Cartesion Prime (PCD-1000A/3) V10.21

K251370

Canon Medical Systems Corporation · cleared 2025-12-01 · product code KPS · Radiology

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.4)
“The device is a diagnostic imaging system that combines Positron Emission Tomography (PET) and X-ray Computed Tomography (CT) systems. AICE-i for PET is intended to improve image quality and reduce image noise for FDG whole body data by employing deep learning artificial neural network methods which can explore the statistical properties of the signal and noise of PET data. The AiCE algorithm can be applied to improve image quality and denoising of PET images.”
Algorithmdeep learning artificial neural network method (for AiCE-i for PET) and neural network (for Deviceless PET Respiratory gating system)
source quote (p.8)
“This feature employs a deep learning artificial neural network method to improve image quality and denoise PET images. This algorithm was developed to explore the statistical properties of signal and noise of input PET images and was trained to automatically adapt to different noise levels to produce consistently high-quality images. This feature employs an algorithm which uses a neural network to extract motion information from acquired PET data and to generate a corresponding gating signal which can be used to reduce the effects of respiratory motion, thereby improving the image quality of reconstructed PET images.”
Adaptive (vs locked)No
source quote (p.8)
“This algorithm was developed to explore the statistical properties of signal and noise of input PET images and was trained to automatically adapt to different noise levels to produce consistently high-quality images. This neural network was trained on FDG studies of 27 cancer patients (BMI: 19.82-45.35, 3 instances unknown) acquired entirely from the U.S. and selected to be representative of both sexes as well as a wide range of scan characteristics.”
PCCPNo
Cybersecurity addressedYes
source quote (p.10)
“Cybersecurity documentation, per the FDA guidance document "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions”, issued on September 27, 2023, was included in this submission.”

Validation studies (9)

Retrospective clinical

n=16 patients

Bench

sample size not stated

endpoints: Contrast Recovery Coefficient (CRC); Background Variability (BGV); Contrast to Noise Ratio (CNR); absence of artifacts; quantitativity (SUVmean)

Bench

sample size not stated

endpoints: accuracy of SUV (max and mean); tumor volume

Bench

sample size not stated

endpoints: SUVmean; background variability (BGV); contrast recovery coefficient (CRC); signal to noise ratio (SNR (with Std error)); artifacts

standards: NEMA NU-2, Section 7

Reader study (MRMC)

n=10 cases

endpoints: diagnostic quality; overall image quality; image sharpness; image noise

Retrospective clinical

n=27 patients

Bench

sample size not stated

endpoints: accuracy of SUV (max and mean); tumor volume

Retrospective clinical

n=11 patients

endpoints: quantified outputs on high uptake regions (e.g., lesions) of the reconstructed datasets

Reader study (MRMC)

n=10 patients

endpoints: diagnostic quality; performance as device-based gated images; motion correction

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

34
recalls in product code, 24mo
8
MAUDE reports in code, 12mo
-72%
vs code's own 3-yr baseline
4
drift signals on this device
  • recall_reason_pattern

    Software/algorithm-related recall in product code KPS (GE MEDICAL SYSTEMS ISRAEL, FUNCTIONAL IMAGING 9, Andrey Sakharov Haifa Israel, initiated 2025-12-24): "There is a potential intermittent issue on certain Omni Legend systems that can result in a streaking artifact in the PET clinical scan images. This streaking artifact is most eas" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:98269

  • recall_reason_pattern

    Software/algorithm-related recall in product code KPS (GE MEDICAL SYSTEMS ISRAEL, FUNCTIONAL IMAGING 4, Hayozma St Tirat Carmel Israel, initiated 2025-06-20): "Unintended radial detector motion may occur during patient setup or during patient scan if system does not have correct version of gantry software installed. Unintended detector mo" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97193

  • recall_reason_pattern

    Software/algorithm-related recall in product code KPS (Hermes Medical Solutions AB Strandbergsgatan 16 Stockholm Sweden, initiated 2024-10-31): "Due a potential software/configuration issue that may result is incorrect alignment during reconstructing a SPECT/CT study." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:95673

  • recall_reason_pattern

    Software/algorithm-related recall in product code KPS (Canon Medical System, USA, INC., initiated 2024-09-17): "When PET-CT system is executing reconstruction, if PET acquisition for another patient is performed (or PET reconstruction for another patient is performed from raw data processing" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:95471

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. 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).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K251370