Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K172998
    Device Name
    uWS-MI
    Date Cleared
    2018-04-05

    (190 days)

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

    K101749, K063324, K130451, K130902

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

    uWS-MI is a software solution intended to be used for viewing, manipulation, and storage of medical images. It supports interpretation and evaluation of examinations within healthcare institutions. It has the following additional indications:

    The PET/CT Oncology application is intended to provide tools to display and analyze the follow-up PET/CT data, with which users can do image registration, lesion segmentation, and statistical analysis.

    The PET/CT Dynamic Analysis application is intended to display the dynamic PET image data and its associated timeactivity curve.

    The PET/CT Brain Analysis (NeuroQ™) application is intended to analyze the brain PET scan, give quantitative results of the relative activity of 240 different brain regions, and make comparison of activity of normal brain regions in AC database.

    The PET/CT Cardiac Analysis (ECTbTM) application is intended to provide cardiac short axis reconstruction, browsing function. And it also performs perfusion analysis and cardiac function analysis of the cardiac short axis.

    Device Description

    uWS-MI is a comprehensive software solution designed to process, review and analyze PET, CT and PET/CT patient studies. It can transfer images in DICOM 3.0 format over a medical imaging network or import images from external storage devices such as CD/DVDs or flash drives. These images can be functional data, such as PET as well as anatomical datasets, such as CT. It can be at one or more time-points or include one or more time-frames. Multiple display formats including MIP and volume rendering and multiple statistical analysis including mean. maximum and minimum over a user-defined region is supported. A trained, licensed physician can interpret these displayed images as well as the statistics as per standard practice.

    AI/ML Overview

    The acceptance criteria and study proving device performance are not explicitly detailed in the provided text in the format requested. However, based on the scattered information, I can infer some points and explicitly state what is missing.

    The device is uWS-MI, a software solution for viewing, manipulation, and storage of medical images, with specific applications for PET/CT Oncology, PET/CT Dynamic Analysis, PET/CT Brain Analysis (NeuroQ™), and PET/CT Cardiac Analysis (ECTb™).

    The document is a 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices rather than providing a detailed performance study with specific acceptance criteria and detailed quantitative results.

    Here's an attempt to extract and synthesize the information based on your requested format:


    1. Table of Acceptance Criteria and Reported Device Performance

    Feature/ApplicationAcceptance Criteria (Implied)Reported Device Performance
    General Image ProcessingEquivalent functionality to predicate device (K123920 Syngo.via)All listed general functions (2D/3D review, filming, fusion, ROI/VOI, MIP display, compare) are "Same" as predicate.
    PET/CT Dynamic AnalysisEquivalent functionality to reference device (K101749 Syngo™TrueD Software)All listed functions (ROI Analysis, Pseudo color, Automatic cine, Curve Analysis, Table Statistics, Save, Filming) are "Same" as reference device. Reframe/Rebin functionality is present but differs from reference device, with a remark that it "will not impact the safety and effectiveness of the device."
    PET/CT OncologyEquivalent functionality to reference device (K063324 GE PET VCAR)All listed functions (Compare display, Auto registration, Manual registration, Fix Segmentation, Adaptive Segmentation, Spread, Statistical Analysis, Save) are "Same" as reference device.
    PET/CT Brain Analysis (NeuroQ™)Equivalent functionality to reference device (K130451 NeuroQ™3.6)All listed functions (Reformat, Quality Control, Slice Display, Compare, PET/CT Fusion, EQuAL analysis, AmyQ, Save results, Capture region/display, Exit) are "Same" as reference device.
    PET/CT Cardiac Analysis (ECTb™)Equivalent functionality to reference device (K130902 Emory Cardiac Toolbox™3.2)All listed functions (Reconstruction, SSS, Polor Maps, Perfusion Analysis, Viability Analysis, Functional Analysis, Save results, Capture region/display, Exit) are "Same" as reference device.
    Safety and EfficacyOverall safety and effectiveness profile similar to predicate device."uWS-MI was found to have a safety and effectiveness profile that is similar to the predicate device."

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

    The document does not explicitly state the sample size used for the test set or the data provenance (e.g., country of origin, retrospective/prospective). However, it mentions "Performance evaluation Report for PET/CT Oncology and Image Fusion" as part of Performance Verification. Details about this report, including the data used, are not provided. Given the nature of a 510(k) summary, the data often comes from internal testing designed to show equivalence, rather than large-scale clinical trials.

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

    This information is not provided in the document. Ground truth establishment details are absent.

    4. Adjudication Method for the Test Set

    This information is not provided in the document.

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

    A MRMC comparative effectiveness study was not specifically mentioned or detailed. The document focuses on demonstrating substantial equivalence based on features and software verification, and states "No clinical study was required." for general device clearance. The performance of specific applications (NeuroQ™ and ECTb™) leverages their prior clearances, implying that their functionalities, rather than a new comparative effectiveness study of the full uWS-MI system, were reviewed.

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

    The device is described as "stand-alone software," and its primary verification listed is "Software Verification and Validation." This suggests that the performance verification would have evaluated the algorithm's output independently, as a standalone system. However, the exact metrics and results of this standalone performance are not explicitly provided beyond the statement of functional equivalence to predicate/reference devices.

    7. Type of Ground Truth Used

    The type of ground truth used for specific performance evaluations is not explicitly stated. However, considering the device's function as an image post-processing and analysis tool, the ground truth would typically involve:

    • Expert consensus or expert readings: For evaluating the accuracy of image analysis, measurements, or lesion segmentation outputs.
    • Pathology or clinical outcomes data: For validating the diagnostic accuracy of features, particularly for oncology applications, though "no clinical study was required" suggests this was not the primary method for this 510(k).
    • Phantom or synthetic data: For testing algorithm robustness and accuracy in controlled environments.

    Since the PET/CT Brain Analysis (NeuroQ™) and PET/CT Cardiac Analysis (ECTb™) applications were cleared previously, their ground truth would have been established during their initial clearances, likely involving expert-derived truth based on clinical images or phantoms.

    8. Sample Size for the Training Set

    The document does not provide information regarding the sample size of any training set. As a 510(k) for a software device, the focus is often on functional equivalence and verification/validation, rather than detailing the machine learning model training process if such models are embedded.

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

    This information is not provided in the document.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1