LogoFDA 510(k) Search
Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K230249
    Device Name
    Ikshana
    Manufacturer
    ImmersiveTouch
    Date Cleared
    2023-10-16

    (259 days)

    Product Code
    LLZ
    Regulation Number
    892.2050
    Type
    Traditional
    Panel
    Radiology (RA)
    Reference & Predicate Devices
    K183105,K190764
    Why did this record match?
    Device Name :

    Ikshana

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

    Ikshana is a software device to display medical images. It includes functions for image review, image manipulation, measurements, and 3D visualization.

    Medical images may only be interpreted using an FDA-cleared display monitor that meets technical specifications that are reviewed and accepted by the FDA.

    Ikshana is intended to be used as an adjunct to the interpretation of images performed using diagnostic imaging systems and is not intended for primary diagnosis. Display monitors used for reading medical images for diagnostic purposes must be FDA-approved radiology monitors.

    Ikshana software is indicated for use by qualified healthcare professionals, including, but not restricted to, radiologists, non-radiology specialists, physicians, and technologists.

    When accessing the Ikshana software from a wireless stereoscopic head-mounted display (HMD) or mobile device, the images viewed are for informational purposes only and are not intended for diagnostic use.

    Device Description

    Ikshana is a stand-alone modular software platform to be used by clinicians for the visualization of medical images in 3D to allow for surgical planning activities. The device takes 2D medical images and creates accurate 3D representations that clinicians can then view on a stereoscopic display. This modular package is used to

    • · Load patient CT/MR DICOM data
    • . View DICOM data using a traditional computer monitor or in Augmented Reality (AR) using a head-mounted display, HMD (Microsoft HoloLens 2).
    AI/ML Overview

    The provided document describes the acceptance criteria and the study conducted for the Ikshana device, particularly focusing on its measurement and segmentation capabilities.

    1. Table of Acceptance Criteria and Reported Device Performance:

    Feature/MetricAcceptance CriteriaReported Device Performance
    Measurement StudyInter and intra-user variability within set acceptable limits. Paired t-tests comparing Ikshana to Medical Mimics measurements (p > 0.05). Bland-Altman plots showing 95% of differences within acceptable limits.All inter and intra-user measurements fell within the set acceptance criteria. Paired t-tests resulted in p-values > 0.05, indicating no significant difference between Ikshana and Medical Mimics measurements. Bland-Altman plots confirmed high equivalence with 95% of differences within acceptable limits.
    Segmentation StudyVisual comparison with reference device showing high level of equivalence. Average DICE coefficient representing high agreement. Paired t-test comparing volume measurements (p > 0.05).Visual comparison showed a high level of equivalence between Ikshana and Mimics Medical. Average DICE coefficient of approximately 96% for 60 trials. Paired t-test resulted in a p-value above 0.05, suggesting likely equivalence between the two methods.

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

    • Measurement Study: A combination of orthopedic and maxillofacial models was used. The specific number of cases for the test set is not explicitly stated, but the study evaluated "multiple users."
    • Segmentation Study: 60 trials were conducted using a combination of cardiovascular, orthopedic, and maxillofacial models. The specific number of cases is not explicitly stated beyond "60 trials."
    • Data Provenance: Not specified in the provided text (e.g., country of origin or whether it was retrospective/prospective).

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

    • Segmentation Study: The results were "validated by subject matter experts." The specific number and qualifications of these experts are not mentioned.
    • Measurement Study: The ground truth for the measurement study seems to be derived from a comparison with the reference device, Medical Mimics, which implies its measurements are considered a reference standard, rather than expert consensus on individual cases.

    4. Adjudication Method for the Test Set:

    • The document does not explicitly describe an adjudication method like 2+1 or 3+1. For the segmentation study, it states results were "validated by subject matter experts," which suggests some form of expert review, but the specific process is not detailed. For the measurement study, the comparison is directly with the reference device's measurements.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

    • No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly described for assessing the improvement of human readers with AI assistance. The studies focused on the performance of the device itself (measurement and segmentation accuracy/equivalence).

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

    • Yes, the performance studies described (Measurement Study and Segmentation Study) appear to be standalone evaluations of the Ikshana software's capabilities. The measurement study compared Ikshana's measurements to another device, and the segmentation study compared Ikshana's segmentation models to a reference device, with expert validation. This assesses the algorithm's performance directly.

    7. The Type of Ground Truth Used:

    • Measurement Study: The ground truth for the measurement study appears to be established through measurements obtained using the referenced predicate device, Mimics Medical. The study aimed to show "equivalence" with the predicate, implying the predicate's measurements serve as the reference.
    • Segmentation Study: The ground truth for the segmentation study was established by comparing Ikshana's segmentation models with those from the previously cleared reference device, Mimics Medical (K183105), and these results were "validated by subject matter experts." This indicates a hybrid approach, using a cleared device as a primary reference and expert review for validation.

    8. The Sample Size for the Training Set:

    • The document does not provide information about the sample size used for the training set. The focus is on the performance evaluation of the final device.

    9. How the 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, as details about the training process are not included.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1