed and trained specifically to generate CT Images”
source quote (p.5)
“The system allows user selection of three strengths of Deep Learning Image Recon: Low, Medium or High.”
Validation studies (2)
Bench
sample size not stated
endpoints: Low Contrast Detectability (LCD) using the head and body MITA/FDA low contrast phantoms and a model observer; Image Noise (pixel standard deviation) using both head and body uniform phantoms; High-Contrast Spatial Resolution (MTF) using a quality assurance phantom with a small diameter tungsten wire surrounded by water inside the phantom to generate the point spread function; Streak Artifact Suppression using an oval uniform polyethylene phantom with embedded high attenuation objects to produce the artifacts; Spatial Resolution, longitudinal (FWHM slice sensitivity profile); Low Contrast Detectability/resolution (statistical); Noise Power Spectrum (NPS) and Standard Deviation of noise; CT Number Uniformity; CT Number Accuracy; Contrast to Noise (CNR) ratio; Artifact analysis – metal objects, unintended motion, truncation
standards: ISO 13485
Reader study (MRMC)
n=60 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 images according to three key metrics of image quality preference - image noise texture, image sharpness, and image noise texture homogeneity
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
- 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
- re_clearance
The FDA AI/ML device list shows a newer 510(k) K201745 (decision 2020-12-10) from GE Medical Systems, LLC for a matching device line ("Deep Learning Image Reconstruction for Gemstone Spectral Imaging") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K201745
- …and 5 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).