Search Results
Found 1 results
510(k) Data Aggregation
(47 days)
The BOX DICOM Viewer™ is a software Teleradiology system used to receive DICOM images, scheduling information and textual reports, organize and store them in an internal formation available across a network via web and customized user interfaces. The BOX DICOM Viewer™ is used by hospitals, imaging centers, radiologist reading practices.
Contraindications: The BOX DICOM Viewer™ is not intended for the acquisition of mammographic image data and is meant to be used by qualified medical personnel only who are qualified to create and diagnose radiological image data.
The BOX DICOM Viewer™ is a software system to be used to view DICOM compliant studies, which are stored. The BOX DICOM Viewer™ is intended for professional use only as a viewing tool for medical image studies.
The BOX DICOM VIEWER software allows for acquisition of images from DICOM devices and lets users view those images from their personal computers. A third party DICOM device sends to the Box DICOM Proxy listener, the files are then sent to the Upload Proxy, then to the DICOM processor where the DICOM header data is extracted. Finally, the BOX DICOM VIEWER will communicate with a database component to store all the information required for patients, users, studies and configuration settings.
Here's a breakdown of the acceptance criteria and study information for the BOX DICOM Viewer, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria for device performance. Instead, it relies on a comparative approach, demonstrating substantial equivalence to a predicate device (CLARISO PACS, K132799). The performance is reported by stating that the subject device (BOX DICOM Viewer) matches or improves upon the predicate's functionalities without introducing new safety risks.
| Functionality | Predicate (CLARISO PACS) Performance | Subject Device (BOX DICOM Viewer) Performance | Impact on Safety and/or Efficacy (if different) |
|---|---|---|---|
| Core Functionalities (1-37): Web Browser, Intended Use, Intended User, Network, Monitor, User Interaction/Input, Import/Export Images, Acquisition Devices, Image Organization, Image Search, Image Storage, Database Software, Greyscale Image Rendering, RGB Image Rendering, Localizer Lines, Localizer Point, Orientation Markers, Distance Markers, Study Data Overlays, Stack Navigation, Window Level, Zoom, Panning, Horizontal/Vertical Flip, Clockwise/Counterclockwise Rotate, Invert Image, Text Annotation, Area Measurement Annotation, Angle Measurement Annotation, Cobb Angle Measurement Annotation, Image Annotation, Security, DICOM 3.0 Conformance, Worklist, Thumbnail Viewing, Login, Audit | All "Yes" or specific descriptions (e.g., Google Chrome for browsers, 10/100/100 Ethernet, Above 19inch monitor, MySQL database) | "Same as predicate" for all these functionalities. The document states "The full features and functions of Clariso have been imported to the BOX DICOM Viewer". | "No differences between predicate and subject device" or "No difference". "No impact on safety or efficacy" for all these. |
| User Interface (38): Text styles, colors, fonts, and icons | CLARISO PACS styles | BOX Styles (new styles, colors, fonts, and icons were added) | "Yes, there are differences, however these changes do not affect device functions and does not raise new potential safety risks. Therefore, it is our determination that there is 'No impact on safety or efficacy'." |
| WebGL Rendering Optimizations (39): Hardware acceleration | No hardware acceleration. | Yes, Hardware acceleration is used. "WebGL rendering optimizations" are added. | "Yes, there are differences, between the predicate and the subject device for WebGL since the subject device uses hardware acceleration and the predicate does not. However this difference do not affect the device IFU and does not raise new potential safety risks. The device has been tested and has passed predetermined criteria and therefore, it is our determination that there is 'No impact on safety or efficacy'." |
| Support for high resolution Retina displays (40) | Pixelated display on high-DPI displays only (i.e., "Retina Displays"). | Full pixel density on all displays. "Added support for high resolution Retina displays." | "Yes, there is a difference. The subject device will display the full pixel density of the saved image where the predicate device only did so if it was set to 'Retina Display' mode. This difference actually aids the viewer to always see the image as captured by the modality. The difference does not affect the device IFU and does not raise new potential safety risks. Therefore, it is our determination that there is 'No impact on safety or efficacy'." |
| Keyboard shortcuts for all tools and all annotation types (41) | Limited keyboard shortcut support. | Keyboard shortcuts allowed for tools and all annotation types. "Added keyboard shortcuts for all tools and all annotation types." | "Yes, there is a difference. In the predicate, it was not possible for the User to use the inherent functions of the operating system to create keyboard short cuts. In the subject device, keyboard shortcuts allowed for tools and all annotation types which may help the User view images." |
2. Sample size used for the test set and the data provenance
The document does not specify a distinct "test set" in the context of image data or patient cases for performance evaluation. The testing described is nonclinical testing related to the system's functionalities.
- Sample Size for Test Set: Not applicable or not specified in terms of clinical cases/images. The testing appears to be functional verification and validation of the software itself.
- Data Provenance: Not specified, as clinical data is not mentioned as part of the validation testing.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not provided in the document. As the validation is focused on technical functionalities and equivalence to a predicate, there is no mention of establishing ground truth by medical experts for image interpretation.
4. Adjudication method for the test set
This information is not provided in the document.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The device is a DICOM viewer, not an AI-powered diagnostic tool, and the focus of the submission is on substantial equivalence to an existing viewer, not on improving human reader performance.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, in essence. The testing described as "Nonclinical Testing" and the "Verification & Validation Test Plan" appears to be a standalone evaluation of the software's functionalities against predetermined criteria. The document states: "The BOX DICOM Viewer™ system and configuration has been assessed and tested at BOX Inc. and has passed all pre-determined testing criteria." and "Validation testing indicated, that as required by the risk analysis, designated individuals performed all verification and validation activities and that the results demonstrated that the predetermined acceptance criteria were met."
However, it's crucial to note that this "standalone" performance refers to the functional capabilities of the viewer (e.g., rendering correctly, performing measurements, handling DICOM data), not a diagnostic algorithm's accuracy in identifying medical conditions. The device is explicitly described as a "viewing tool" for medical image studies and emphasizes that "A physician, providing ample opportunity for competent human intervention interprets images and information being displayed and printed."
7. The type of ground truth used
The concept of "ground truth" in the clinical diagnostic sense (e.g., pathology, outcomes data) is not applicable to the nonclinical testing described for this device. The ground truth for this device's validation is based on:
- Functional Specifications: The software's ability to perform its stated functions (e.g., display images, perform measurements, store data) as defined in its design.
- Predicate Device Equivalence: The functions of the BOX DICOM Viewer are compared directly against the known and accepted functionalities of the CLARISO PACS predicate device.
8. The sample size for the training set
This information is not provided. The BOX DICOM Viewer is described as a software system that imports features from a previously cleared device and adds new functionalities. There is no mention of a "training set" in the context of machine learning or AI algorithm development, as the viewer itself is not presented as an AI diagnostic tool.
9. How the ground truth for the training set was established
This information is not provided, as there is no mention of a training set for an AI algorithm.
Ask a specific question about this device
Page 1 of 1