Search Results

Synapse Enterprise Viewer (EV) is a software-based enterprise image viewer used with general purpose servers and dedicated reading workstations. It allows for communication, rendering on the server component and communication and display of DICOM and non-DICOM images as well as reports.

The device is intended for use as a diagnostic, review and analysis tool by trained professionals such as radiologists, physicians and technologist. Synapse EV is not intended for diagnostic use on mobile devices.

Synapse Enterprise Viewer is not to be used for primary mammography diagnosis.

The Synapse Enterprise Viewer Software Version 1.0 (Hereafter referred to as Synapse EV), the subject of this Premarket Notification Submission, is intended for communication, storage, display, manipulation, measurement, printing, and processing of radiological data including images, reports, patient status and clinical information acquired from various medical imaging and information systems. This software device provides post processing of existing medical images; it does not control how the medical images are acquired.

Synapse EV is a multipurpose, enterprise wide application used for Radiologist interpretation, in-house clinical review, and physician image and information access. It is a web-based, zero-download viewer that uses Internet technology at the foundation of its design. This design allows for a user interface that takes advantage of familiar functions of modern browsers and can be used as a web application on a PC or Mobile device.

As a zero-download viewer application, Synapse is accessible by anyone connected to a Synapse web server via an intranet or the Internet over standard HTTP or a secure HTTPS (SSL) connection. Synapse users may be assigned different security levels to access patient and study folders. All tools are available to all users regardless of their physical location or health provider function.

Compatible with both Intranet and Internet network connections, an installed Synapse EV Software will typically be comprised of one or more Synapse EV Servers. As the client a standard browser is being used.

The provided text is a 510(k) summary for the FUJIFILM Synapse Enterprise Viewer Version 1.0. It aims to demonstrate substantial equivalence to a predicate device rather than providing a study proving specific performance metrics against defined acceptance criteria for a diagnostic medical device per se.

The document indicates that no clinical studies were required to support the safety and effectiveness of the software. Therefore, many of the requested details regarding acceptance criteria and a study proving those criteria are not applicable in this context. The submission focuses on software validation and verification to ensure the device performs as intended and is safe for its stated use as an image viewer.

Here's an analysis based on the provided text, addressing the points where information is available and noting where it is not:

1. A table of acceptance criteria and the reported device performance

No explicit "acceptance criteria" and "reported device performance" in the typical sense for a diagnostic medical device (e.g., sensitivity, specificity, AUC) are provided. This submission is for an image viewer, not an AI diagnostic algorithm. The acceptance criteria would primarily relate to software functionality, display accuracy, and adherence to standards.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Test Set Sample Size: Not explicitly stated. The text mentions "integration testing for all components" and "selected simulated workflow validation." This suggests a comprehensive test suite covering various functionalities, but a specific number of cases or images is not provided.
• Data Provenance: Not specified. Given it's a viewer for various radiological data, it would likely involve diverse image types and formats, but no origin or retrospective/prospective nature is detailed.

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)

Not applicable in the context of image viewer software validation. The text states:

• "Selected simulated workflow validation and new feature validation was performed by product owners who have comprehensive understanding of user requirements as well as clinical expertise to validate the design and behavior of the implemented features and functionality."
• "User Guide validation was performed by the test engineering team."

These individuals are verifying the software's functionality and adherence to requirements, not establishing a diagnostic ground truth for an AI algorithm.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

Not applicable. There is no mention of expert consensus or adjudication for diagnostic accuracy. The validation described is for software functionality.

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 such study was done or mentioned. The device is an enterprise image viewer, not an AI-assisted diagnostic tool.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

Not applicable. The device is a viewer, intended for human-in-the-loop review and analysis. It is not a standalone algorithm.

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)

Not applicable in the diagnostic sense. The "ground truth" for this software validation would be the functional specifications and requirements. The software is verified to correctly display, manipulate, and communicate medical images and data according to its design.

8. The sample size for the training set

Not applicable. The Synapse Enterprise Viewer is a traditional software application, not an AI/ML algorithm 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 device.

Ask a specific question about this device