(260 days)
The syngo Application Software is a medical software for real-time viewing, image manipulation, communication, and storage of medical images and data on exchange media. It is used for diagnostic image viewing and postprocessing and for viewing and postprocessing during interventional procedures.
The syngo Application Software can be deployed on independent hardware such as a stand-alone diagnostic review. postprocessing, and reporting workstation. It can also be configured within a network to send and receive DICOM data.
Furthermore, the syngo Application Software can be deployed on systems of the Siemens Angiography system family. It provides image guided solutions in the operating room, for image guided surgery, by image fusion and by navigation systems, image guided solutions in interventional cardiology and image guided solutions for interventional oncology, interventional radiology, and interventional neuroradiology.
The syngo Application Software can also be combined with fluoroscopy systems or radiographic systems.
The syngo Application Software can be configured with a variety of syngo or Windows-based software options, which are intended to assist the physician in diagnosis, treatment control. It includes commercially available postprocessing techniques and OEM options.
Procedures that can be performed include: minimally invasive surgical procedures and minimally invasive tumor treatment.
The "syngo Application Software" (VE30A) is medical diagnostic software for realtime viewing, diagnostic review, post-processing image manipulation, optimization, communication, reporting, and storage of medical images and data on exchange media. It provides image-quided solutions in the operating room, for image-guided surgery, by Image Fusion and by navigation systems, image-guided solutions in interventional cardiology and electrophysiology, and image-guided solutions for interventional oncology, interventional radiology, and interventional neuroradiology. It can be deployed with a variety of syngo or Windows-based software options, which are intended to assist the physician in the evaluation of digital radiographic examinations, including diagnosis and/or treatment planning.
Siemens "syngo Application Software" (VE30A) is designed to work with digital radiographic, fluoroscopic, interventional, and angiographic systems.
Based only on the provided text, here is an analysis of the acceptance criteria and the study that proves the device meets them:
Disclaimer: The provided document is a 510(k) summary for a software update. It focuses on demonstrating substantial equivalence to a predicate device rather than a comprehensive, de novo clinical study with detailed performance metrics against acceptance criteria for a novel AI algorithm. Therefore, much of the requested information (like specific AI performance metrics, MRMC studies, or detailed ground truth establishment for a large test set) is not present in this type of regulatory document. The "tests" described are primarily software verification and validation, and functional testing to ensure the new features perform as expected and do not introduce new safety issues.
Acceptance Criteria and Reported Device Performance
The document does not explicitly present a table of quantitative acceptance criteria for device performance (e.g., specific accuracy, sensitivity, specificity thresholds for an AI algorithm). Instead, the acceptance criteria are generally framed around software verification and validation, and functional performance of the new features to ensure they are "as safe and effective" as the predicate device.
Implicit Acceptance Criteria and Reported Performance:
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Adherence to "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 11, 2005) and "Off-The-Shelf Software Use in Medical Devices". | "Software documentation for a Moderate Level of Concern software... is also included as part of this submission." |
| Risk analysis completion, hazard identification, and implementation of risk control measures. | "The Risk analysis was completed, and risk control was implemented to mitigate identified hazards." |
| Software specifications met acceptance criteria. | "The testing results support that all the software specifications have met the acceptance criteria." |
| Software verification and validation demonstrate safety and effectiveness compared to the predicate device. | "All software validation data demonstrates that the Subject Device is as safe and effective when compared to the Predicate Device that is currently marketed for the same intended use. All test results met all acceptance criteria." "Software validation data demonstrates that the Subject Device is as safe and effective when compared to the Predicate Device." "All conducted test results passed. Software validation data demonstrates that the Subject Device is as safe and effective when compared to the Predicate Device." |
| New/updated functionalities (syngo Embolization Guidance for Radial Access, Configurable archive flags, Overlay Protect Mode, Manual 2D3D registration improvement) perform as expected without raising new safety/effectiveness issues. | "The updated syngo Embolization Guidance feature for Radial Access was tested for availability and basic flow to create and detect vessels." "Configurable archive flags, Overlay Protect Mode, and Manual 2D3D registration improvement completed workflow were tested." "Performance tests were conducted to test the functionality... These tests have been performed to assess the functionality of the Subject Device. The results of all conducted testing were found acceptable and do not raise any new issues of safety or effectiveness." |
| Human Factors Usability Validation shows no safety-relevant functions requiring summative usability validation. | "The Human Factor Usability Validation showed no safety-relevant functions that need to be validated with a summative usability validation according to the IEC and FDA Guidelines." "syngo Application Software" (VE30) is safe and effective for intended users, uses, and use environments through the design control verification and validation process. No further risk mitigations are necessary." |
| Conformance to cybersecurity requirements. | "Siemens conforms to the cybersecurity requirements by implementing a process of preventing unauthorized access, modifications, misuse, or denial of use, or the unauthorized use of information that is stored, accessed, or transferred from a medical device to an external recipient. Provided in this submission is a cybersecurity statement that considers IEC 80001-1:2010." |
| Compliance with relevant recognized standards (e.g., ISO, IEC, NEMA, AAMI, ANSI UL standards). | The document lists multiple standards (ISO 14971, ISO 15223-1, IEC 82304-1, IEC 62304, IEC 62366-1, IEC 80001-1, NEMA PS 3.1, ANSI UL 2900-1, ANSI UL 2900-2-1, AAMI TIR57) and states, "Siemens claims conformance to the following performance standards." |
Study Details:
-
Sample sizes used for the test set and data provenance:
- The document implies that "Bench Test Summaries" were conducted and "Software Verification and Validation" was performed, but it does not specify the sample size (e.g., number of images, patients, or cases) of the test set used for these evaluations.
- The document does not provide information on the country of origin of the data or whether it was retrospective or prospective. It only mentions compliance with standards and internal testing.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document does not specify the number or qualifications of experts used to establish "ground truth" for any test set. The testing described appears to be functional and software verification, not clinical performance against expert-defined ground truth in the traditional sense of a diagnostic AI study.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- The document does not mention any adjudication method for establishing ground truth for a test set. This type of detail is typical for studies evaluating diagnostic accuracy, which is not the primary focus of this software update K230955 submission as presented.
-
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 was done or reported in this document. The submission is for a software update to an existing device, focusing on functional performance and substantial equivalence, not a comparative clinical effectiveness study of an AI-assisted diagnostic tool.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The document describes "non-clinical performance testing" and software verification and validation. This type of testing would be considered "standalone" in the sense that the software's functionality is directly assessed (e.g., "The updated syngo Embolization Guidance feature for Radial Access was tested for availability and basic flow to create and detect vessels."). However, it is not a standalone diagnostic performance study in terms of an algorithm providing a diagnosis without human input. The device's purpose is "to assist the physician in the diagnosis, treatment planning, and treatment control."
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The document does not specify a type of ground truth in the context of diagnostic accuracy (e.g., pathology, outcomes data, expert consensus). The "ground truth" implicitly referred to is the expected functional behavior and correct output of the software features based on their design specifications, which are verified through various internal tests.
-
The sample size for the training set:
- The document does not mention a training set or its size. This is understandable as the submission is for a software update with specific functional enhancements, rather than the development and validation of a new machine learning algorithm.
-
How the ground truth for the training set was established:
- As no training set is mentioned, information on how its ground truth was established is not provided.
§ 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).