Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K090469
    Date Cleared
    2009-05-22

    (88 days)

    Product Code
    Regulation Number
    892.2040
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    CARESTREAM DRYVIEW 5850 LASER IMAGER

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

    The CARESTREAM DRYVIEW 5850 Laser Imager is intended to provide highresolution hard copy images from digital imaging source output signals. The device is intended for use with KODAK DRYVIEW media including DVM (DryView mammography) films. The imager with a variety of digital modalities, including, but not limited to, CR (Computed Radiology), DR (Digital Radiology), CT (Computerized Tomography), MRI (Magnetic Resonance Imaging) and FFDM (Full Field Digital mammography). Image resizing is used to preserve true geometric size images. The images are to be used for medical diagnosis and referral to physicians and their patients.

    Device Description

    The CARESTREAM DRYVIEW 5850 Laser Imager is intended to provide highresolution hard copy images from digital imaging source output signals. The device is intended for use with KODAK DRYVIEW media including DVM (DryView mammography) films. The imager will interface with a variety of digital modalities, including, but not limited to, CR (Computed Radiology), DR (Digital Radiology), CT (Computerized Tomography), MRI (Magnetic Resonance Imaging) and FFDM (Full Field Digital mammography). Image resizing is used to preserve true geometric size images. The images are to be used for medical diagnosis and referral to physicians and their patients.

    The subject device and predicate devices use the same technical design base. The printers receive image data from the modality. User control is performed directly by the modality or through the host control. KODAK DRYVIEW imaging media is removed from a daylight cartridge and transported to the laser imaging station. Image data and media merge at the laser station and the film is scanned. The exposed media is transported through the integrated processor and exits the printer.

    Software is used to control the image management and machine functions. AIQC (Automated Image Quality Control) matches printing power with film characteristics to provide consistently high image quality.

    AI/ML Overview

    The CARESTREAM DRYVIEW 5850 Laser Imager is intended to provide high-resolution hard copy images from digital imaging source output signals for medical diagnosis and referral to physicians and their patients.

    Here's an analysis of the provided information regarding acceptance criteria and the study that proves the device meets them:

    1. Table of Acceptance Criteria and Reported Device Performance

    Acceptance Criteria CategorySpecific CriteriaReported Device Performance
    Safety and EffectivenessCompliance with voluntary standardsAssured via meeting voluntary standards: DICOM, SMPTE, UL 60950, IEC 60601-1-1, IEC 60825-1, ISO 12207, ISO 14971.
    Equivalence to Predicate DeviceSame safety standards as predicateDesigned to equivalent safety standards as KODAK DRYVIEW 8900 with Mammography Accessory.
    Consistency of Image QualityAssure consistency between input signals and output densityIncorporates a test pattern generator and Automatic Image Quality Control (AIQC) system.
    High Resolution PrintingHigh resolution printing capabilityDescribed as a "high resolution printer."
    Quality Assurance TestingTools for MQSA quality assurance testingIncorporates test patterns to assist in MQSA quality assurance testing.

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

    The provided document does not explicitly describe a formal "test set" in the context of clinical or performance data. The evaluation of the device relied on compliance with standards and a comparison to a predicate device. Therefore, no information is available regarding:

    • Sample size for a test set.
    • Country of origin of data.
    • Retrospective or prospective nature of data.

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

    This information is not applicable as the document does not describe a study involving a "test set" that required expert establishment of ground truth for a diagnostic outcome. The device is a printer, and its performance evaluation focused on technical specifications and output quality.

    4. Adjudication Method for the Test Set

    This information is not applicable for the same reasons as point 3.

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

    A MRMC comparative effectiveness study was not performed or reported in the provided document. The focus was on the device's technical performance and equivalence to a predicate, not on how its use might impact human reader performance.

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

    This is a standalone device in the sense that its primary function is to print images based on digital inputs. However, the document does not describe a "standalone study" in the common understanding of an algorithm's diagnostic performance without human interaction. Instead, it describes technical performance and image quality as objectively measured and compared to standards and a predicate device.

    7. Type of Ground Truth Used

    The "ground truth" in this context refers to the technical specifications and image quality standards that the device is designed to meet, as well as the performance characteristics of the predicate device. It's about how accurately the printer reproduces digital images, not about diagnostic accuracy of the images themselves. The document states that "Medical personnel review images displayed by the subject device and its predicate. This offers ample opportunity for competent human intervention in case of a malfunction or other failure." This implies the ultimate "ground truth" for diagnostic purposes remains with the human medical expert reviewing the printed image.

    8. Sample Size for the Training Set

    This information is not applicable. The device is a hardware printer with software control, not an AI/ML algorithm that undergoes "training" with a dataset in the typical sense. Its design and automated functions (like AIQC) are built-in, not learned from a training set of images.

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

    This information is not applicable for the same reasons as point 8. The "ground truth" for its internal calibration and quality control (AIQC) would be factory-set parameters and established film characteristics.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1