Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K060840
    Device Name
    SVIEW
    Date Cleared
    2006-04-07

    (10 days)

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

    SVIEW

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

    SView 1.0 is a medical image management device intended for viewing, manipulating and analyzing DICOM-compliant medical images acquired from MRI scanners and other DICOM -compliant imaging devices. SView™ 1.0 can be used for real-time image viewing, manipulation and analysis that aid a cardiologist or radiologist in their diagnosis. In addition, it facilitates the physician's reporting and reviewing of patient studies.

    Device Description

    SView " 1.0 is a tool for 2D (two-dimensional) viewing and manipulation of DICOM compliant MR images and other DICOM-compliant images. The proposed device provides real-time image viewing, manipulation, analysis and reporting.

    AI/ML Overview

    The provided 510(k) summary for the SView™ Version 1.0 PACS/Medical Image Management Device does not describe an acceptance criteria or a study proving the device meets said criteria in the way typically associated with algorithms or AI models.

    This device is classified as a "PACS / Medical Image Management Device" and a "System, Image Processing." The 510(k) summary explicitly states:

    "The SView™ medical image management device contains no image digitizers and uses only lossless compression. On this basis, MRI Cardiac Services, Inc. believes that clinical investigation is not necessary."

    Instead of a clinical study, the submission focuses on demonstrating substantial equivalence to a predicate device (AccuView Diagnostic Imaging Workstation Software Package, K990241) by comparing features and specifications. The "Laboratory and Clinical Testing" section describes general software testing rather than a performance study against clinical endpoints or ground truth.

    Therefore, many of the requested details about acceptance criteria, performance, sample sizes, and ground truth are not applicable to the information provided in this 510(k) summary.

    Here's an analysis based on the information available:

    1. Table of Acceptance Criteria and Reported Device Performance:

    Not applicable. The submission does not define specific performance metrics or acceptance criteria for an algorithm's diagnostic performance. The substantial equivalence argument rests on functional equivalency with the predicate device for image viewing and manipulation.

    2. Sample size used for the test set and the data provenance:

    • Test Set Sample Size: Not applicable. No clinical test set for algorithmic performance evaluation is described.
    • Data Provenance: Not applicable.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    Not applicable. No ground truth establishment for a diagnostic algorithm is described.

    4. Adjudication method for the test set:

    Not applicable. No test set requiring adjudication is described.

    5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

    No. The document explicitly states that "clinical investigation is not necessary." Therefore, no MRMC study was conducted.

    6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

    Not applicable. This device is described as a "tool for 2D (two-dimensional) viewing and manipulation of DICOM compliant MR images" and not a standalone diagnostic algorithm. Its function is to aid a cardiologist or radiologist, implying a human-in-the-loop scenario, but no performance study is detailed.

    7. The type of ground truth used:

    Not applicable. No ground truth for an algorithm's diagnostic performance is mentioned.

    8. The sample size for the training set:

    Not applicable. This device is a PACS/image management system, not an AI/ML algorithm that requires a training set.

    9. How the ground truth for the training set was established:

    Not applicable. As above, no training set or ground truth for training is described.

    Summary of what the document does say about testing:

    • Laboratory and Clinical Testing: "SView 1.0 is intended for use with existing MRI images for real-time image viewing, image manipulation, and analysis that aid a cardiologist or radiologist in their diagnosis. In addition it facilitates the physician's reporting and reviewing of patient studies. The SView™ medical image management device contains no image digitizers and uses only lossless compression. On this basis, MRI Cardiac Services, Inc. believes that clinical investigation is not necessary."
    • Software Testing: "Extensive testing of the device will be performed by programmers, by nonprogrammers, quality assurance staff and by potential customers prior to commercial release." This refers to software validation and verification, not clinical performance studies.

    In conclusion, this 510(k) summary for SView™ 1.0 explicitly states that clinical investigation (and by extension, the detailed performance studies, ground truth establishment, and sample sizes you've asked about) was deemed unnecessary because the device is a medical image management system that does not perform diagnostic algorithms, uses lossless compression, and is claiming substantial equivalence based on functional similarity to an existing predicate device.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1