(21 days)
Visage PACS is a system for distributing, viewing, and processing medical images and reports within and outside health care environments. It is to be used only by trained and instructed health care professionals. Visage PACS consists of the following components:
Visage PACS Storage: Visage PACS Storage offers an archiving option for long-term storage of image data.
Visage PACS Web: Data that are stored on the Visage PACS Storage server can be accessed simultaneously by multiple web-based viewing stations within or outside a healthcare enterprise through web clients.
Visage CS: Visage CS is a client server system that uses thin client technology for distribution of 3D image data generated from image data of state-of-the-art scanning modalities.
Integration with other hospital information systems (HIS, RIS, CIS) is provided via special interfaces.
Only DICOM for presentation images can be used on an FDA approved monitor for mammography for primary image diagnosis. Only uncompressed or non-lossy compressed images must be used for primary image diagnosis in mammography.
Visage PACS is a system to distribute, view, and process medical images and reports within and outside of health care environments. It consists of the following components:
- Visage PACS Storage 1
- -Visage PACS Web
- Visage CS -
Visage PACS Storage: A server receives image data in DICOM format via the hospital network. This provides universal connections to archives, modalities and workstations. The modalities that are supported by Visage PACS Storage are listed in the DICOM Conformance Statement. Visage PACS Storage offers an archiving option for long-term storage of image data.
Visage PACS Web: Data that are stored on the Visage PACS Storage server can be accessed simultaneously by multiple web-based viewing stations within a healthcare enterprise or from elsewhere outside through web clients. The image data transfer is done in DICOM format via the Intranet or the Internet. Images can be viewed directly within a web browser (Internet Explorer). The system offers simple functions for image manipulation and measurements. Reports can be viewed together with the images on one page.
Visage CS: Visage CS is a client server system that uses thin client technology for distribution of 3D image data generated from image data of state-of-the-art scanning modalities. The thin client viewer allows to view and process 3D image data. No DICOM data is transferred to the client. Instead of image data, a stream of compressed screen content information is transmitted during interaction.
Modification: Implementation of the cardiac analysis option. With the new version of the software the user can import cardiac CT time series in order to utilize them for the LV analysis (analysis of the left ventricle). The LV analysis tool card helps with the analysis of the left ventricle in cardiac CT time series. This toolcard quides the user through an LV analysis step by step. The LV tools support the physician in finding the left ventricle in the image data. The LV tool card supports the user to find and display the long and short axes of the left ventricle and to segment the left ventricle. It supports the user to calculate the total volume of the left ventricle over one heart cycle, the stroke volume and the ejection fraction of the various LV regions and the accumulated wall motion.
The provided 510(k) summary for K072205 (VISAGE PACS/CS 5.0) focuses on demonstrating substantial equivalence to a predicate device (AquariusNet Server/Thin client K012086) for its new cardiac analysis and other imaging features. It does not contain a detailed study with acceptance criteria and reported performance metrics in the format typically used for AI/ML device evaluations.
Instead, the submission emphasizes validation and effectiveness through a risk analysis, risk management plan, and software development process, stating that "hazard analysis, verification and validation tests (according to our software development process) and evaluations by hospitals" have been performed. However, specific quantitative acceptance criteria or detailed study results with sample sizes, expert qualifications, or ground truth methodologies are not included in the provided text.
The closest information provided related to "acceptance criteria" and "reported performance" is in the Substantial Equivalence Comparison Chart, which indicates the presence or absence of certain features in the new device and the predicate device. This is a functional comparison, not a performance study in the sense of accuracy, sensitivity, or specificity.
Given the information provided, here's what can be extracted and what is missing:
1. Table of Acceptance Criteria and Reported Device Performance
No specific quantitative acceptance criteria or reported performance metrics (e.g., sensitivity, specificity, accuracy) are provided in the document. The comparison chart below shows feature equivalence, not performance against specific clinical thresholds.
| Feature | Acceptance Criteria (Not explicitly stated as numeric) | Reported Device Performance (Presence of feature) |
|---|---|---|
| Volume measurements | Functional capability as in predicate | Yes |
| Semi-automatic coronary artery segmentation | Functional capability as in predicate | Yes |
| Coronary artery navigation and measurement | Functional capability as in predicate | Yes |
| Functional analysis of the left ventricle | Functional capability as in predicate | Yes |
| Vessel segmentation tool with increased specificity and improved performance | Functional capability as in predicate | Yes |
| Fusion and side-by-side registration as separate concepts | Functional capability as in predicate | Yes |
| Pixel probing support in fusion mode | Functional capability as in predicate | Yes |
| Change of algorithm for curved slices | Functional capability as in predicate | Yes |
| Automatic generation of thick slices | Functional capability as in predicate | Yes |
| Improved bone removal for CT runoff studies | Functional capability as in predicate | Yes |
| Changed curved planar reformat (CPR) viewer | Functional capability as in predicate | Yes |
| Changed lumen view | Functional capability as in predicate | Yes |
| 4D cardiac CT data support | Functional capability as in predicate | Yes |
| Automatic short/long axis view | Functional capability as in predicate | Yes |
| Semi-automatic segmentation of left ventricle and coronary artery | Functional capability as in predicate | Yes |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The provided document does not specify the sample size used for any test set or the data provenance for validation. It mentions "evaluations by hospitals" in a general sense but no details are given.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The provided document does not specify the number or qualifications of experts used to establish ground truth for any test set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The provided document does not describe any adjudication method for a test set.
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 comparative effectiveness study is mentioned or detailed in the provided 510(k) summary. This submission predates the common requirement for such studies for many AI/ML devices.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device, VISAGE PACS/CS, is a Picture Archiving and Communications System (PACS) with advanced visualization and analysis tools. Its description states: "A physician, providing ample opportunity for competent human interprets images and information delivered by VISAGE PACS/CS." This indicates that the device is intended for human-in-the-loop use. A standalone algorithm-only performance study is not described or implied. The focus is on providing tools to assist a human interpreter.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The provided document does not specify the type of ground truth used for any evaluations.
8. The sample size for the training set
The provided document does not specify details about a training set or its sample size. This is typical for submissions preceding the specific requirements for AI/ML device training data.
9. How the ground truth for the training set was established
The provided document does not specify how ground truth for a training set was established, as it does not explicitly mention a training set.
§ 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).