Search Filters

Search Results

Found 2 results

510(k) Data Aggregation

    K Number
    K232489
    Device Name
    VenusX
    Manufacturer
    Date Cleared
    2024-04-12

    (239 days)

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

    K042720

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

    The VenusX radiotherapy delivery system is intended to provide precision radiotherapy for lesions, tumors, and conditions anywhere in the body where radiation treatment is indicated.

    Device Description

    The VenusX Radiotherapy System is a medical linear accelerator that delivers therapeutic radiation to patient in accordance with the physician's prescription. It supports CRT /IMRT Treatment Techniques (Mode). The system consists of a photon therapeutic 6 MV X-ray radiation beam producing component with a photon diagnostic kV X-ray radiation beam producing component that is installed in a radiation-shielded vault and a control console area located outside the treatment room.

    AI/ML Overview

    The provided text describes a medical device called VenusX, a radiotherapy delivery system, and its submission for FDA clearance. However, it does not include detailed information about specific acceptance criteria related to its performance in terms of accuracy or clinical effectiveness as one would expect for a diagnostic AI device or a device with a direct measurable output related to patient diagnosis/treatment efficacy (e.g., sensitivity, specificity, accuracy).

    Instead, the document focuses on demonstrating substantial equivalence to predicate devices (Varian UNIQUE and Varian On Board Imaging) by comparing technological characteristics and ensuring adherence to various safety, electrical, software, and biocompatibility standards.

    Therefore, many of the requested points cannot be answered based on the provided text. I will answer the points that can be addressed from the document and explicitly state when information is not available.

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

    The document primarily discusses compliance with various standards and safety requirements rather than performance metrics like sensitivity, specificity, or quantifiable clinical outcomes. Therefore, a table listing "acceptance criteria" and "reported device performance" in the typical sense for a clinical study is not possible from this text.

    The "acceptance criteria" mentioned are related to:

    • Electrical Safety and EMC: Compliance with IEC 60601-1-2:2014+AMD1:2020. Reported performance: "The system complies with the following standards."
    • Bench Testing: Conformance to various IEC and ANSI AAMI standards (e.g., ANSI AAMIES/IEC60601-1, IEC 60601-1-3, IEC 60601-2-1, IEC 60601-2-68, IEC 62274, IEC 62366-1, IEC 60601-1-6, IEC 60976, IEC 61217). Reported performance: "Test results met all the pre-determined acceptance criteria."
    • Cybersecurity: Compliance with security requirement testing, threat mitigation testing, closed box vulnerability scanning, and penetration testing, with reference to IEC 62443-4-1 Section 9.4. Reported performance: "The results of the cybersecurity testing showed that VenusX meets the cybersecurity requirements under Section524B(b) of FD&C Act."
    • Hardware and Software V&V: Conformance to 21 CFR §820, ISO 13485, ISO 14971, and FDA guidance "Content of Premarket Submissions for Device Software Functions." Reported performance: "Test results showed conformance to applicable requirements specifications and assured hazard safeguards functioned properly." Also, "there were no software DRs (Discrepancy Reports) remaining which had a priority of Safety Intolerable or Customer Intolerable." The software is considered "enhanced" level of concern.
    • Biocompatibility: Compliance with ISO 10993-1, ISO 10993-5, ISO 10993-10 for the Carbon fiber couch top. Reported performance: "Test results met all the pre-determined acceptance criteria."

    The document states that the VenusX device "provides precision radiotherapy" and its "Cone Beam CT Imager device (CBCT) is used for verification of correct patient position in relation to isocenter and verification of the treatment fields in relation to anatomical and/or fiducial landmarks." It does not provide quantitative performance metrics for these functions.

    A comparison of technological characteristics between the VenusX and predicate/reference devices is provided (pages 5-8), indicating that the VenusX has similar intended use, indications for use, and core functionalities (e.g., photon energy, maximum treatment field size, patient support, microwave source, interface for external system gating, image registration, data interface, record treatment delivery results, treatment techniques). Some differences are noted, such as FFF mode dose rates, SAD, number of MLC leaves (101 leaves in two orthogonal layers vs. 120), maximum leaf over travel, average leaf transmission (≤ 0.05% for VenusX vs. ≤ 2.0% for predicate), MV Detector size (larger for VenusX: 43cm x 43cm vs. 30cm x 40cm), and MV Pixel (higher resolution for VenusX: 2816x2816 vs. 1024x768). For CBCT, the VenusX also uses the FDK algorithm, with a dose per acquisition ≤ 2cGy (vs. ≤ 1.4cGy for reference device) and a 512x512 reconstruction matrix / 360° acquisition mode.

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

    This information is not provided in the document. The testing described is primarily non-clinical (bench testing, electrical safety, cybersecurity, hardware/software V&V, biocompatibility). There is no mention of a clinical "test set" in the context of patient data, nor its provenance or design.

    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)

    This information is not provided in the document. Since no clinical "test set" with patient data requiring ground truth by experts is described, this point is not applicable.

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

    This information is not provided in the document. Since no clinical "test set" requiring adjudication is described, this point is not applicable.

    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

    This information is not provided in the document. The VenusX is a radiotherapy delivery system, not a diagnostic AI system designed to assist human readers in interpreting images or data. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant to the described device.

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

    The document refers to the device's technical performance against engineering and safety standards. It does not describe an "algorithm only" standalone performance in the sense of a diagnostic or analytical algorithm reporting a clinical outcome. The device itself (a linear accelerator) performs the function of radiation delivery, and its imaging components (MV, CBCT) are for positional verification.

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

    For the non-clinical testing, the "ground truth" implicitly refers to the specified technical requirements, standards, and design specifications. For example, in electrical safety, the ground truth is adherence to the IEC 60601-1-2 standard. For hardware/software V&V, it's conformance to requirements specifications and hazard safeguards. There is no mention of ground truth established from clinical data like pathology or outcomes data.

    8. The sample size for the training set

    This information is not provided in the document. The document describes a medical linear accelerator system, not an AI model that requires a "training set" of data in the typical sense. The software and hardware development involves verification and validation, but not a data-driven training process in the way a machine learning model would.

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

    This information is not provided in the document. As noted in point 8, there is no mention of a "training set" for an AI model.

    Ask a Question

    Ask a specific question about this device

    K Number
    K120789
    Manufacturer
    Date Cleared
    2012-08-14

    (152 days)

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

    K042720

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

    ExacTrac is intended to be used to place patients at an accurately defined point within the treatment beam of a medical accelerator for stereotactic radiosurgery or radiotherapy procedures, in order to treat lesions, tumors and conditions anywhere in the body when radiation treatment is indicated. ExacTrac may also be used to monitor the patient position during the treatment.

    Device Description

    ExacTrac is a patient positioning and monitoring system providing the following main features: Patient positioning based on comparison between ExacTrac acquired X-ray images and calculated DRR (Digital Reconstructed Radiographs) using data provided by a treatment planning system. Patient positioning based on comparison between a CBCT scan, acquired by a 30 Imaging Device and imported into ExacTrac, and CT data provided by a treatment planning system. Both modalities can be based on: anatomical landmarks or implanted markers. Patient monitoring during treatment.

    AI/ML Overview

    The provided text doesn't explicitly state quantitative acceptance criteria or a specific study that proves the device meets them with performance metrics. It rather discusses the general clinical evaluation methods used to support the substantial equivalence decision for the ExacTrac system. However, I can extract and organize the available information relevant to your request.

    Here's a breakdown based on the provided text:

    Acceptance Criteria and Device Performance

    The document does not provide a table of precise quantitative acceptance criteria (e.g., specific accuracy thresholds) or corresponding reported device performance values. The clinical evaluation focuses on supporting "substantial equivalence."

    Study Information

    The document describes the methods used for clinical evaluation rather than a single, detailed study with specific results.

    1. Table of Acceptance Criteria and Reported Device Performance: This information is not provided in the given text. The document focuses on general methods of clinical evaluation rather than specific numerical acceptance criteria and performance outcomes.

    2. Sample Size Used for the Test Set and Data Provenance:

      • Test Set (Implicit):
        • For X-ray images: "Analysis of existing x-ray image datasets acquired with ExacTrac 5.5 during routine clinical use." No specific sample size is given.
        • For CBCT datasets: "Analysis of existing CBCT datasets during routine clinical use for retrospective clinical study." No specific sample size is given.
      • Data Provenance: The data comes from "routine clinical use," implying it is retrospective and likely from various clinical sites using ExacTrac 5.5. The country of origin is not specified but given the manufacturer (Brainlab AG, Germany), it's plausible the data could be international, including European and potentially US data.
    3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications: This information is not provided in the text. The document does not detail how ground truth was established for the "existing x-ray image datasets" or "existing CBCT datasets."

    4. Adjudication Method for the Test Set: This information is not provided in the text.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: There is no indication of an MRMC comparative effectiveness study being performed to assess the effect size of human readers improving with AI vs. without AI assistance. The ExacTrac device is a patient positioning and monitoring system, not primarily an AI-driven diagnostic or interpretation tool that directly assists human readers in making diagnoses.

    6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Performance Study: The document describes "Patient positioning based on comparison between ExacTrac acquired X-ray images and calculated DRR" and "Patient positioning based on comparison between a CBCT scan... and CT data." This implies the system (algorithm) performs an alignment task. While these are standalone functions of the algorithm, the text does not quantify or provide the results of a specific standalone performance study in terms of accuracy metrics. The clinical evaluation mentions "Simulated treatment of anthropomorphic human-bone phantoms," which would involve standalone system performance, but again, no quantitative results are given.

    7. Type of Ground Truth Used:

      • For the "Simulated treatment of anthropomorphic human-bone phantoms": The phantom's known anatomical landmarks or implanted markers would serve as a form of ground truth, established by the phantom's design and potentially precise measurements.
      • For the "Analysis of existing x-ray image datasets" and "existing CBCT datasets": The text doesn't explicitly state the ground truth establishment method. It's likely that ground truth for alignment tasks would be based on:
        • Comparison to calculated DRRs or CT data: The "Indication for use" and "Device description" mention comparing acquired images to DRRs/CT data from a treatment planning system. The treatment planning system's calculated (expected) positions might serve as the reference.
        • Anatomical landmarks or implanted markers: The device description explicitly states both modalities can be based on these, which would inherently provide a ground truth for positioning.
    8. Sample Size for the Training Set: This information is not provided in the text. As ExacTrac is a patient positioning system leveraging image comparison and potentially markers, it's not described as a deep learning or AI system that requires a distinct "training set" in the modern sense. It uses existing image data (DRRs, CTs) and acquired images for comparison.

    9. How the Ground Truth for the Training Set Was Established: This information is not applicable in the context of the provided text, as a specific "training set" for an AI model is not mentioned. The device's operation is based on comparing acquired patient images to reference images (DRRs, CTs) from a treatment planning system, where the ground truth is implicitly defined by the initial treatment plan or the known positions of markers/anatomy in those reference images.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1