Deep Learning Image Reconstruction
K193170GE Healthcare Japan Corporation · cleared 2019-12-13 · product code JAK · Radiology
Premarket evidence — what FDA accepted
source quote (p.3)
“The Deep Learning Image Reconstruction software is a deep learning based reconstruction method intended to produce cross-sectional images of the head and whole body by computer reconstruction of X-ray transmission data taken at different angles and planes, including Axial, Helical (Volumetric), and Cardiac acquisitions, for all ages.”
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 to give an image appearance, as shown on axial NPS plots, similar to traditional FBP images while maintaining the performance of ASiR-V in the following areas: image noise (pixel standard deviation), low contrast detectability, high-contrast spatial resolution, and streak artifact suppression.”
source quote (p.5)
“The fundamental technology, i.e the DLIR algorithm, remains unchanged from the predicate.”
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; Low Contrast Detectability (LCD) with statistical method; 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); Noise Power Spectrum (NPS) and Standard Deviation of noise; CT Number Accuracy and Uniformity; Contrast to Noise (CNR) ratio; Artifact analysis – metal objects, unintended motion, truncation; Pediatric Image Quality Performance; Low Dose Lung Cancer Screening
standards: 21CFR 820, ISO 13485
Reader study (MRMC)
n=60 cases
endpoints: assessment of image quality related to diagnostic use according to a 5-point Likert Scale; image noise texture preference; image sharpness preference; image noise texture homogeneity preference
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
- re_clearance
The FDA AI/ML device list shows a newer 510(k) K230807 (decision 2023-04-20) from GE Healthcare Japan Corporation 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:K230807
- re_clearance
The FDA AI/ML device list shows a newer 510(k) K220961 (decision 2022-07-29) from GE Healthcare Japan Corporation 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:K220961
- re_clearance
The FDA AI/ML device list shows a newer 510(k) K212067 (decision 2021-09-17) from GE Healthcare Japan Corporation 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:K212067
- 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 is another firm in the same product code.
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 is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:98588
- 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 6 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).