LogoFDA 510(k) Search
Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K131704
    Device Name
    EPIDOSE
    Manufacturer
    SUN NUCLEAR CORPORATION
    Date Cleared
    2013-08-05

    (55 days)

    Product Code
    IYE
    Regulation Number
    892.5050
    Type
    Traditional
    Panel
    Radiology (RA)
    Reference & Predicate Devices
    K935928
    Why did this record match?
    Device Name :

    EPIDOSE

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

    Model 1214 EPIDose is a radiotherapy beam QA software application intended for twodimensional (2D) electronic portal imaging device (EPID) image conversion to a phantom dose distribution for the purpose of comparison with a simulated dose distribution in the same phantom geometry as calculated by the treatment planning system (TPS).

    EPIDose is indicated for radiotherapy beam QA of radiotherapy treatment plans delivered on any treatment delivery device with an EPID that outputs DICOM-compliant images.

    Device Description

    Sun Nuclear EPIDose product, model 1214, is a software application that converts electronic portal imaging device (EPID) image data -acquired by a third party treatment delivery device (TDD)- to a dose distribution which can subsequently be compared with the planned dose distribution for radiation therapy quality assurance purposes. From this companson of the EPIDose result to the planned dose, a qualified clinician makes the decision whether the TDD along with its accessories (including the treatment planning system, or TPS) is capable of delivering the treatment as prescribed.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study details for the Sun Nuclear Corporation Model 1214 EPIDose, based on the provided 510(k) summary:

    1. Table of Acceptance Criteria and Reported Device Performance:

    Acceptance Criteria (Minimum Pass Rate using Gamma Analysis)Reported Device Performance (Achieved Pass Rates)
    68% (with 3.5% dose difference and 3.5 mm DTA)Above 94%

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

    • Sample Size: "various clinical and non-clinical cases" were used. A specific number is not provided.
    • Data Provenance: The data was generated through "measurements internally performed as well as through reference." The country of origin is not specified, but the submission is from Sun Nuclear Corporation in Melbourne, FL, USA.
    • Retrospective/Prospective: Not explicitly stated, but "internally performed measurements" suggest prospective testing specific to the device's development and validation.

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

    This information is not provided in the document. The comparison was primarily made against film results, implying that previous film dosimetry protocols served as the reference, rather than independent expert consensus per se for each case.

    4. Adjudication Method for the Test Set:

    This information is not applicable/provided in the context of this study. The performance was assessed by comparing EPIDose results directly against film results using gamma analysis, not through a human adjudication process to establish ground truth for each case.

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

    No, a MRMC comparative effectiveness study was not done. The study compares the device's output to film dosimetry, not improvements in human reader performance with and without AI assistance.

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

    Yes, this was a standalone performance study. The EPIDose software converts EPID images to a dose distribution, which is then compared to planned dose distributions. The study focuses on the accuracy of this conversion performed by the algorithm itself, independently of human interpretation during the comparison (though a "qualified clinician makes the decision" based on the comparison, this study validates the conversion part).

    7. The Type of Ground Truth Used:

    The ground truth used was film dosimetry (film results). The EPIDose results were compared to dose distributions derived from film, which is a widely accepted method for radiation therapy dosimetry.

    8. The Sample Size for the Training Set:

    The document does not provide information on the sample size used for the training set.

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

    The document does not provide information on how ground truth was established for a training set. Given that the device's "significant technological characteristic" is a "patented method for image to dose conversion," it's likely that fundamental physics principles and established dosimetry methods (potentially including film or other reference dosimeters) were used in its development and calibration, rather than a distinct "training set" with independently established ground truth in the machine learning sense. The performance study described seems to be a validation study against an existing reference standard (film).

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1