LogoFDA 510(k) Search
Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K250414
    Device Name
    CaloPix
    Manufacturer
    Tribun Health
    Date Cleared
    2025-05-14

    (90 days)

    Product Code
    QKQ
    Regulation Number
    864.3700
    Type
    Traditional
    Panel
    Pathology
    Reference & Predicate Devices
    K213883,K232202
    Predicate For
    N/A
    Why did this record match?
    Reference Devices :

    K213883, K232202

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

    For In Vitro Diagnostic Use Only

    CaloPix is a software only device for viewing and management of digital images of scanned surgical pathology slides prepared from Formalin-Fixed Paraffin Embedded (FFPE) tissue.

    CaloPix is intended for in vitro diagnostic use as an aid to the pathologist to review, interpret and manage these digital slide images for the purpose of primary diagnosis.

    CaloPix is not intended for use with frozen sections, cytology, or non-FFPE hematopathology specimens.

    It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the quality of the images obtained and the validity of the interpretation of images using CaloPix.

    CaloPix is intended to be used with the interoperable components specified in the below Table:

    Scanner HardwareScanner Output File FormatInteroperable Displays
    Leica Aperio GT 450 DX scannerSVSDell U3223QE
    Hamamatsu NanoZoomer S360MD Slide scannerNDPIJVC Kenwood JD-C240BN01A
    Device Description

    CaloPix, version 6.1.0 IVDUS, is a web-based software-only device that is intended to aid pathology professionals in viewing, interpreting and managing digital Whole Slide Images (WSI) of glass slides obtained from the Hamamatsu NanoZoomer S360MD slide scanner (NDPI file format) and viewed on the JVC Kenwood JD-C240BN01A display, as well as those obtained from the Leica Aperio GT 450 DX scanner (SVS file format) and viewed on the Dell U3223QE display.

    CaloPix does not include any automated Image Analysis Applications that would constitute computer aided detection or diagnosis.

    CaloPix is for viewing digital images of scanned glass slides that would otherwise be appropriate for manual visualization by conventional light microscopy.

    As a whole, CaloPix is a pathology Image Management System (IMS) which brings case-centric digital pathology image management, collaboration, and image processing. CaloPix consists of:

    • Integration with Laboratory Information Systems (LIS): Allows to obtain automatically from the LIS patient data associated with the cases, scanned whole slide images and other related medical images to be analyzed. The data stored in the database is automatically updated according to the interface protocol with the LIS.

    • DataBase: After ingestion, scanned WSI can be organized in the CaloPix database consisting of folders (cases) containing patient identification data and examination results from a LIS.

    Ingestion of the slides is performed through an integrated module that allows their automatic indexation based on patient data retrieved from the LIS. After their ingestion, image files are stored in a CaloPix-specific file storage environment, that can be on premises or in the cloud.

    • The CaloPix viewer component to process scanned whole slide images, that includes functions for panning, zooming, screen capture, annotations, distance and surface measurement, and image registration. This viewer relies on image servers (IMGSRV) which extract image tiles from the whole slide image file and send these tiles to the CaloPix viewer for smooth and fast viewing.
    AI/ML Overview

    The FDA 510(k) clearance letter for CaloPix indicates that the device's performance was evaluated through a series of tests to demonstrate its safety and effectiveness. The primary study described in the provided document focuses on technical performance testing rather than a clinical multi-reader multi-case (MRMC) study.

    Here's a breakdown of the requested information based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    TestAcceptance CriteriaReported Device Performance
    Pixel-wise comparison (Image Reproduction Accuracy)The 95th percentile of the pixel-wise color differences (CIEDE2000, ΔE00) in any image pair between CaloPix and the predicate device's IRMS must be less than 3 (ΔE00 < 3).Test results showed that the 95th percentile of pixel-wise differences between CaloPix and the comparators (NZViewMD and Aperio WebViewer DX) were less than 3 CIEDE2000. The output images were considered pixel-wise identical and visually adequate.
    Measurements of Area and DistanceAccuracy of measurements made in CaloPix reviewer confirmed by comparing to predicate device viewers. (Specific numerical criteria not provided).Tests verified that the distance and area measurements made in the CaloPix viewer accurately reflected the measurements made in the NZViewMD viewer and the Aperio WebViewer DX viewer.
    Turnaround Time- Image loading: ≤ 10 seconds- Panning: ≤ 7 seconds- Zooming: ≤ 7 secondsTurnaround times for opening an image and panning or zooming have been determined and found to be adequate for the intended use of the subject device. (Specific measured times not provided, but stated to meet criteria).
    Human Factors Validation StudyCaloPix to be safe and effective for the intended users, uses, and use environments (per FDA guidance "Applying Human Factors and Usability Engineering to Medical Devices (2016)").CaloPix has been found to be safe and effective for the intended users, uses and use environments.

    2. Sample Size and Data Provenance for Test Set

    • Sample Size for Pixel-wise Comparison: 30 whole slide images (WSIs). Specifically:
      • 25 H&E-stained (Formalin-Fixed Paraffin Embedded - FFPE) tissue glass slides.
      • 5 IHC-stained (Masson's trichrome stain, CD8, CD3, or CD20) FFPE tissue glass slides.
    • Data Provenance: Not explicitly stated regarding country of origin. The study appears to be a technical performance test using pre-scanned slides. It is unclear if these were from a retrospective or prospective collection for the purpose of this specific test. The mention of "FFPE tissue glass slides" implies clinical relevance.

    3. Number of Experts and Qualifications for Ground Truth

    • Number of Experts: One pathologist.
    • Qualifications of Experts: The text states, "as verified by a pathologist," but does not specify the pathologist's experience level (e.g., years of experience, board certification). This was for identifying "relevant pathological features" for ROIs.

    4. Adjudication Method for Test Set

    • No "adjudication method" in the sense of multiple readers coming to a consensus for diagnostic ground truth is described. The ground truth for the pixel-wise comparison was based on pre-identified Regions of Interest (ROIs) verified by a single pathologist. For the measurement and turnaround time tests, the comparison was against predicate device software performance.

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

    • No MRMC comparative effectiveness study was done comparing human reader performance with and without AI assistance. The described tests are technical performance evaluations of the viewing and management software's rendering accuracy, measurement functions, and speed.

    6. Standalone (Algorithm Only) Performance

    • This device, CaloPix, is described as a "software only device for viewing and management of digital images." It "does not include any automated Image Analysis Applications that would constitute computer aided detection or diagnosis." Therefore, no standalone (algorithm only) performance, as typically understood for an AI/CADe/CADx device, was conducted or is applicable since the device's function is solely as a viewing platform, not an analytical algorithm.

    7. Type of Ground Truth Used

    • Technical Ground Truth: For the pixel-wise comparison, the "ground truth" was established by comparing CaloPix's image rendering output against the image rendering of the predicate device's Image Review Manipulation Software (IRMS) (i.e., NZViewMD and Aperio WebViewer DX), with the acceptance criteria based on CIEDE2000 values. The relevant pathological features within the slides were identified by a pathologist for ROI selection.
    • For measurements, the ground truth was the measurements obtained from the predicate device's IRMS.
    • For turnaround time, the ground truth was the pre-defined time limits.
    • For human factors, the ground truth was the satisfaction of usability and safety criteria.

    8. Sample Size for the Training Set

    • Not Applicable / Not Provided: As CaloPix is a viewing and management software without AI/CAD algorithms, there is no mention of a "training set" in the context of machine learning model development. The tests described are functional and technical performance evaluations, not AI model validation.

    9. How Ground Truth for Training Set was Established

    • Not Applicable / Not Provided: See point 8.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1