Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K213462
    Manufacturer
    Date Cleared
    2022-02-11

    (107 days)

    Product Code
    Regulation Number
    892.1720
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    EzRay M18 (Model: VMX-P400)

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

    EzRay M18 (Model: VMX-P400) is a portable X-ray system, intended for use by a qualified/trained physician or technician to acquire X-ray images of the desired parts of a patient's anatomy on adult and pediatric patients (including head, chest, abdomen, cervical spine, and extremities).

    The device may be used for handheld diagnostic imaging of body extremities.

    The system is subject to the following limitations of use when stand-mounted:

    • The device may be used for diagnostic imaging of the head, abdomen, cervical spine, or extremities.

    • The device may be used for imaging of the chest when used without a grid.

    This device is not intended for mammography.

    Device Description

    EzRay M18 (Model: VMX-P400), a medical portable X-ray system, operates on 57.6 Vdc supplied by a rechargeable Li-ion battery pack. The system is composed of an X-ray generating part including an X-ray tube, a device controller, a power controller, a user interface, a beam limiting part, and two optional components: remote controller and stand. The device software supports the EzRay M18 system, and the software is of Moderate level of concern. The device is designed for the human body using image receptors. The image detectors, a necessary component for a fully-functional x-ray system, are not part of this submission.

    AI/ML Overview

    The provided document is a 510(k) premarket notification for the EzRay M18 (Model: VMX-P400) mobile X-ray system. It establishes substantial equivalence by comparing the device to a predicate device (MinXray, Inc. TR90BH, K182207) and a reference device (OSKO, Inc. XR5, K150663).

    However, the document does not contain information about an AI/algorithm component. Instead, it focuses on the hardware and its compliance with established safety and performance standards for X-ray systems. Therefore, many of the requested details related to AI performance, ground truth establishment, expert adjudication, and MRMC studies are not applicable or cannot be extracted from this document.

    Here's the information that can be extracted, based on the non-clinical testing performed for this traditional 510(k) submission:

    Acceptance Criteria and Reported Device Performance (Non-AI Device)

    This device is an X-ray system, not an AI-powered diagnostic tool. The acceptance criteria for such a device primarily revolve around safety, electrical performance, and image quality characteristics, rather than diagnostic accuracy metrics like sensitivity or specificity for a specific condition.

    Acceptance Criteria CategoryReported Device Performance (as described in the document)
    Safety and Electrical Performance- Complies with IEC 60601-1:2005 (Medical electrical equipment - General requirements for basic safety and essential performance).
    • Complies with IEC 60601-1-2:2014 (Electromagnetic compatibility - Requirements and tests).
    • Complies with IEC 60601-2-28:2017 (Medical Electrical Equipment - Exposure conditions - Diagnostic X-ray equipment).
    • Complies with IEC 60601-2-54:2009, AMD1:2015, AMD2:2018 (X-ray equipment for radiography and radioscopy).
    • Complies with IEC 62133-2:2017 (Secondary cells and batteries containing alkaline or other non-acid electrolytes – Safety requirements for portable sealed secondary cells, and for batteries made from them, for use in portable applications).
    • Conforms to 21 CFR 1020 Subchapter J (Performance Standards for Ionizing Radiation Emitting Products), specifically 21 CFR 1020.30 (Diagnostic x-ray system) and 21 CFR 1020.31 (Radiographic Equipment). |
      | Image Quality Performance Parameters | - MTF (Modulation Transfer Function) results compared with reference device (XR5, K150663) and found equivalent.
    • Spatial Frequency results compared with reference device and found equivalent.
    • DQE (Detective Quantum Efficiency) results compared with reference device and found equivalent.
    • NPS (Noise Power Spectrum) results compared with reference device and found equivalent. |
      | Functional Equivalence | - Capable of setting higher mA (20 mA vs 15 mA max for predicate) under same maximum tube voltage (90kV), allowing capture of radiographic images for the same body parts as the predicate device.
    • User interface (soft touch push buttons) and collimator (continuously adjustable light beam type) are similar to the predicate.
    • Energy source (rechargeable Li-ion battery pack) is the same as the predicate. |
      | Intended Indications for Use Adherence | - Intended for use to acquire X-ray images of desired parts of a patient's anatomy on adult and pediatric patients (head, chest, abdomen, cervical spine, extremities).
    • May be used for handheld diagnostic imaging of body extremities.
    • Stand-mounted use limitations: diagnostic imaging of head, abdomen, cervical spine, or extremities; chest imaging without a grid.
    • Not intended for mammography. (All align with predicate and intended use). |

    Study Details (Relevant to this Traditional 510(k) X-ray System Submission)

    1. Sample Size used for the test set and data provenance:

      • For image performance testing, the document states: "Image performance testing was performed on the EzRay M18 in comparison with a reference device XR5 (K150663) using a FDA-cleared flat-panel detector, 1417WCC (K171418)."
      • The document does not specify the sample size (e.g., number of images, phantoms, or subjects) used for this image performance testing.
      • The data provenance (country of origin, retrospective/prospective) is not mentioned. These tests are typically bench tests using phantoms or controlled images, not patient data in the context of an X-ray machine clearance.
    2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

      • This is not applicable as the study described is a technical performance comparison of an X-ray machine's image characteristics (MTF, DQE, etc.) with a reference device, rather than a diagnostic accuracy study requiring expert human reads for ground truth. Ground truth for these technical measurements is derived from the physical properties of the test phantoms or from established engineering principles and measurements.
    3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

      • Not applicable. There's no human reader interpretation or adjudication described, as the study focuses on the physical image output quality metrics.
    4. 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:

      • Not applicable. This submission is for a mobile X-ray system hardware, not an AI diagnostic algorithm. Therefore, no MRMC study, AI assistance, or human reader improvement associated with AI is discussed or performed.
    5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

      • Not applicable. There is no AI algorithm being submitted. The device is purely an imaging acquisition system.
    6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

      • For the image performance testing, the "ground truth" for metrics like MTF, DQE, spatial frequency, and NPS would be derived from the physical and mathematical properties of the test phantoms or technical measurement standards used in a controlled laboratory setting. It is essentially comparing objective technical measurements against those of a known, legally marketed device.
    7. The sample size for the training set:

      • Not applicable. This device does not involve a "training set" as it is a hardware device, not a machine learning model.
    8. How the ground truth for the training set was established:

      • Not applicable. As above, there is no training set mentioned or implied for this device.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1