Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K221568
    Date Cleared
    2022-09-12

    (104 days)

    Product Code
    Regulation Number
    892.1550
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Evolution XHD Series Ultrasound Diagnostic System is a high frequency general-purpose ultrasound system. It is intended for use by, or under the direction of a qualified and trained physician for ultrasound imaging, measurement, display and analysis of the human body and fluid. The device is intended for use in a hospital environment.

    The systems support the following clinical applications:

    The Evolution XHD Series Diagnostic Ultrasound System is applicable for adult and pediatric. It is intended for use in Pediatric, Small parts (breast, thyroid, testicles, prostate), Peripheral vessel, Dermatological, Musculoskeletal (conventional), Musculoskeletal (superficial).

    Modes of operation include: B Mode, Color Doppler, Power Doppler, Combined modes: B+Color Doppler, B+Power Doppler, B+PW Doppler.

    Device Description

    The Evolution XHD Series device is a high frequency general purpose, software controlled, diagnostic imaging system used to acquire and display high-resolution, real-time ultrasound data. The Evolution XHD Series device is comprised of transducers responsible for ultrasound signal generation, and a main unit that controls the transducers, processes the acoustic data, and processes and displays images.

    The main unit is a laptop ultrasound console with integrated keyboard, a color video LCD type display and operates from an integrated battery or separate power supply/charger.

    Evolution XHD Ultrasound Diagnostic System integrated 4 linear probe transducers: L22-8 K2, L28-12K2, L38-22K2, L62-38K2.

    AI/ML Overview

    1. Table of Acceptance Criteria and Reported Device Performance:

    The document does not explicitly present acceptance criteria in a tabular format with corresponding reported device performance for specific clinical metrics. Instead, the submission focuses on demonstrating substantial equivalence to a predicate device by comparing technical specifications, safety standards compliance, and qualitative attributes.

    Therefore, for this section, I can only extract the comparative information provided and highlight the general "compliance" or "equivalence" as the reported performance, as specific quantitative metrics for acceptance were not detailed in the provided text.

    Acceptance Criteria (Implied)Reported Device Performance
    Intended UseSubstantially Equivalent to predicate device.
    Indications for UseLess than Predicate Device: Does not support Abdominal, Neonatal Cephalic, Ophthalmic applications, but considered substantially equivalent in safety and effectiveness as no new risk is raised.
    UserQualified and trained physician (Same as predicate).
    EnvironmentHospital environment (Same as predicate).
    Transducer Types AvailableLinear Array (Same as predicate).
    Transducer Center Frequency15-50MHz (Predicate: 15-49MHz).
    Transducer Element256-element linear array detector (Same as predicate).
    Modes of OperationB Mode, Color Doppler, Power Doppler, PW Doppler. Less than Predicate Device: Does not support M-Mode, but considered substantially equivalent in safety and effectiveness as no new risk is raised.
    DICOM ComplianceDICOM 3.0 (Same as predicate).
    # Transmit Channels128 digital channels (Predicate: 64 digital channels). Performance Improvement: Better image quality due to more channels.
    # Receive Channels64 digital channels (Same as predicate).
    Patient Contact MaterialsMeet ISO 10993-1 and FDA guidance (Same as predicate).
    Acoustic OutputWithin FDA guidelines (Track 3) (Same as predicate).
    General Safety & EffectivenessComplies with ANSI/AAMI ES60601-1, IEC60601-2-37, IEC60601-1-2, ISO 10993-1 (Same as predicate).
    LabelingConforms to 21 CFR Part 801 (Same as predicate).
    Software FunctionsZoom, Dual Display, Annotation, Bodymark, Report, DICOM (Similar to predicate).
    MeasurementDistance, Area, Volume, Angle, Length trace, Curve (Similar to predicate).
    BiocompatibilityEvaluated and meets ISO10993 series standard and FDA guidance.
    Cleaning and Disinfection EffectivenessEvaluated and found to comply with applicable medical device safety standard.
    Thermal, Electrical, Electromagnetic, and Mechanical SafetyEvaluated and found to comply with applicable medical device safety standard.
    Risk ManagementApplied (Requirement review, Design reviews, Integration testing, Performance testing, Safety testing).

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

    The document states: "The subject of this premarket submission, did not require clinical studies to support substantial equivalence." This implies that there were no clinical test sets or study data used to demonstrate performance against acceptance criteria in the traditional sense of a clinical trial. The evaluation primarily relied on non-clinical tests and a comparison with the predicate device's established performance and safety standards.

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

    As no clinical studies were performed, there were no experts used to establish a ground truth for a test set. The device's safety and effectiveness were assessed through compliance with engineering standards and comparison to a legally marketed predicate device.

    4. Adjudication method for the test set:

    Since no human readers or expert panels were involved in a clinical test set, there was no adjudication method employed.

    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:

    The document does not mention any MRMC comparative effectiveness study, nor does it discuss AI assistance for human readers or any effect size related to such assistance. The device is described as an "Ultrasound Diagnostic System" for image acquisition, measurement, display, and analysis, without indicating any artificial intelligence components directly aiding human interpretation beyond general "Auto Optimize" software functions in some models.

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

    The document describes the device as an "Ultrasound Diagnostic System" that provides imaging, measurement, display, and analysis for a physician. It does not describe any standalone algorithm-only performance without human-in-the-loop. The system is intended to be used "by, or under the direction of a qualified and trained physician."

    7. The type of ground truth used:

    As no clinical studies were performed, there was no "ground truth" established from expert consensus, pathology, or outcomes data for the purpose of validating the device's diagnostic accuracy in a clinical context. The basis for the substantial equivalence determination relied on:

    • Compliance with recognized voluntary standards (e.g., AAMI/ANSI ES60601-1, IEC 60601-1-2, IEC 60601-2-37, ISO 10993-1).
    • Non-clinical testing for acoustic output, biocompatibility, cleaning and disinfection effectiveness, and thermal, electrical, electromagnetic, and mechanical safety.
    • Comparison of technical specifications and performance characteristics to a legally marketed predicate device (FUJIFILM SonoSite Vevo MD Imaging System, K190476).

    8. The sample size for the training set:

    The document describes a 510(k) submission for an "Ultrasound Diagnostic System," which is hardware- and software-based medical imaging equipment. It does not mention any machine learning or AI components that would require a "training set" in the context of diagnostic algorithm development. The "software functions" listed are typical for ultrasound systems (Zoom, Dual Display, Annotation, Bodymark, Report, DICOM), with "Auto Optimize" being a general image processing function. Therefore, a training set for an AI-driven diagnostic algorithm is not applicable or discussed here.

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

    As no training set for an AI-driven diagnostic algorithm is mentioned, the method for establishing its ground truth is not applicable or discussed in the provided document.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1