Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K170451
    Date Cleared
    2017-03-16

    (29 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    FDX Console (DR-ID300CL) Software

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

    The FDX Console is a workstation intended to associate digital (CR and/or DR) images with patient and exam information, apply image processing to facilitate diagnosis, display the image, and output the resulting image and exam data for further display, distribution, or archiving. The FDX Console is not for use in Mammography.

    Device Description

    The FDX Console is used by a radiographer for viewing Digital Radiography (DR) and Computed Radiography (CR) images for final quality assurance (QA) checking and image processing and optimization prior to transferring the images to external devices such as a PACS or a printer. Furthermore, when connected to Fuji Image Readers via a network, the FDX Console is used to enter patient ID information, exposure information, and in the case of CR register Image Plate (IP) barcode numbers. The FDX Console is compatible with the ACR/NEMA DICOM Version 3.0 standard. The four primary features of the FDX Console are patient identification, exam selection, image processing, and image transmission.

    AI/ML Overview

    The provided text describes a 510(k) premarket notification for the FDX Console (DR-ID300CL) Software. The submission aims to demonstrate substantial equivalence to legally marketed predicate devices, not primarily to prove performance against specific acceptance criteria through clinical studies. Therefore, much of the requested information regarding acceptance criteria, specific device performance metrics, sample sizes for test sets, expert ground truth establishment, adjudication methods, MRMC studies, or standalone performance studies is explicitly stated as "not required" or not detailed in the document in the context of device performance evaluation.

    Here's an analysis based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The document does not present acceptance criteria in terms of specific performance metrics (e.g., sensitivity, specificity, accuracy) for diagnosis or detection by the FDX Console software. This is because the device is a medical image processing workstation, not a diagnostic AI algorithm that directly interprets images for disease. The "acceptance criteria" discussed are related to conformance to voluntary standards and demonstrability of substantial equivalence.

    Acceptance Criteria (Not in terms of performance metrics)Reported Device Performance and Compliance
    Conformance to DICOM, V3.0 2007Conforms
    Conformance to IEC 62304: 2006 (Medical Device Software – Software Life Cycle Processes)Conforms
    Conformance to IEC 62366: 2014 (Medical devices – Application of usability engineering to medical devices)Conforms
    All verification and validation activities performed as required by risk analysisResults were satisfactory
    Software modifications do not alter technological characteristics of predicatesDemonstrated (by comparison table)

    2. Sample Size for the Test Set and Data Provenance

    Not Applicable (N/A) for a medical image processing workstation. The submission indicates that "Clinical studies were not required as there is no change in image processing." The focus was on non-clinical performance data (software V&V and conformance to standards) to demonstrate substantial equivalence to existing devices. There is no mention of a "test set" of medical images for evaluating diagnostic performance.

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

    N/A. As no clinical studies or test sets for diagnostic performance were conducted, no experts were used to establish ground truth for such a purpose.

    4. Adjudication Method for the Test Set

    N/A. No test set for diagnostic performance was utilized.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

    No. The document explicitly states: "Clinical studies were not required as there is no change in image processing." Therefore, no MRMC study comparing human readers with and without AI assistance was performed or reported.

    6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

    No. The FDX Console is described as a workstation that "applies image processing to facilitate diagnosis, display the image, and output the resulting image and exam data," meaning it is an assistive tool within a human workflow, not a standalone diagnostic algorithm. No standalone performance study was conducted or reported.

    7. Type of Ground Truth Used

    N/A. Since no clinical studies were performed to evaluate diagnostic performance against a ground truth, this is not applicable. The device's function is image processing and management, not direct diagnostic interpretation.

    8. Sample Size for the Training Set

    N/A. The FDX Console is an image processing software with fixed algorithms. It is not an AI/ML device that requires "training data" in the typical sense of machine learning for diagnostic tasks. Its function is to apply established image processing techniques.

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

    N/A. As the device does not involve machine learning requiring a training set with established ground truth, this information is not applicable. The software's algorithms are based on predefined image processing techniques.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1