Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K083504
    Date Cleared
    2008-12-12

    (16 days)

    Product Code
    Regulation Number
    892.1200
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    GE DISCOVERY NM/CT 570C

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The intended use of the GE Discovery NM/CT 570c system is primarily to perform combined cardiac SPECT and CT diagnostic imaging applications, including CT-based SPECT attenuation correction and functional-anatomical mapping (registration and fusion).

    The GE Discovery NM/CT 570c system intended uses include performing nuclear cardiac imaging procedures for detection and imaging of racer uptake in the patient body for clinical diagnostic purposes as well as performing general Head & Body Computed Tomography (CT) applications

    Device Description

    The GE Discovery NM/CT 570c system is a back-to-back combination of the Ventri 1.1 SPECT scanner (K080124) and the LightSpeed 7.1 CT scanner (K061817), sharing a common LightSpeed 7.1 patient table. In addition to providing CT and SPECT standalone capabilities, it uses the CT images to correct for non-uniform attenuation of the SPECT images and to facilitate localization of the emission activity in the patient anatomy.

    AI/ML Overview

    The provided document describes the GE Discovery NM/CT 570c system, a combination of SPECT and CT imaging systems. However, the available text does not contain detailed acceptance criteria, specific study results in terms of numerical performance metrics, or information regarding sample sizes, data provenance, expert qualifications, or adjudication methods for studies typically associated with AI/algorithm performance claims.

    The submission is for a device system (hardware and associated software), not specifically an AI-driven diagnostic device as per modern understanding. Therefore, many of the requested categories like "multi-reader multi-case comparative effectiveness study" or "standalone algorithm performance" are not applicable in this context.

    Here's an attempt to fill in the table and provide information based only on the provided text, with many fields necessarily marked as "Not Applicable" or "Not Provided."


    1. Table of Acceptance Criteria and Reported Device Performance

    Acceptance Criteria CategoryAcceptance Criteria (Not Explicitly Stated as Numerical)Reported Device Performance (as described in the text)
    SPECT-CT Attenuation CorrectionExpected to improve uniformity and localization of SPECT images."Data acquired with uniform phantom shows that SPECT-CT attenuation-corrected images are more uniform than SPECT images without attenuation correction."
    Localization CapabilitiesExpected to facilitate localization of emission activity."The images also demonstrate the localization capabilities of the SPECT-CT."
    Safety and EffectivenessSubstantially equivalent to predicate devices (Ventri 1.1, LightSpeed 7.1, Infinia LightSpeed, Xeleris 2)."substantially equivalent in terms of safety and effectiveness to the legally marketed Ventri 1.1 (K080124), the legally marketed LightSpeed 7.1 (K061817), the legally marketed Infinia LightSpeed (K061817) and the legally marketed Xeleris 2 Processing and Review Workstation (K051673), based upon similar intended use and system performances."
    Intended UsePerform combined cardiac SPECT and CT diagnostic imaging, including CT-based SPECT attenuation correction and functional-anatomical mapping, and general Head & Body CT applications.The device's capabilities are described as fulfilling these intended uses.

    2. Sample size used for the test set and the data provenance

    • Sample Size: Not provided. The document mentions "Data acquired with uniform phantom," indicating a phantom study was conducted. No patient sample size for a test set is mentioned.
    • Data Provenance: The study was conducted with a "uniform phantom." No country of origin for data or retrospective/prospective nature is specified, although phantom studies are typically controlled laboratory experiments.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

    • Number of Experts: Not provided.
    • Qualifications of Experts: Not provided. The evaluation appears to be based on physical phantom data and direct measurement/observation of image characteristics (uniformity, localization) rather than expert interpretation of patient images for ground truth.

    4. Adjudication method for the test set

    • Adjudication Method: Not applicable/Not provided. The evaluation described involves a "uniform phantom" and is focused on the physical performance of the system (attenuation correction, localization) rather than a diagnostic performance study requiring expert adjudication of clinical cases.

    5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

    • MRMC Study: No, not applicable. This submission predates widespread AI in medical imaging devices and does not describe any human-in-the-loop diagnostic assistance features or related studies. The device is a scanner system, not an AI diagnostic tool.
    • Effect size: Not applicable.

    6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

    • Standalone Performance: Not applicable as per the modern definition of an "algorithm only" device. The "data acquired with uniform phantom" is essentially a technical validation of the system's performance (attenuation correction, localization) in a controlled setting, which could be considered a form of standalone performance for the system as a whole, but not an AI algorithm.

    7. The type of ground truth used

    • Ground Truth Type: For the phantom study, the "ground truth" implicitly refers to the known physical properties and uniformity of the phantom. For clinical applications, substantial equivalence relies on the established performance of the predicate devices. There is no mention of expert consensus, pathology, or outcomes data being used for the performance evaluation detailed in the summary.

    8. The sample size for the training set

    • Sample Size for Training Set: Not provided. This being a conventional imaging system rather than an AI/machine learning device, the concept of a "training set" for an algorithm, as typically defined, is not directly applicable.

    9. How the ground truth for the training set was established

    • Ground Truth for Training Set: Not applicable. As above, there is no mention of an AI algorithm training set. The device functions based on established physics and engineering principles for SPECT and CT imaging, with software for processing and fusion.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1