Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K131483
    Date Cleared
    2013-10-07

    (137 days)

    Product Code
    Regulation Number
    892.1680
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    PHILIPS PIXIUM 4343RC

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

    As a part of a radiographic system, the Pixium 4343RC is intended to acquire digital radiographic images. The Pixium 4343RC is suitable for all routine radiography exams, including specialist areas like intensive care, trauma, or pediatric work, excluding fluoroscopy, angiography and mammography.

    Device Description

    The Pixium 4343RC is a Solid State X-ray Imaging Device that converts x-ray patterns into electrical signals are converted into visible images for use in medical diagnosis. In the device, a cesium iodide scintillator absorbs the input x-ray photons. The scintillator in turn emits visible spectrum photons that illuminate an array of photodetectors that create an electrical charge representation of the x-ray input. A matrix scan of the array converts the integrated charges into a modulated electrical signal.

    The detector is permanently installed and intended to be integrated into an x-ray system, where it constitutes an x-ray receptor for direct x-ray imaging. It is electrically powered and connected with the x-ray system. The device is connected to the Philips XD-S Eleva Radiography Workstation to create a complete x-ray imaging chain, and it is intended to be used exclusively in the Philips Digital Diagnost x-ray system, one of the predicate devices.

    AI/ML Overview

    Here's an analysis of the acceptance criteria and study information for the Philips Pixium 4343RC, based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The submission for the Philips Pixium 4343RC primarily focuses on demonstrating substantial equivalence to predicate devices through technical characteristic comparisons and a clinical concurrence study. It does not explicitly list "acceptance criteria" in a quantitative performance metric sense (e.g., target accuracy, sensitivity/specificity thresholds for diagnostic tasks). Instead, the acceptance criteria are implicitly that the new device performs at least as well as, or is equivalent to, the predicate devices across various technical and clinical aspects.

    The table below summarizes the key technical characteristics and performances compared between the new device and its predicates, which serve as the implicit "acceptance criteria" for demonstrating equivalence.

    Acceptance Criteria (Predicate Device Performance)Reported Device Performance (Philips Pixium 4343RC)Discussion/Outcome (as per document)
    Indications for Use:
    Acquire digital radiographic images for routine radiography, including specialist areas (intensive care, trauma, pediatric work), excluding fluoroscopy, angiography, and mammography. (Aligned with FD-W17)Acquire digital radiographic images for routine radiography, including specialist areas (intensive care, trauma, pediatric work), excluding fluoroscopy, angiography, and mammography.Identical / Equivalent
    X-Ray Absorber: CsI Scintillator (Both Predicates)CsI ScintillatorIdentical
    Installation type: Stationary, permanently installed (Pixium 4600)Stationary, permanently installedIdentical
    Readout Mechanism: Switching Diode (Pixium 4600) / Thin Film Transistor (FD-W17)Thin Film TransistorEquivalent
    MTF (Modulation Transfer Function):
    1 lp/mm: 62% (Pixium 4600), 60% (FD-W17)1 lp/mm: 64%Equivalent
    2 lp/mm: 33% (Pixium 4600), 30% (FD-W17)2 lp/mm: 32%Equivalent
    3 lp/mm: 17% (Pixium 4600), 15% (FD-W17)3 lp/mm: 17%Equivalent
    3.4 lp/mm: 13% (Both Predicates)3.4 lp/mm: 13%Equivalent
    3.5 lp/mm (Nyquist): 12% (Both Predicates)3.5 lp/mm (Nyquist): 12%Equivalent
    DQE (Detective Quantum Efficiency) at 1 μGy:
    1 lp/mm: 50% (Pixium 4600), 51% (FD-W17 at 2.5 µGy)1 lp/mm: 51% (at 1 µGy)Equivalent
    2 lp/mm: 40% (Pixium 4600), 39% (FD-W17 at 2.5 µGy)2 lp/mm: 42% (at 1 µGy)Equivalent
    3 lp/mm: 23% (Pixium 4600), 22% (FD-W17 at 2.5 µGy)3 lp/mm: 25% (at 1 µGy)Equivalent
    3.4 lp/mm: 17% (Pixium 4600), 15% (FD-W17 at 2.5 µGy)3.4 lp/mm: 18% (at 1 µGy)Equivalent
    3.5 lp/mm (Nyquist): 15% (Pixium 4600), 13% (FD-W17 at 2.5 µGy)3.5 lp/mm: Not explicitly stated, but implies high similarity to 3.4 lp/mm.Equivalent
    Image Processing: Philips Thoravision (Pixium 4600) / XD-S Eleva Workstation (FD-W17)XD-S Eleva WorkstationIdentical

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

    The document mentions a "concurrence study" was conducted but does not specify the sample size (number of images or cases) used for the test set.

    The data provenance is not explicitly stated as country of origin, nor is it explicitly labeled as retrospective or prospective. Given it's a "concurrence study" for regulatory submission, it is typically a controlled study, which could be either.

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

    The document does not specify the number of experts used or their qualifications for establishing ground truth in the concurrence study. It only states that the study confirmed the device "provides images of equivalent diagnostic capability to the predicate radiographic system." This implies expert assessment, but details are missing.

    4. Adjudication Method for the Test Set

    The document does not specify the adjudication method used in the concurrence study.

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

    The document does not mention or describe an MRMC comparative effectiveness study evaluating how much human readers improve with AI vs. without AI assistance. The study described is a "concurrence study" focused on the diagnostic capability of the new device's images being equivalent to a predicate, not on human-AI collaboration.

    6. Standalone (Algorithm Only) Performance Study

    The device itself is a Solid State X-ray Imaging Device (a digital detector), not an AI algorithm. Therefore, the concept of "standalone (algorithm only)" performance study, often associated with AI software, is not applicable in this context. The entire device, including its hardware and integrated image processing software (XD-S Eleva Workstation), is being evaluated as a system that produces diagnostic images.

    7. Type of Ground Truth Used

    The document implies that the ground truth for the concurrence study was based on the diagnostic capability of images from the predicate device. The study's goal was to show that the new device "provides images of equivalent diagnostic capability to the predicate radiographic system." This means the predicate device's images (presumably deemed diagnostically acceptable by current clinical practice) served as the reference for equivalence. It does not explicitly mention pathology or outcomes data as direct ground truth for the study itself, but rather clinical equivalence.

    8. Sample Size for the Training Set

    The document does not mention a training set sample size. This is understandable as the Pixium 4343RC is a hardware device (X-ray imager) with associated image processing software. While the image processing software itself might have been "trained" or optimized during its development, this submission focuses on the performance of the integrated hardware and software system, comparing it to predicate devices, not detailing the training of specific algorithms within the image processor.

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

    Since no training set and associated ground truth are explicitly mentioned for this device's submission, this information is not provided in the document.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1