Search Results

Vision Series PACS 5.5 is designed and marketed for soft copy reading, communication and storage of studies produced by digital modalities, to include Digital Mammography. Vision Series PACS receives images acquired from DICOM-compliant medical imaging systems, data from FDA-cleared Computer-Aided Detection systems and other FDA-cleared Image processing systems.

Vision Series PACS imports images and render said images, upon request, within the AMICAS LightBeam Diagnostic Workstation utilizing both lossless (reversible) and lossy (irreversible) compression.

To support the diagnostic interpretation of Mammography studies, Vision Series PACS will display the full fidelity DICOM image in a non-compressed format. Images will be rendered with patient and clinical information clearly displayed as part of the DICOM Overlay as required by MQSA, on monitors cleared by FDA for use in Digital Mammography. Lossy compressed mammography images and digitized film screen images should not be used for the purpose of primary diagnosis. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5Mpixel resolution and meets other technical specifications reviewed and accepted by FDA.

Within Vision Series PACS 5.5, the AMICAS Real Time Worklist offers real-time status of radiology activity and provides customizable workflow management capabilities. Communication of critical results is facilitated and documented through optional, and configurable, components within the Real Time Worklist.

Vision Reach is an optional component within the PACS 5.5 offering which provides clinicians secure, proactive communication and access to clinical reports and images.

Order and Report information generated by HIS/RIS and report creation systems are received and displayed in PACS via the transmission of HL7 messaging. For this data. AMICAS is not the creator, but instead the downstream recipient which relies on the validity of data from said systems.

Vision Series PACS must be installed on suitable, commercial-standard hardware. It is the user's responsibility to ensure monitor quality, ambient light conditions and image compression ratios are consistent with the clinical application.

AMICAS Vision Series PACS 5.5 is software intended to create and display twodimensional and three-dimensional images of anatomy from a series of digitally acquired images.

The provided text is a 510(k) summary for the AMICAS Vision Series PACS 5.5. It focuses on demonstrating substantial equivalence to a predicate device (AMICAS Vision Series PACS 4.3) rather than detailing specific acceptance criteria and a study to prove meeting those criteria. The submission primarily highlights feature comparisons and general safety considerations.

Therefore, much of the requested information cannot be extracted from this document, as the submission does not include a detailed performance study with specific acceptance criteria as would be found in a clinical trial or performance evaluation for a novel AI device.

Here's a breakdown of what can and cannot be answered based on the provided text:

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

The document does not explicitly define acceptance criteria as typically seen for novel device performance (e.g., sensitivity, specificity thresholds). Instead, it presents a comparison of features between the new device and its predicate to demonstrate substantial equivalence.

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

This information is not provided in the document. The filing mentions "Functional testing is an integral part of Amicas, Inc. Product Development process" and "Amicas Vision Series 5.5 is tested with reference to its Software Requirements Specifications," but gives no details about specific test sets, sample sizes, or data provenance.

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 in the document. The document refers to "trained and qualified professionals" (radiologists, technologists, and clinicians) as typical users, but not as experts establishing ground truth for testing.

4. Adjudication method (e.g. 2+1, 3+1, none) 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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted or reported for this submission. The device is a Picture Archiving Communication System (PACS), not an AI-assisted diagnostic tool for which such a study would typically be performed to measure reader improvement. The document mentions "data from FDA-cleared Computer-Aided Detection systems and other FDA-cleared Image processing systems" can be received, but the PACS itself is not presented as an AI-powered diagnostic tool.

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

This information is not applicable/not provided. The device is a PACS, which is an imaging display and management system that always involves a human-in-the-loop for interpretation and diagnosis. It's not a standalone algorithm performing a diagnostic task.

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

This information is not provided in the document. Given the nature of a PACS system, testing would likely focus on functionality, image integrity, and display accuracy, rather than clinical diagnostic ground truth as in a disease detection algorithm.

8. The sample size for the training set

This information is not applicable/not provided. The device is a software system (PACS) for image management and display, not an AI or machine learning algorithm that requires a training set.

9. How the ground truth for the training set was established

This information is not applicable/not provided. As explained above, the device is not an AI/ML algorithm requiring a training set.

Ask a specific question about this device