Search Results

The vRad PACS with Mammography software is used with general purpose computing hardware which meets or exceeds minimum specifications. vRad PACS with Mammography is intended to receive, transmit, store, and display images for clinical purposes and is comprised of three components: Viewer, Storage, and Cache. The vRad PACS Viewer component is intended for installation on an off-the-shelf PC meeting or exceeding minimum specifications and networked with vRad PACS Storage component. The vRad PACS Viewer is intended to serve as the primary user interface for the processing of medical images for presentation on displays appropriate to the medical task being performed. The vRad PACS Viewer can process medical images from DICOM modalities such as X-ray radiography, X-ray computed tomography, magnetic resonance imaging, ultrasound, nuclear medicine, and images from other DICOM-compliant modalities. The vRad Storage component is intended to handle the DICOM protocol and store images as DICOM files to a location where they can be read by vRad PACS Cache and transmitted to radiologists' workstations for viewing by the vRad PACS Viewer.

vRad PACS with Mammography may be used for the display, manipulation, and interpretation of lossless compressed or non-compressed mammography images that have been received in the DICOM "For Presentation" format and displayed on a monitor that meets technical specifications reviewed and cleared by FDA.

vRad PACS with Mammography is a device which consists solely of software that allows electronic transmission of radiological patient images from one location to another. The device is capable of accepting, storing, digitally processing, and displaying medical images for the purposes of providing digital diagnostic image interpretation services by trained radiologists on PC workstations. The software provides functions for performing operations related to manipulation, enhancement, compression, and quantification of medical images.

vRad PACS with Mammography is a modified version of vRad PACS (K090649) that will now allow display of presentation-quality digital mammography images.

The provided text describes a PACS system (Picture Archiving and Communications System) with mammography capabilities, not an AI or CAD (Computer-Aided Detection) device. Therefore, the concept of "acceptance criteria" as it relates to statistical performance metrics (like sensitivity, specificity, AUC) for disease detection, or the effect size of AI assistance on human readers, is not directly applicable in the same way it would be for an AI-powered diagnostic tool.

This 510(k) submission is for a PACS system, which is essentially software for managing and displaying medical images. The "acceptance criteria" here are primarily functional, performance, and safety requirements to demonstrate that the device is substantially equivalent to a predicate device.

However, I can extract information related to the device's performance claims and the testing conducted, aligning it to the closest relevant categories from your request.

Here's a breakdown based on the provided document:

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

The document doesn't present a formal table of quantitative acceptance criteria with reported performance in the way an AI diagnostic device would (e.g., "Sensitivity > X%"). Instead, the acceptance criteria are implicitly met by successfully passing a comprehensive set of tests and showing substantial equivalence to the predicate device.

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 does not specify a "test set" in the context of a dataset of medical images used to evaluate diagnostic performance (like sensitivity/specificity for disease detection). The testing described is software verification and validation. Therefore, there's no mention of sample size for a clinical test set or data provenance in this context.

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. As this is not an AI/CAD diagnostic device, there's no mention of expert-established ground truth for a test set of medical images. The "ground truth" for the software's functionality would be its adherence to design specifications and user requirements.

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

Not applicable, for the same reasons as above.

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

Not applicable. This is not an AI-assisted device, and no MRMC study is mentioned. The device's purpose is to display, store, and transmit images, not to provide diagnostic assistance.

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

Not applicable. This is a PACS system, which is a tool for human radiologists. It does not perform diagnostic tasks independently.

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

Not applicable in the conventional sense of diagnostic performance for a disease. The "ground truth" for this device's testing relates to its correct functioning against design specifications and user requirements, not medical conditions.

8. The sample size for the training set

Not applicable. The vRad PACS with Mammography is not a machine learning model that requires a training set of data.

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

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device