Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K152867
    Date Cleared
    2015-10-21

    (21 days)

    Product Code
    Regulation Number
    892.5050
    Reference & Predicate Devices
    Predicate For
    N/A
    Why did this record match?
    Reference Devices :

    K122450

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

    MHI-TM2000 Linear Accelerator System is intended for radiation therapy of lesions, tumors and conditions anywhere in the body where radiation treatment is indicated.

    Device Description

    The MHI-TM2000 Linear Accelerator System (hereinafter called "MHI-TM2000 (Ver. 3.5)") is an Image-Guided Radiation Therapy device generating 6MV high energy X-ray for precision radiation therapy of tumors and conditions, where radiation treatment is indicated.

    It includes a linear accelerator, multi-leaf collimator, electric portal imaging device and couch. It also includes O-ring-type gantry platform, X-ray-head-mounted gimbals, Built-in Imaging System, and function to continuously align treatment beam with moving target for precise radiotherapy of moving targets, as notable characteristics.

    The MHI-TM2000 (Ver. 3.5) has been developed based on MHI-TM2000 Linear Accelerator System previously cleared by FDA under K122450 (hereinafter called "MHI-TM2000 (K122450)'').

    Modification was made for introducing a method of radiation therapy called "Dynamic WaveArc" ("DWA") that delivers radiation while rotating both O-ring-shaped gantry (Gantry rotation) and rotational floor of the gantry that moves entire gantry (Ring rotation), or rotating the Ring rotation only.

    Radiation type, energy, and the method of generating radiation are identical between MHI-TM2000 (Ver. 3.5) and MHI-TM2000 (K122450)

    AI/ML Overview

    This document describes a 510(k) premarket notification for the MHI-TM2000 Linear Accelerator System, focusing on a modification (Ver. 3.5) that introduces a "Dynamic WaveArc" (DWA) radiation therapy method.

    Here's an analysis of the provided text regarding acceptance criteria and supporting studies:

    1. A table of acceptance criteria and the reported device performance:

      The document does not explicitly provide a table of acceptance criteria and reported device performance in the typical sense of quantitative metrics for a diagnostic or AI device. Instead, it states that the device's substantial equivalence is based on its conformance to:

      • Applicable requirements specifications.
      • Hazard safeguards functioning properly.
      • Customer needs and intended use.

      The modification (addition of "Dynamic WaveArc" radiation therapy method) is evaluated against the predicate device (MHI-TM2000 (K122450)). The device performance is implicitly stated as meeting the standards and ensuring safety and effectiveness, as indicated in the "Summary of Performance Testing" and "Conclusion" sections.

      The key performance characteristic discussed is the addition of the Dynamic WaveArc (DWA) radiation therapy method, which is present in MHI-TM2000 (Ver. 3.5) and not in the predicate device. All other technological characteristics, indications for use, operation principles, and methods of operation are stated to be identical.

    2. Sample sizes used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective):

      The document describes "verification testing" and "validation testing" but does not provide specific details on sample sizes for test sets (e.g., number of patients, treatment plans, or cases). It also does not specify the data provenance (country of origin, retrospective/prospective). The testing appears to be primarily focused on engineering verification and validation rather than clinical trial data involving patient outcomes.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience):

      The document does not mention the involvement of experts to establish ground truth for a test set. This is consistent with the nature of the device being a radiation therapy delivery system, where the focus is on the accurate and safe delivery of radiation as programmed, rather than diagnostic interpretation.

    4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

      No adjudication method is described, as the testing does not involve subjective interpretation or a need for consensus among experts for ground truth establishment.

    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:

      No MRMC comparative effectiveness study was conducted or described. This document pertains to a linear accelerator system, which is a treatment delivery device, not a diagnostic imaging or AI-assisted diagnostic device that would typically involve human readers interpreting AI outputs.

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

      The term "standalone" performance for an algorithm is not applicable here as the device is a physical radiation therapy system, not a standalone AI algorithm. The performance testing focuses on the system's ability to deliver radiation according to its design and specifications.

    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

      The concept of "ground truth" as typically applied to AI/diagnostic devices (e.g., pathology for cancer detection) is not explicitly mentioned or used in this document. The "ground truth" for a linear accelerator would relate to its physical performance metrics, such as radiation dose accuracy, beam shaping precision, gantry rotation accuracy, and the ability to deliver the planned treatment. These are evaluated through engineering tests, calibration, and quality assurance procedures against established physical and safety standards.

    8. The sample size for the training set:

      The document does not mention a training set sample size. This device is a hardware system with a new operational method, not a machine learning model that requires a training set.

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

      As there is no mention of a training set, the establishment of ground truth for such a set is not applicable.

    Summary of Study Described:

    The study proving the device meets its acceptance criteria is primarily an engineering verification and validation study based on design control procedures.

    • Design Control Procedures: Include requirements reviews, risk analysis, and verification and validation testing.
    • Standards Conformance: The device conforms to several international standards including:
      • ISO14971: Risk Management Standard
      • FDA Quality System regulation (21 CFR 820)
      • ISO13485: Quality Management System Standard
      • IEC 60601-1, IEC 60601-1-2, IEC 60601-2-28, IEC 60825-1, IEC 60976, IEC 62304
    • Verification Testing: Included regression testing, showing conformance to applicable requirements specifications and assuring hazard safeguards functioned properly.
    • Validation Testing: Showed conformance to customer needs and the intended use of the MHI-TM2000 (Ver. 3.5).
    • Bench Testing: The results are explicitly stated to be from "bench testing."
    • Substantial Equivalence: The conclusion is that the verification and validation (from bench testing) support the substantial equivalence of the MHI-TM2000 (Ver. 3.5) with its predicate device (MHI-TM2000 (K122450)), particularly noting that the modification (Dynamic WaveArc) does not significantly affect safety and effectiveness.

    In essence, the study is a technical compliance review and testing process to ensure the modified device (with the DWA feature) continues to meet safety and performance standards equivalent to its predicate, rather than a clinical study evaluating AI performance or diagnostic accuracy.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1