(25 days)
syngo.via WebViewer is intended to be a software-only solution for reviewing medical images from syngo.via. The system cannot be used as stand-alone device. It is intended to be an option for syngo.via system only. syngo.via WebViewer is not intended for storage or distribution of medical images from one medical device to another. syngo.via WebViewer is a client server architecture and the client is intended to run on web clients which are connected to the healthcare institution IT infrastructure where the customer has to ensure HIPPA compliance. syngo.via WebViewer supports interpretation and evaluation of examinations within healthcare institutions, for example, in Radiology, Nuclear Medicine and Cardiology environments. The communication of syngo.via WebViewer with connected medical IT systems will be done via standard interfaces such as but not limited to DICOM. The system is not intended for the displaying of digital mammography images for diagnosis in the U.S.
This premarket notification covers Siemens ' PACS syngo.via WebViewer. syngo.via WebViewer is intended to be a software-only solution for reviewing medical images from syngo.via. The system cannot be used as stand-alone device. It is intended to be an option for syngo via system only. syngo. via Web Viewer is not intended for storage or distribution of medical images from one medical device to another. syngo.via WebViewer is a client server architecture and the client is intended to run on web clients which are connected to the healthcare institution IT infrastructure where the customer has to ensure HIPPA compliance. syngo. via Web Viewer supports interpretation and evaluation of examinations within healthcare institutions, for example, in Radiology, Nuclear Medicine and Cardiology environments. The communication of syngo.via WebViewer with connected medical IT systems will be done via standard interfaces such as but not limited to DICOM. The system is not intended for the displaying of digital mammography images for diagnosis in the U.S. The system is a software only medical device. It defines minimum requirements to the hardware it runs on. The hardware itself is not seen as a medical device and not in the scope of this 510(k) submission. It supports the physician in diagnosis and treatment planning.
The provided text is a 510(k) Summary for the Siemens syngo.via WebViewer. This document describes the device, its intended use, and its substantial equivalence to predicate devices. However, this document does not contain explicit acceptance criteria or a study demonstrating that the device meets such criteria.
The 510(k) submission process for a Picture Archiving and Communications System (PACS) like syngo.via WebViewer primarily focuses on establishing substantial equivalence to existing legally marketed devices, rather than conducting new clinical trials with specific statistical performance metrics and acceptance criteria as might be expected for an AI-powered diagnostic device.
Here's a breakdown of why the requested information is largely absent based solely on the provided text, and what could be inferred or is generally understood for this type of device:
1. A table of acceptance criteria and the reported device performance
- Acceptance Criteria: Not explicitly stated in the document. For a PACS viewer, acceptance criteria would typically revolve around functional performance (e.g., image display accuracy, speed, compliance with DICOM standards, user interface usability, data integrity, security).
- Reported Device Performance: Not quantitively reported in the document. The document affirms that the device "passed all necessary verification and validation steps to demonstrate safety and effectiveness" and "does not introduce any new significant potential safety risks and is substantially equivalent to and performs as well as the predicate devices." This is a qualitative statement of performance relative to predicates rather than a measured performance against specific criteria.
2. Sample sized used for the test set and the data provenance
- Test Set Sample Size: Not specified. Validation for a PACS viewer typically involves testing against various types of DICOM images and objects (CT, MR, SC, PDF) to ensure correct display and functionality. The "sample" here would be representative medical images, but the document doesn't quantify how many were used.
- Data Provenance: Not specified. It's implied that various types of DICOM images would be used for testing, but their origin (country, retrospective/prospective) is not detailed.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Ground Truth Experts: Not applicable or specified. For a PACS viewer, "ground truth" isn't generally established by experts in the same way it would be for a diagnostic AI algorithm. The viewer's "ground truth" is adherence to DICOM standards for image display and manipulation, and the successful execution of its functions. The verification and validation would be conducted by software testers and engineers, likely with medical domain knowledge.
4. Adjudication method for the test set
- Adjudication Method: Not applicable or specified. Again, for a PACS viewer, the "test set" isn't typically adjudicated like an AI diagnostic outcome. Functional and performance testing would involve objective checks against specifications and industry standards.
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
- MRMC Study: No. The syngo.via WebViewer is a medical image viewing and management system, not an AI-assisted diagnostic tool designed to improve human reader performance. Therefore, an MRMC study and
"effect size of how much human readers improve with AI vs without AI assistance" are not relevant to this device as described.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Not applicable as a diagnostic algorithm. The device itself is described as a "software-only solution for reviewing medical images" and "cannot be used as stand-alone device" meaning it requires the syngo.via system to function. It functions as a standalone software component (algorithm only in its specified role), but its "performance" is in displaying images and managing data, not making diagnoses without a human.
7. The type of ground truth used
- Type of Ground Truth: Not applicable in the traditional sense of a diagnostic device (e.g., pathology, outcomes data). The "ground truth" for a PACS viewer essentially refers to the correct and accurate display of DICOM images as per specifications and standards, and the proper functioning of its features (e.g., measurements, windowing). This is verified through comparison against known correct outputs or adherence to technical specifications.
8. The sample size for the training set
- Training Set Sample Size: Not applicable. The syngo.via WebViewer is not described as an AI/ML device that requires a "training set" in the context of machine learning model development. It's a traditional software application.
9. How the ground truth for the training set was established
- Ground Truth for Training Set: Not applicable, as there is no "training set."
Summary based on the provided document:
The 510(k) summary focuses on demonstrating the substantial equivalence of the syngo.via WebViewer to previously cleared predicate devices (Siemens syngo.x and Siemens InSpace 4D). It highlights similarities in intended use, technological characteristics (image communication, processing, supported image types, user interface, hardware), and adherence to relevant industry standards (IEC 62304 for software lifecycle, ISO 14971 for risk management, IEC 60601-1-1-6 for usability, DICOM, HL7, JPEG, JPEG2000 for communication and compression).
The "study" referenced implicitly is the verification and validation activities performed during the device's development cycle, which are stated to be compliant with QSR design processes, IEC 62304, ISO 14971, and IEC 60601-1-1-6. These activities would have ensured that the software functions as intended and meets its specifications, including accurate rendering of medical images and adherence to interface standards. However, direct evidence of specific acceptance criteria met through a formal study with statistical outcomes is not part of this 510(k) summary.
§ 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).