Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K203260
    Date Cleared
    2022-01-28

    (449 days)

    Product Code
    Regulation Number
    892.2080
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    syngo.CT Brain Hemorrhage is designed to assist the radiologist in prioritizing cases of suspected intracranial hemorrhage on non-contrast CT examinations of the head. It makes case-level output available to a CT scanner or other PACS system for worklist prioritization. The output is intended for informational purposes only and is not intended for diagnostic use. The device does not alter the original medical image and is not intended to be used as a stand-alone diagnostic device.

    Device Description

    The subject device syngo.CT Brain Hemorrhage is an image processing software that utilizes artificial intelligence learning algorithms to support qualified clinicians in analysis and prioritization of noncontrast head CT DICOM images by algorithmically identifying findings suspicious of acute intracranial hemorrhage. The subject device provides a pipeline for the analysis and identification of potential ICH as well as a finding notification mechanism.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study proving the device's performance, based on the provided text:

    Acceptance Criteria and Device Performance Study for syngo.CT Brain Hemorrhage

    1. Table of Acceptance Criteria and Reported Device Performance

    The document states a performance goal rather than strict acceptance criteria with defined thresholds. The acceptance was based on exceeding this goal.

    Performance MetricPerformance Goal (Acceptance Criteria)Reported Device Performance
    Sensitivity> 80%92.8% (95% CI: 89.3%-95.2%)
    Specificity> 80%94.5% (95% CI: 91.3%-96.5%)
    Average Per-Case Processing TimeComparable to predicate device13.67 seconds (95% CI: 7.48-19.86 seconds)

    2. Sample Size and Data Provenance

    • Test Set Sample Size: 600 anonymized head CT cases.
    • Data Provenance: The cases were collected from 5 sites in the US and Europe. The data was retrospective.
    • Case Distribution: Approximately equal distribution of positive (cases with ICH) and negative (cases without ICH) cases.

    3. Number and Qualifications of Experts for Ground Truth

    • Number of Experts: 3
    • Qualifications: US board-certified neuroradiologists with more than 10 years of experience.

    4. Adjudication Method for the Test Set

    The ground truth was established by majority read of the 3 neuroradiologists. This implies a 2+1 adjudication, where if at least two experts agreed, that decision was taken as the truth.

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

    No MRMC comparative effectiveness study was mentioned. The study described is a standalone performance study of the algorithm. Therefore, there is no information on how human readers improved with AI vs. without AI assistance. The device is intended solely for worklist prioritization and is not for diagnostic use or to alter images.

    6. Standalone (Algorithm Only) Performance Study

    Yes, a retrospective standalone performance study was conducted. The reported sensitivity and specificity values are for the algorithm only, without human-in-the-loop.

    7. Type of Ground Truth Used

    The ground truth was established by expert consensus (majority read of 3 US board-certified neuroradiologists).

    8. Sample Size for the Training Set

    The document does not specify the sample size used for the training set. It only describes the validation (test) set.

    9. How Ground Truth for the Training Set Was Established

    The document does not provide information on how the ground truth for the training set was established. It only details how the ground truth for the test set was created (majority read by 3 neuroradiologists).

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1