(12 days)
The Enterprise Visual Medical System(TM) is classified as a picture archive and communications system. It is a software only solution developed by Emageon Inc., that utilizes off the shelf software, standard computer workstations and standard storage devices that allow authorized physicians and authorized healthcare professionals to acquire, access, visualize and store digital medical images, and data associated with the images, across the enterprise using advanced content management and clinical workflow through a graphical user interface.
Advanced Visualization (Image Viewing) includes: Full featured 2D imaging, 3D Volume Rendering, Multi-Planar Reformatting (MPR), Real-time oblique imaging, Integrated image fusion, JPEG2000-based Adaptive Bandwidth Streaming, DICOM Image Note export, Presentation States, Annotation and Measurement tools, Automated linking, Display protocols, Enterprise Worklist, prior study management, archiving of digital mammography images provided that systems cleared via a cleared 510(k) are used and that digitized secondary captures of those images are not viewed for assisting in diagnosis, utilization of third-party electronic templates, the display of Standard Uptake Value, recording of third party, plug-in software, and user configurable settings for viewing digital medical images and corresponding data.
Emageon Inc.'s EVMS™ software is integrated client-server software package comprised of features that were previously cleared in Vortex ™, 510(k): K012097, and Ultravisual™, 510(k) K042008. The main difference is that the software will now allow display Standard Uptake Value measurements, MPR on irregular data sets and in oblique planes, and automatic region growing, the naming conventions of the components have been modified, the design architecture and the overall design and development process in order to synchronize the existing compliance to the federal QSR 21 CFR, Part 820 with ISO 13485:2003 and ISO 14971:2000/Amd 1 .: 2003(E).
The provided 510(k) summary for Emageon Inc.'s EVMS™ Enterprise Visual Medical System software focuses on demonstrating substantial equivalence to previously cleared devices (Vortex™ and Ultravisual™) rather than presenting a standalone study with defined acceptance criteria and performance metrics for the EVMS™ itself.
The submission states that EVMS™ is an integrated client-server software package comprised of features previously cleared. The main differences are the addition of Standard Uptake Value measurements, MPR on irregular datasets and in oblique planes, automatic region growing, modified naming conventions, and updates to the design architecture and development process to align with ISO standards.
Based on the provided document, here's a breakdown of the information requested, with explicit notes where information is not available or implied by the substantial equivalence approach:
1. Table of Acceptance Criteria and Reported Device Performance:
No specific acceptance criteria or performance metrics (e.g., sensitivity, specificity, accuracy, precision) are defined for EVMS™. The submission relies on the substantial equivalence of its features to previously cleared devices. Therefore, a table for this device cannot be constructed as the data is not present in the document.
2. Sample Size Used for the Test Set and Data Provenance:
- Test Set Sample Size: Not specified.
- Data Provenance: Not specified. The submission refers to "Extensive testing... performed by programmers, non-programmers, quality assurance staff, potential customers, and contracted third parties," but does not detail a specific test set or its origins.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications:
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified. The document mentions "potential customers" testing, which might imply clinical users, but their specific qualifications for establishing ground truth are not detailed.
4. Adjudication Method for the Test Set:
- Adjudication Method: Not specified.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:
- MRMC Study: No. The document does not mention a MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The focus is on the software's functionality and equivalence to prior versions.
- Effect Size of Human Readers' Improvement with AI vs. Without AI Assistance: Not applicable, as no MRMC study was performed or reported.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:
- Standalone Performance Study: No. The document describes the software as an image processing system for display and analysis, intended for use by healthcare professionals. No standalone algorithm performance evaluation (e.g., for automated detection or diagnosis without human review) is reported.
7. The Type of Ground Truth Used:
- Type of Ground Truth: Not specified. Given the nature of the device (an image processing and PACS system), "ground truth" would likely relate to the accuracy of image display, measurements, and advanced visualization renderings compared to expected validated outputs or established clinical standards. However, no specific ground truth methodology is outlined.
8. The Sample Size for the Training Set:
- Training Set Sample Size: Not applicable/Not specified. The device is described as an image processing system, not a machine learning or AI algorithm that undergoes "training" in the traditional sense, as understood for predictive models. Its development involves standard software engineering practices.
9. How the Ground Truth for the Training Set Was Established:
- Ground Truth for Training Set: Not applicable/Not specified. As noted above, the concept of a "training set" and "ground truth" for it, as applied to machine learning, does not appear relevant to this submission. The development process refers to "design, developed, tested and validated according to written procedures" and compliance with QSR and ISO standards. The "ground truth" in this context would be the correct functioning of the software features as per specifications.
§ 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).