K Number
K132824
Date Cleared
2014-02-06

(150 days)

Product Code
Regulation Number
892.2050
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The CARESTREAM Vue PACS is an image management system whose intended use is to provide completely scalable local and wide area PACS solutions for hospital and related institutions/sites, which will archive, distribute, retrieve and display images and data from all hospital modalities and information systems.

The system contains interactive tools in order to ease the process of analyzing and comparing three dimensional (3D) images. It is a single system that integrates review, dictation and reporting tools to create a productive work environment for the radiologists and physicians.

The Vue Motion software program is used for patient management by clinicians in order to access and display patient data, medical reports, and medical images for diagnosis from different modalities including CR. DR, CT, MR, NM and US.

Vue Motion provides wireless and portable access to medical images for remote reading or referral purposes from web browsers including usage with validated mobile devices. This device is not intended to replace full workstations and should be used only when there is no access to a workstation. For primary interpretation and review of mammography images, only use display hardware that is specifically designed for and cleared by the FDA for mammography.

Device Description

CARESTREAM Vue PACS is an image management system whose intended use is to provide completely scalable local and wide area PACS solutions for hospital and related institutions/sites, which will archive, distribute, retrieve and display images and data from all hospital modalities and information systems.

It is a software only solution that contains interactive tools in order to ease the process of analyzing and comparing three dimensional (3D) images. It is a single system that integrates the review, dictation and reporting tools that creates a productive work environment for the radiologists and physicians.

Vue PACS provides functionality to allow remote site access to image and patient data enabling diagnostic reading through industry standard interfaces. It is designed using an open architecture that allows for various proprietary and off the shelf software components to be integrated with off the shelf hardware components and configured meeting the user's specific needs in a single-site or multi-site environment.

CARESTREAM Vue Motion is a Light Viewer designed to provide wireless and portable access to medical images for remote reading or referral purposes from web browsers including enterprise distribution of the radiology images and related data. The needs to provide real time imaging results and imaging related data to the enterprise users' commands that imaging solutions have a simple distribution mechanism through simple and broadly used technology. The patient portfolio is made available to physicians from their offices within their EMR. from home on local PC's or remotely through tablet and other devices. With integration into EMR systems, Vue Motion helps hospital users and healthcare facilities enhance patient care, by bringing the complete patient imaging record and supporting data into the healthcare enterprise. Image storage, viewing and distribution becomes a seamless part of the EMR.

A "patient search page", including smart Google-like search capabilities is also available for users that have no local EMR/HIS integration.

Vue Motion is offered as an option for the PACS, Vue Archive (onsite or via Vue Cloud) or The Carestream Vendor Neutral Archive and provides a zero footprint imaging viewer that can be deployed on the fly and accessible by the right user from anywhere, over virtually any operating system or over virtually any browser enabled device. The software technology uses HTML5 which allows any browser enabled device to run the software application.

CARESTREAM Vue Motion has a simpler GUI for viewing including zoom, pan, windowing, basic measurements, cine etc. It works on any operating system and with virtually any browser enabled device such as PC's, iPad, mobiles etc. It is selfdeployable and performs well over low bandwidth networks. It supports collaboration with other users through the sticky notes mechanism.

AI/ML Overview

The provided text describes the CARESTREAM Vue PACS v11.4 Vue Motion, an image management system with mobile access capabilities. It outlines the product's description, intended use, and technological characteristics, as well as its substantial equivalence to a predicate device.

However, the document does not explicitly state specific acceptance criteria in a quantitative or pass/fail manner, nor does it detail a formal study with a defined test set, ground truth establishment, or expert involvement. Instead, it broadly describes testing activities.

Here's an analysis based on the information available:


1. Table of Acceptance Criteria and Reported Device Performance

As specific quantitative acceptance criteria are not explicitly stated, the table below presents the types of performance aspects tested and the overall reported outcome.

Acceptance Criteria (Implied)Reported Device Performance
Bench Performance:
- Luminance Response (on approved devices)Each device (Apple iPad2, Apple iPhone 4S, Galaxy S3, Galaxy Note 10.1) was determined to be acceptable in bench performance testing.
- Device and Display Settings (on approved devices)Each device (Apple iPad2, Apple iPhone 4S, Galaxy S3, Galaxy Note 10.1) was determined to be acceptable in bench performance testing.
- Optimal Viewing Angle (on approved devices)Each device (Apple iPad2, Apple iPhone 4S, Galaxy S3, Galaxy Note 10.1) was determined to be acceptable in bench performance testing.
- Resolution (on approved devices)Each device (Apple iPad2, Apple iPhone 4S, Galaxy S3, Galaxy Note 10.1) was determined to be acceptable in bench performance testing.
- Noise (on approved devices)Each device (Apple iPad2, Apple iPhone 4S, Galaxy S3, Galaxy Note 10.1) was determined to be acceptable in bench performance testing.
- Reflectivity (on approved devices)Each device (Apple iPad2, Apple iPhone 4S, Galaxy S3, Galaxy Note 10.1) was determined to be acceptable in bench performance testing.
- Battery Life (on approved devices)Each device (Apple iPad2, Apple iPhone 4S, Galaxy S3, Galaxy Note 10.1) was determined to be acceptable in bench performance testing.
- Exception Handling (on approved devices)Each device (Apple iPad2, Apple iPhone 4S, Galaxy S3, Galaxy Note 10.1) was determined to be acceptable in bench performance testing.
Clinical Assessment:The Clinical Assessments indicated that Vue Motion images of diagnostic quality can be displayed on each of the devices across all target modalities.
- Display of diagnostic quality images (on approved devices)The Clinical Assessments indicated that Vue Motion images of diagnostic quality can be displayed on each of the devices across all target modalities.
Functional QA:Functional QA testing demonstrated that key features of the system operate acceptably on PCs, Mobile, and Tablet Devices.
- Acceptable operation of key system features (on all platforms)Functional QA testing demonstrated that key features of the system operate acceptably on PCs, Mobile, and Tablet Devices.
Equivalence to Predicate Device:Bench performance testing results support equivalence to the Carestream PACS predicate. Clinical Assessments support equivalence to the Carestream PACS predicate. No substantial differences that affect safety and efficacy were noted compared to the CARESTREAM PACS predicate (K110919). The new product brings features to additional display devices and performs the same.
- Performance and safety equivalence to predicateBench performance testing results support equivalence to the Carestream PACS predicate. Clinical Assessments support equivalence to the Carestream PACS predicate. No substantial differences that affect safety and efficacy were noted compared to the CARESTREAM PACS predicate (K110919). The new product brings features to additional display devices and performs the same.

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

  • Sample Size for Test Set: Not explicitly stated as a numerical count of cases or images. The document refers to "each of the devices" (Apple iPad2, Apple iPhone 4S, Galaxy S3, and Galaxy Note 10.1) being tested.
  • Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The document mentions "Vue Motion images of diagnostic quality" were used but doesn't detail their source or type.

3. Number of Experts and Qualifications for Ground Truth Establishment

  • Number of Experts: Not specified.
  • Qualifications of Experts: Not specified. It only states that "Clinical Assessments" were performed, implying involvement of medical professionals, but their number and specific qualifications (e.g., radiologists, years of experience) are not detailed.

4. Adjudication Method for the Test Set

  • Adjudication Method: Not specified. The document does not describe any multi-reader review or consensus process for clinical assessment.

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

  • MRMC Study Done: No. The document does not mention an MRMC study comparing human readers with and without AI assistance. The focus is on demonstrating that the device itself can display images of diagnostic quality and is equivalent to the predicate PACS.
  • Effect Size of Human Readers Improvement with AI vs. without AI: Not applicable, as no MRMC study was performed.

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

  • Standalone Performance Done: This device is an image display and management system, not primarily an AI algorithm for diagnostic interpretation. Its performance is tied to its ability to render medical images accurately on specified mobile devices. The "Bench Testing" and "Functional QA testing" could be considered components of standalone performance for the software/device combination, but not in the context of an AI diagnostic algorithm's standalone accuracy. The "Clinical Assessments" evaluate the display capabilities for human diagnostic use, rather than an algorithm's diagnostic output.

7. Type of Ground Truth Used

  • Type of Ground Truth: For the "Clinical Assessments," the implicit ground truth seems to be the widely accepted understanding of "diagnostic quality" for medical images when viewed on the tested devices, presumably benchmarked against a full diagnostic workstation (the predicate PACS). This is not an explicit ground truth like pathology reports or patient outcomes data, but rather a qualitative assessment of display fidelity suitable for diagnosis by human users.

8. Sample Size for the Training Set

  • Sample Size for Training Set: Not applicable. This document describes a PACS and mobile viewer, not a machine learning or AI model that requires a "training set" in the conventional sense. The "training" here would refer to the software development and quality assurance processes.

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

  • Ground Truth for Training Set: Not applicable, as it's not an AI/ML system with a conventional training set. The "ground truth" for the software development and testing would be the functional requirements and specifications of the PACS and mobile viewer, ensuring it correctly processes, transmits, and displays DICOM images in accordance with industry standards and clinical needs.

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).