Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K223780
    Device Name
    Lumos 3DX
    Manufacturer
    Date Cleared
    2023-07-06

    (202 days)

    Product Code
    Regulation Number
    872.1800
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Lumos 3DX ™ System is an extraoral X-ray source (intraoral X-ray detection) dental X-ray system for producing diagnostic dental radiographs of the teeth, jav, and other oral structures. The system provides 3D imaging for diagnostic purposes via tomosynthesis. For use on adult patients only.

    Device Description

    The Lumos 3DX system is a 3D dental chairside X-ray system on a mobile stand that uses tomosynthesis (limited-angle tomography) to generate 3D images of the teeth and surrounding structures. A custom digital sensor is placed in the patient's mouth and multiple images are acquired around an arc of rotation and then fed into a 3D reconstruction algorithm. The digital sensor provided with the system is specifically for use with the Lumos 3DX device. The sensor has a higher frame rate that enables the Lumos 3DX system to capture 30 images in a short period of time. A server is provided as part of the Lumos 3DX system and wirelessly connects to one or more Lumos 3DX systems. After capturing images, the Lumos 3DX wirelessly transfers them to the server for reconstruction. This server can then be connected to the local network for access of the reconstructed data.

    AI/ML Overview

    The Lumos 3DX System is a dental X-ray system that provides 3D imaging for diagnostic purposes via tomosynthesis, for use on adult patients only. Its acceptance criteria and performance are as follows:

    1. Table of Acceptance Criteria and Reported Device Performance:

    Acceptance CriteriaReported Device Performance
    Image Quality PerformanceDemonstrated high spatial resolution, good contrast, and low noise using image quality phantoms. The 3D volume voxel size was also verified.
    Patient MotionEvaluation showed typical patient movements during imaging do not significantly affect the system or the resulting 3D volume. This justified the use of dental phantoms and cadaver subjects for clinical image quality analysis.
    System Verification & ValidationHazard mitigation performed, demonstrating the Lumos 3DX meets design input and user needs.
    Compliance to StandardsComplies with applicable IEC series of X-ray performance standards, including IEC60601-2-65. Meets all applicable 21CFR Subchapter J performance standards (radiation safety, dosimetry, leakage, stray radiation).
    Clinical Diagnostic QualityImages obtained from dental phantoms with human teeth and simulated bone, as well as cadaver subjects, were evaluated by dental professionals and found to be of diagnostic quality for clinical use.

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

    • Test Set Sample Size: "A number of 3D images" were obtained. Specific numerical sample sizes for the image quality phantoms, dental phantoms, and cadaver subjects are not provided in the document.
    • Data Provenance: The document does not explicitly state the country of origin. The test set primarily used dental phantoms with human teeth and simulated bone, as well as cadaver subjects for the clinical imaging evaluation. The study appears to be retrospective in the sense that existing phantoms and cadavers were used, but images were prospectively acquired using the Lumos 3DX system specifically for this evaluation.

    3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:

    • Number of Experts: Not specified. The document mentions "dental professionals" were used for the evaluation.
    • Qualifications of Experts: The document states "dental professionals" were involved. Specific qualifications (e.g., years of experience, specialization like radiologist) are not provided.

    4. Adjudication Method for the Test Set:

    • The document implies a consensus or evaluation by "dental professionals." However, a specific adjudication method (e.g., 2+1, 3+1) is not explicitly stated. The statement "Based on the evaluations made by the dental professionals, the images obtained with the Lumos 3DX were of diagnostic quality for clinical use" suggests a qualitative assessment.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:

    • No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not conducted or reported in the provided text. The study primarily focuses on the standalone performance of the device's image quality for diagnostic use.

    6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:

    • Yes, the clinical utility of the Lumos 3DX was demonstrated through a "Clinical Imaging Evaluation." This evaluation assessed the images generated by the Lumos 3DX system itself (the algorithm/system only) for diagnostic quality, which dental professionals then reviewed. While human reviewers assessed the output, the performance being tested was that of the device generating the images, not an AI aiding human diagnosis.

    7. The Type of Ground Truth Used:

    • Image Quality Phantoms: These phantoms inherently provide a known, objective ground truth for metrics like spatial resolution, contrast, and noise.
    • Dental Phantoms with Human Teeth and Simulated Bone, and Cadaver Subjects: For the clinical imaging evaluation, these served as the ground truth. The structures within these phantoms and cadavers represent actual anatomical conditions, and their diagnostic quality was assessed by dental professionals. This can be considered a form of "expert consensus" on the diagnostic utility relative to a known anatomical state.

    8. The Sample Size for the Training Set:

    • The document does not provide any information regarding a training set size. The context is a 510(k) summary for a medical device (an X-ray system), not an AI/ML algorithm submission that typically requires specific training set details. The "reconstruction algorithm" mentioned is likely a traditional image processing algorithm rather than a machine learning model requiring a distinct training phase.

    9. How the Ground Truth for the Training Set Was Established:

    • As no training set is mentioned for an AI/ML algorithm, this information is not applicable and not provided in the document.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1