(335 days)
The Communify PACS Viewer 1.5 is a Picture Archiving and Communications System (PACS) viewer designed to be used to view Digital Imaging and Communications in Media (DICOM), DICOM-RT and non-DICOM information and data. The Communify PACS Viewer 1.5 is a software application that runs on standard "off-the-shell" personal computers, business computers, and servers running standard operating systems. Communify PACS Viewer is an image and display software that accepts DICOM data from any OEM modality which supports DICOM standard imaging data; the system provides the capability to organize images generated by OEM vendor equipment, perform digital manipulations, create graphical representations of anatomical areas, and perform quantitative measurements.
Communify PACS Viewer 1.5 is designed to support the use and viewing of DICOM-RT (radiotherapy extensions), such as Structure Set, Contour, Dose, Dose Value Histogram and Plan information.
In Communify PACS Viewer 1.5, mammographic images should only be viewed on mammography monitors that are cleared or approved by FDA. Users should not apply lossy compression to mammographic images and only DICOM "for presentation" mammography images may be displayed. Communify PACS Viewer 1.5 does not manipulate or edit any mammography image acquisition system manufacturer's proprietary image processing methods.
Please note that Communify PACS Viewer 1.5 does not run on mobile smartphones and tablets.
Communify PACS Viewer (version 1.5) is a Picture Archiving and Communications System (PACS) viewer application which allows users to view, manipulate, annocate, transmit to other facilities, print, and animate all manners of DICOM and DICOM-RT images and modalities include, but are not limited to, CR, CT, DX, MR, NM, PT, RF, US, and XA.
Communify PACS Viewer 1.5 contains common image manipulation functions (such as zoom, pan, triangulation, and window/level) and common image labeling tools (including measurements tools, drawing tools, and annotation overlays). The annotation overlay displays all the important metadata (as configured by the user) for each displayed series study. Although annotation fields depend on the modality and the patient study, the Annotation Overlay Template Wizard provides a full list of annotation fields the user can assign into the image display. For RT studies, Communify PACS Viewer 1.5 allows the visualization of the RT Structure Set, Dose, Dose Value Histogram, and Plan data.
There are shortcut keys, toolbars, and right-click menus for easy access to tools and features. The Hanging Protocol editor of the Communify PACS Viewer configures the presentation layout of images on the screen when a study is loaded. This allows commonly used display formats and presets to be saved and easily accessed to allow for faster case study reviews.
The provided text does not contain detailed acceptance criteria or a specific study proving the device meets acceptance criteria in the format typically used for performance studies of medical AI devices. Instead, it describes a PACS viewer (Communify PACS Viewer 1.5) and its substantial equivalence to predicate devices (Communify PACS Viewer 1.0 and MIMviewer 4.1).
The "Performance Data" section mentions "Software verification and validation was performed following FDA guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." and states that "Tests were conducted successfully to address issues in the hazard analysis, confirm the functionality in the verification and validation section and to provide comparisons of samples with 510(k)-cleared DICOM-RT readers." This indicates a software validation process, but not a clinical study with specific performance metrics such as sensitivity, specificity, or reader agreement that would typically be associated with an AI device's acceptance criteria.
Based on the provided information, I can extrapolate the following:
1. A table of acceptance criteria and the reported device performance
Since this is a PACS viewer and not an AI-powered diagnostic device, the "acceptance criteria" appear to be related to its functionality, display capabilities, and adherence to DICOM standards, rather than diagnostic accuracy metrics. The document implies that the device successfully met these functional and comparative criteria.
| Acceptance Criteria (Implied) | Reported Device Performance (Implied) |
|---|---|
| Functional Equivalence to Predicate Devices | The device performs all capabilities of Communify PACS Viewer 1.0 and supports DICOM-RT data like MIMviewer 4.1. |
| DICOM Compliance and Modality Support | Processes and displays medical images from DICOM compliant modalities (CR, CT, DX, MR, NM, PT, RF, US, XA, and others). |
| Image Manipulation and Annotation Features | Supports common image manipulation (zoom, pan, triangulation, window/level) and labeling tools (measurements, drawing, annotation overlays). |
| DICOM-RT Data Visualization | Allows visualization of RT Structure Set, Dose, Dose Value Histogram, and Plan data. |
| Maintenance of Source Data Integrity | Does not alter the source data and original image. |
| Software Verification and Validation | Tests were conducted successfully to address issues in hazard analysis and confirm functionality per FDA guidance. |
| Comparison to 510(k)-cleared DICOM-RT Readers | Comparisons of samples were positive, indicating comparable performance. |
| Mammographic Image Handling | Viewed on FDA-cleared/approved monitors; no lossy compression; only DICOM "for presentation" mammography images displayed. |
| Operating Environment | Runs on standard "off-the-shelf" personal computers, business computers, and servers; does not run on mobile smartphones/tablets. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document mentions "comparisons of samples with 510(k)-cleared DICOM-RT readers." However, it does not specify the sample size, type of data (e.g., patient cases), country of origin, or whether the tests were retrospective or prospective. It refers to general software verification and validation, which typically involves testing with a representative set of data but not necessarily a clinical "test set" in the context of diagnostic performance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
This information is not provided. The study described is a software verification and validation study, not a clinical study involving human expert review for establishing ground truth on diagnostic performance.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable, as this was not a clinical study involving expert adjudication of cases.
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 MRMC study was performed. The device is a PACS viewer, not an AI diagnostic tool designed to assist human readers in making diagnoses or interpretations that would be measured by an MRMC study. The comparison was for functional equivalency, not diagnostic improvement.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. The device is a viewer, and its performance is inherently human-in-the-loop (the user viewing the images). It does not have a "standalone algorithm" performance in the traditional sense of an AI diagnostic device.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Given that the study was software verification and validation and comparison to predicate devices for functional equivalence, the "ground truth" would likely be adherence to DICOM standards, correct display of image data, accurate execution of manipulation functions, and consistency with data rendered by cleared predicate devices. It would not typically involve expert consensus, pathology, or outcomes data for diagnostic accuracy.
8. The sample size for the training set
Not applicable. The device is a software application (PACS viewer), not an AI model that requires a training set.
9. How the ground truth for the training set was established
Not applicable, as there is no training set for this type of device.
§ 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).