(62 days)
The Stair Systems Constellation Suite Software system is a picture archiving and communications system (PACS) intended to be used as a networked Digital Imaging and Communications in Medicine (DICOM) and non- DICOM information and data management system. The STAIR System PACS & DICOM Viewer Software is comprised of modular software programs that run on standard "off-the-shelf" personal computers, business computers, and servers running standard operating systems. STAIR System & DICOM Viewer Software system is an image, data storage and display software that accepts DICOM data from any OEM modality which support DICOM standard imaging data: The system provides the capability to organize images generated by OEM vendor equipment, perform digital manipulation, create graphical representations of anatomical areas, and perform quantitative measurements.
The STAIR Systems Constellation Suite Software system should not be used for Diagnostic review of full-field digital mammograms.
STAIR Constellation Suite is a collection of applications Coded in the Microsoft C# application language. A color scheme defined as a way to identify both highlighted or important information within the user interface and as a "not so grey" environment that could stand up to a user who was likely to work 10-12 hours a day in front of it. The layout and design of the layers of the UI evolved from the "old design" of having 3 separate computers. each with a single monitor copy of a single element of the system into a modern, multimonitor native design which incorporates large performance gains through the use of Microsoft's DirectX technologies.
The core of the Suite is the database, is an adaptive star relational design for Microsoft SQL Server 2008 Enterprise. The data server provides a dedicated, central place to provide disaster recovery servicing, and the large multi-terabyte storage required for PACS. Attaching to this are Northstar PACS clients, Cosmos Enterprise Managmenet Clients, Apex Servers, and Cascade Servers; all of which are STAIR produced software products.
The Northstar PACS client is intended to be a desktop replacement product, with the interface dominating the screen space on a workstation.computer. TThis design decision was made to accommodate non- technical doctors who, we found, typically prefer to have a simplified and unobtrusive environment to work in. Color based exam status listings were evolutionary, and grew from the initial 'field of green' into the more advanced dynamic tree view seen today in the client. It is a multi-monitor capable client, currently configurable in a 1, 2, or 3 monitor footprint.
Cosmos represents the nerve center of the STAIR Constellation Suite, providing services for securing the STAIR network, maintaining Paperless workflow, and other such critical day-today system maintenance tasks. Typically users will include hospital or practice administrators and functional personnel who may need to make modifications to STAIR database entries. It is an OLTP client, and requires port level access to the main STAIR database central server installation to function (we use DSN-less connections to the database usually requiring port 1433 to be excepted in the workstation's firewall rule set). The client performs many tasks, some of which are not relevant to every customer. though we encourage adoption of STAIR electronic processes by our clients in order to help them streamline their office efficiency. RIS integration is partially available (per vendor, STAIR offers no supported HL7 interface at this time), and can be incorporated in most cases to allow a RIS system to perform synchronization and workflow tasks in harmony with STAIR kept data records.
The Apex DICOM Storage Server provides the primary server capabilities of the STAIR system. It was built to be automatable such that it typically runs unattended, but a user interface is used to both help monitor and control the various DICOM storage processes necessary to import each study from an external source (modality, another PACS, etc). The Apex server incorporates a DICOM SCP service grouping that allows for DICOM ping response, client protocol negotiation, transfer syntax negotiation, and several other system-level DICOM negotiations. As each case is received; it is stored via a Service host to the local hard drive (into the STAIRIMAGE hierarchy), it is queued for storage at the top, and it is stored as data to the main database in one of 8 available simultaneous thread 'putaway' processes (shown as 'idle').
The STAIR Cascade is a DICOM SCU, and auxiliary compression Server product originally designed to allow the send and receive functions of DICOM to be split from the STAIR Apex product and balanced onto a separate physical server. This was to allow for load balancing within the STAIR Enterprise, and the product has evolved now into a secondary server role, handling transmission queues for all enterprise clients. To allow for DICOM transmissions to be seamless, we use a database table XMISSION QUES, and each client transmission request to the database are handled as a threaded process (8 simultaneous). Each process begins by downloading the Imageset for a requested case from the STAIR database to a local cache, where it is then added to a queue within the program for processing. As each queue slot opens, another case is promoted until the queue empties.
Here's an analysis of the provided text regarding the Stair Systems Constellation Suite, focusing on the acceptance criteria and study information:
Based on the provided 510(k) Summary, there is no specific information detailing acceptance criteria for device performance or a study proving that the device meets such criteria.
The document primarily focuses on establishing "substantial equivalence" of the Stair Systems Constellation Suite to predicate devices, as required for a 510(k) premarket notification. This process typically relies on demonstrating that the new device has the same intended use, similar technological characteristics, and raises no new issues of safety or effectiveness compared to legally marketed devices.
Let's address each point of your request based on the available text:
-
A table of acceptance criteria and the reported device performance
- Not available in the provided text. The document does not define specific performance metrics or acceptance criteria for the device (e.g., image display accuracy, processing speed, measurement precision etc.)
-
Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not available. The document does not describe any specific test set of data used for performance evaluation, nor does it mention data provenance. The "verification and validation testing" mentioned in the Conclusion is a general statement, without details on the scope, methodology, or data used.
-
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 available. Since no specific test set or performance evaluation study is described, there's no mention of experts or ground truth establishment.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not available. No adjudication method is described.
-
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. There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study. This device is a PACS/DICOM viewer software, not an AI-assisted diagnostic tool.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable. This device is a PACS system designed for human interaction and image management/display. It's not an AI algorithm performing standalone diagnostic tasks. The closest equivalent would be its performance in managing and displaying images according to DICOM standards, but specific standalone performance metrics are not detailed.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Not available. As no specific performance study is detailed, no ground truth type is mentioned. The "Conclusions" state: "A comparison of the labelling, substantial equivalence table, and verification and validation testing has established that the device meets its intended use and design specifications." This indicates that the validation focused on compliance with design specifications and intended use, likely through functional testing and adherence to standards (like DICOM), rather than clinical "ground truth" performance in a diagnostic sense.
-
The sample size for the training set
- Not applicable. The device described is a PACS and DICOM viewer software, which is an infrastructure and display system, not a machine learning or AI model that requires a training set.
-
How the ground truth for the training set was established
- Not applicable. As it's not an AI/ML device, there's no training set or ground truth in that context.
§ 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).