Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K980831
    Date Cleared
    1998-08-27

    (176 days)

    Product Code
    Regulation Number
    892.1000
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The intended use and indications for use for each of the types of Post-Processing Techniques described in this submission are described below.

    ProPak Techniques
    The ProPak Package for Picker MR systems or workstations provide supplemental information regarding contrast changes over time for those images extracted from MR temporal datasets. The indications for use for the MR system remain unchanged.

    Apparent Diffusion Coefficient Mapping
    The Picker Diffusion-Weighted MR Imaging Package has been designed to image the diffusive mobility of water or other proton-containing molecules. One important clinical application is to visualize the apparent loss of mobility of water molecules in brain tissue affected by acute stroke. Areas of decreased diffusion, as is observed in acute cerebral infarcts, appear as areas of higher image intensity. Post-processing using ADC mapping produces parametric images with further contrast manipulation.

    Diffusion weighted MR pulse sequences are more accurate than conventional MRI pulse sequences in identifying the occurrence of acute stroke during the first 24 hours after onset of symptoms.

    Device Description

    There are two basic types of post-processing techniques included in this submission. The first type is known as ProPak and is a set of techniques for processing temporally resolved image data sets and performing general perfusion analysis. The second type of technique is called ADC mapping and is for processing data from diffusion-weighted imaging sequences. All of the techniques included in this submission are for processing existing images that have already been reconstructed.

    AI/ML Overview

    The provided document is a 510(k) premarket notification for "Image Post-Processing Techniques" (ProPak and Apparent Diffusion Coefficient Mapping). This type of submission focuses on demonstrating substantial equivalence to legally marketed predicate devices, rather than establishing specific acceptance criteria and proving performance through a standalone clinical study with detailed metrics typically found in efficacy studies.

    Therefore, the document does not contain the detailed information requested regarding specific acceptance criteria, a standalone study proving performance against those criteria, sample sizes for test/training sets, ground truth establishment, or multi-reader multi-case (MRMC) comparative effectiveness studies.

    Instead, the submission relies on demonstrating that the new device has "similar technological characteristics and intended use" to existing predicate devices. The "Safety and Effectiveness" section explicitly states: "The Post-Processing Techniques described in this submission are substantially equivalent in technological characteristics and intended use to the GE Functool Option, the Philips Quantitative Analysis Package and the Picker Diffusion-Weighted Imaging Package."

    Here's a breakdown of what can be extracted and what is missing based on your request:


    1. A table of acceptance criteria and the reported device performance

    • Acceptance Criteria: Not explicitly defined or reported in the document. The implicit "acceptance criterion" for a 510(k) is substantial equivalence to predicate devices, meaning the new device is as safe and effective as existing legally marketed devices.
    • Reported Device Performance: No specific performance metrics (e.g., sensitivity, specificity, accuracy, precision) are reported for the new device. The document describes the features and intended uses of the device and compares them to predicate devices, inferring similar performance.
    ParameterAcceptance Criteria (Implied by Substantial Equivalence)Reported Device Performance (as described in comparison to predicates)
    CompatibilityMust be compatible with existing MR systems/workstations like predicates."Same" as predicate (available on Independent Workstations or MR System Operator's Console).
    InputsMust process MR images, single/multi-slice datasets (ProPak), and diffusion-weighted images (ADC Mapping)."Same" as predicate (MR images, single/multi-slice datasets with equally spaced time intervals (ProPak), Diffusion-weighted images (ADC Mapping)).
    FeaturesMust provide post-processing features comparable to predicates (e.g., semi-automated, color parametric images, pixel-by-pixel analysis, time intensity information)."Semi-automated," "Color parametric images (optional)," "Analysis on a pixel-by-pixel basis or region of interest," "Time intensity information in plot or tabular form." These are similar to predicate features (automated, color parametric images, overlay, pixel-by-pixel, time intensity info).
    Filming and ArchivingMust allow filming, storage, and archiving similar to predicates."Same" as predicate (images can be filmed, stored, or archived).
    Anatomy of InterestMust apply to similar anatomical regions as predicates."Same" as predicate (Brain and Body Imaging).
    Processing AlgorithmsMust include algorithms comparable to predicates (e.g., Area Mapping, Time to Peak Mapping, ADC Mapping)."Area Mapping," "Time to Peak Mapping," "ADC Mapping." These are algorithms identified for the device. Predicates have different but related algorithms like "Negative Enhancement Integral" and "Mean Time to Enhance."
    Indications for Use (ProPak)Must provide supplemental information regarding contrast changes over time for images from MR temporal datasets, with unchanged MR system indications."Provides supplemental information regarding contrast changes over time for those images extracted from MR temporal datasets. The indications for use for the MR system remain unchanged." (Matches predicate's general description).
    Indications for Use (ADC Mapping)Must image diffusive mobility, visualize loss of mobility in acute stroke, and produce parametric images with further contrast manipulation."Designed to image the diffusive mobility of water or other proton-containing molecules... visualize the apparent loss of mobility of water molecules in brain tissue affected by acute stroke... produces parametric images with further contrast manipulation." (Adds the parametric image aspect to the predicate's description).

    2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

    • Not Applicable / Not Provided. The document does not describe a specific "test set" or clinical study for the new device itself to establish performance metrics against acceptance criteria. The basis for safety and effectiveness is substantial equivalence to predicate devices, which implies that the predicate devices had already demonstrated effective performance.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

    • Not Applicable / Not Provided. As no specific "test set" with ground truth establishment for this device is described, there's no mention of experts for ground truth.

    4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

    • Not Applicable / Not Provided. No test set or ground truth adjudication method 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, not done/described. This document does not describe an MRMC study or any study involving human readers' performance with or without the AI (post-processing) assistance. The device is a post-processing tool and its equivalence is based on its technical specifications.

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

    • Not explicitly described as a standalone performance study. While the device itself is an algorithm (post-processing technique), the document doesn't detail a study specifically to measure its standalone performance (e.g., accuracy of mapping values against a gold standard). Its "performance" is implicitly assumed to be equivalent to the predicate devices based on its similar design and intended use.

    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

    • Not Applicable / Not Provided. No ground truth is described for this device, as its premarket notification relies on substantial equivalence.

    8. The sample size for the training set

    • Not Applicable / Not Provided. This document does not refer to a "training set" as it's not describing a machine learning model's development in detail, but rather a software feature set that processes existing images.

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

    • Not Applicable / Not Provided. As no training set is mentioned, no ground truth establishment for it is described.

    In summary, the provided K980831 document is a request for regulatory clearance based on substantial equivalence. It focuses on comparing the new device's technical characteristics and intended use to already cleared predicate devices. It does not contain the detailed clinical study information (like defined acceptance criteria, sample sizes, ground truth, or MRMC studies) that would be expected for a device proving novel efficacy or performance through a dedicated study.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1