Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K211951
    Device Name
    GI Genius
    Date Cleared
    2021-07-23

    (30 days)

    Product Code
    Regulation Number
    876.1520
    Reference & Predicate Devices
    Predicate For
    Why did this record match?
    Reference Devices :

    DEN200055

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

    The GI Genius System is a computer-assisted reading tool designed to aid endoscopists in detecting colonic mucosal lesions (such as polyps and adenomas) in real time during standard white-light endoscopy examinations of patients undergoing screening and surveillance endoscopic mucosal evaluations. The GI Genius computer-assisted detection device is limited for use with standard white-light endoscopy imaging only. This device is not intended to replace clinical decision making.

    Device Description

    GI Genius is an artificial intelligence-based device that has been trained to process colonoscopy images containing regions consistent with colorectal lesions like polyps, including those with flat (non-polypoid) morphology.

    GI Genius is compatible with the following Video Processors: Fujifilm VP-7000, Olympus CV-180 EXERA II, Olympus CV-190 EXERA III, Fujifilm VP-4450HD, and Pentax EPK-i7000 Video Processor.

    GI Genius is connected between the video processor and the endoscopic display monitor. When first switched on, the endoscopic field of view is clearly identified by four corner markers, and a blinking green square indicator appears on the connected endoscopic display monitor to state that the system is ready to function.

    During live video streaming of the endoscopic video image, GI Genius generates a video output on the endoscopic display monitor that contains the original live video together with superimposed green square markers that will appear when a polyp or other lesion of interest is detected, accompanied by a short sound. These markers will not be visible when no lesion detection occurs.

    The operating principle of the subject device is identical to that of the predicate device, this being a computer-assisted detection device used in conjunction with endoscopy for the detection of abnormal lesions in the gastrointestinal tract. This device with advanced software algorithms brings attention to images to aid in the detection of lesions. The device includes hardware to support interfacing with video endoscopy systems.

    AI/ML Overview

    Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The acceptance criteria are implicitly defined by the comparison to the predicate device (GI Genius v1.0.2). The goal of the study for GI Genius v2.0.0 was to demonstrate non-inferiority or improved performance compared to the predicate.

    CharacteristicAcceptance Criteria (Predicate Device Performance)Reported Device Performance (GI Genius v2.0.0)Result (vs. Predicate)
    Lesion-based sensitivity82.0 %86.5 %Improved
    Frame-level True Positive228,929269,223Improved
    Frame-level True Negative5,235,6825,239,128Improved
    Frame-level False Positive108,115104,669Improved
    Frame-level False Negative232,861192,567Improved
    True Positive Rate per frame Mean49.57 %58.30 %Improved
    True Positive Rate per frame % of polyps99.7 %100 %Improved
    False Positive Rate per frame Mean2.02 %1.96 %Improved
    Frame-Based TPr/FPr ROC curve, AUC0.7230.796Improved
    False positive clusters < 500 msBaseline40 less than baselineImproved
    False positive clusters > 500 msBaseline1 more than baselineSimilar
    Video delay, signal in to signal out1.52 μs1.52 μsSame

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

    The non-clinical testing for standalone performance used 150 videos containing 338 polyps.

    The data provenance is not explicitly stated regarding country of origin or whether it was retrospective or prospective. However, given that it's a re-training of a neural network with "additional procedure videos," it suggests a retrospective dataset of previously recorded endoscopy procedures.

    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 given text.

    4. Adjudication Method for the Test Set

    This information is not provided in the given text.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, and Effect Size

    A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly mentioned for the GI Genius v2.0.0. The evaluation focuses on standalone performance relative to its predicate.

    6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

    Yes, a standalone performance test was done. The text states: "Standalone Performance Testing has been carried out to assess the performance of the subject device in accordance with the same test protocol as that used for the predicate device, the results of which demonstrate substantial equivalence to the predicate device."

    7. The Type of Ground Truth Used

    The ground truth used for performance evaluation appears to be based on the identified "polyps and adenomas" within the procedure videos. While not explicitly stated as "expert consensus" or "pathology," the context of "colonic mucosal lesions (such as polyps and adenomas)" generally implies a clinical or pathological reference standard.

    8. The Sample Size for the Training Set

    The document mentions that the neural network was re-trained with "additional procedure videos" and "improved data augmentation," but it does not specify the sample size of the training set (number of videos or lesions).

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

    The document does not explicitly state how the ground truth for the training set was established. However, given that the device aids in "detecting colonic mucosal lesions (such as polyps and adenomas)," it implies that these lesions were identified and annotated within the training videos, likely by expert endoscopists or pathologists.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1