(50 days)
syngo.via MI Workflows are medical diagnostic applications for viewing, manipulation, 3Dvisualization and comparison of medical images from multiple imaging modalities and/or multiple time-points. The application supports functional data, such as PET or SPECT as well as anatomical datasets, such as CT or MR.
syngo.via MI Workflows enable visualization of information that would otherwise have to be visually compared disjointedly. syngo.via MI Workflows provide analytical tools to help the user assess, and document changes in morphological or functional activity at diagnostic and therapy follow-up examinations. syngo.via MI Workflows can perform harmonization of SUV (PET) across different PET systems or different reconstruction methods.
syngo via MI workflows support the interpretation and evaluation and follow up documentation of findings within healthcare institutions, for example, in Radiology, Nuclear Medicine and Cardiology environments.
Note: The clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard practices and visual comparison of the separate unregistered images. syngo.via MI Workflows are a complement to these standard procedures.
The syngo.via MI Workflows are software only medical devices which will be delivered on CD-ROM / DVD to be installed onto the commercially available Siemens syngo.via software platform by trained service personnel.
syngo.via MI Workflows is a medical diagnostic application for viewing, manipulation, 3Dvisualization and comparison of medical images from multiple imaqinq modalities and/or multiple time-points. The application supports functional data, such as PET or SPECT as well as anatomical datasets, such as CT or MR. The images can be viewed in a number of output formats including MIP and volume rendering.
syngo.via MI Workflows enable visualization of information that would otherwise have to be visually compared disiointedly. syngo.via MI Workflows provide analytical tools to help the user assess, and document changes in morphological or functional activity at diagnostic and therapy follow-up examinations. They additionally support the interpretation and evaluation of examinations and follow up documentation of findings within healthcare institutions, for example, in Radiology (Oncology), Nuclear Medicine and Cardiology environments.
The modifications to the syngo.via MI Workflows (K133644) include the following new features:
syngo.MM Oncology
- Color-coded seqmentations on VRTs indicating the rate of growth or shrinkage
- . Support for additional annotation information that allows the user to adhere to the QIBA protocol for lung nodule assessment
- Acquisition Bundles for consistent and intuitive management of data sets
- Addition of RT Nudge Tool for GTV editing o
- OncoBoard for reviewing studies in multi-disciplinary teams
- Rapid Result Technology automatically calculates and sends Lung CAD results as a o DICOM series within the workflow
syngo.MI Reading
- Further integration of MI Reading with the Cardiology and Neurology ● functionality including volume stripe view and neuro & cardio orientation display
- Snap-back functionality to help re-orientate volumes
syngo.MI Cardiology
- Implementation of display and manipulation of cardiac data in standard cardiac . views instead of using third party applications to do this
- Automatic cardiac reorientation
- o Support for the updated Corridor 4DM 2015, Cedars 2015, and CFR VB14 versions
syngo.MI Neurology
- Implementation of display and manipulation of brain data in standard brain views ●
- Automatic brain reorientation .
- Support for the latest version of Scenium VD20 .
Here's a breakdown of the acceptance criteria and study information for the syngo.via MI Workflows VB10A software, based on the provided text:
Important Note: The provided document is a 510(k) summary for a software update. It focuses on demonstrating substantial equivalence to a predicate device (syngo.via MI Workflows VA30A, K133644), rather than a full de novo clearance or a comprehensive clinical efficacy study. Therefore, detailed performance metrics, extensive study designs, and specific ground truth methodologies for new features are not fully elaborated in this type of document. The performance testing described is primarily focused on software verification and validation rather than clinical outcome studies.
1. Table of Acceptance Criteria and Reported Device Performance
The document describes performance testing as "Verification and Validation activities [that] have been successfully performed on the software package, including assurance that functions work as designed, performance requirements and specifications have been met, and that all hazard mitigations have been fully implemented. All testing has met the predetermined acceptance values."
However, the specific "acceptance criteria" and "reported device performance" in terms of clinical metrics (e.g., sensitivity, specificity, accuracy) are not explicitly detailed in the provided text for the new features. The performance testing is described at a high level, focusing on software quality assurance rather than clinical efficacy against a specific diagnostic task.
Acceptance Criteria (as implied from the text):
- Functions work as designed.
- Performance requirements and specifications have been met.
- All hazard mitigations have been fully implemented.
- "Predetermined acceptance values" for verification and validation (details not provided).
Reported Device Performance:
The document states that "All testing has met the predetermined acceptance values." However, it does not provide the specific numerical results of these tests or which predetermined acceptance values were used (e.g., minimum accuracy levels). This is typical for a 510(k) modification where substantial equivalence is claimed based on software changes that do not alter the fundamental technological characteristics or indications for use.
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify a "test set" in the context of a clinical study or specific number of cases/patients used for performance evaluation that would yield clinical metrics. The performance testing mentioned is about software verification and validation. Therefore, details regarding sample size, country of origin, or retrospective/prospective nature of a clinical test set are not available in this text.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
Similar to point 2, the document does not describe a clinical test set with ground truth established by experts. The performance testing is focused on software functionality rather than diagnostic accuracy involving human experts.
4. Adjudication Method for the Test Set
Since a clinical test set with expert ground truth is not described, an adjudication method is also not mentioned.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study is mentioned or reported in the provided text. The document focuses on the technical modifications and their verification/validation.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
The device is described as "medical diagnostic applications for viewing, manipulation, 3D-visualization and comparison of medical images" and "syngo.via MI Workflows provide analytical tools to help the user assess, and document changes." This clearly positions the device as an assistive tool for human users (clinicians) rather than a standalone AI algorithm providing a diagnosis without human interaction. The note specifically states: "The clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard practices and visual comparison of the separate unregistered images. syngo.via MI Workflows are a complement to these standard procedures." Therefore, a standalone performance study as an algorithm without human-in-the-loop is not relevant for this type of device and is not reported.
7. Type of Ground Truth Used
Given the nature of the software (viewing, manipulation, 3D-visualization, comparison, analytical tools), and the context of a 510(k) for an update, the "ground truth" for the software's functionality would likely involve:
- Engineering specifications and requirements: Ensuring that the software performs calculations correctly, displays data accurately, and that new features function as programmed.
- Reference data/simulations: For quantitative features (e.g., SUV harmonization), ground truth might involve comparing results against known correct values from validated algorithms or phantoms.
- Visual inspection by software testers/engineers: Confirming that visualizations are correct and consistent with input data.
There is no mention of clinical ground truth derived from expert consensus, pathology, or outcomes data for the new features of this software update. The general principle is that the "truth" is established by the underlying medical images interpreted by a clinician.
8. Sample Size for the Training Set
The document does not describe a "training set" in the context of machine learning or AI models. This device is primarily a visualization and analysis software, not explicitly described as containing deep learning or AI models requiring extensive training data in the context of this 510(k). The "Development" section refers to software development and risk management, but not machine learning model training.
9. How the Ground Truth for the Training Set Was Established
As no training set (for machine learning) is implicitly or explicitly mentioned, the method for establishing its ground truth is not applicable or described.
§ 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).