(30 days)
syngo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as position emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR), syngo.via MI workflows can perform harmonization of SUV (PET) across different PET systems or different PET reconstruction methods.
syngo.via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.
syngo.via MI Workflows is a multi-modality post-processing software only medical device, which is intended to be installed on common IT hardware. This hardware must fulfill the defined requirements. The hardware itself is not seen as part of the medical device.
The Siemens syngo.via platform (K191040) and the applications that reside on it are distributed via electronic medium. The Instructions for Use also delivered via electronic medium.
synqo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR).
syngo.via MI Workflows enable visualization of information that would otherwise have to be visually compared disjointedly. syngo.via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.
Scenium assists in the display and analysis of images within the MI Neurology workflow of syngo.via MI Workflows. This software enables visualization and appropriate rendering of multimodality data, providing a number of features which enable the user to process acquired image data.
Scenium consists of four workflows:
- Database Comparison
- -Striatal Analvsis
- -Cortical Analysis
- -Subtraction
The Scenium workflows are used to assist the clinician with the visual evaluation, assessment and quantification of pathologies, such as dementia (i.e., Alzheimer's), movement disorders (i.e., Parkinson's) and seizure analysis (i.e., Epilepsy),
syngo MBF is a software only product intended for visualization, assessment and quantification of medical images: specifically providing quantitative blood flow measurements of PET images. The software is launched from the OpenApps Framework within the MI Cardiology workflow within syngo.Via MI Workflows. The application supports dynamic Rubidium – PET and dynamic Ammonia – PET images. The application provides visualization and measurement tools, for qualitative and quantitative visualization and assessment of the input data. It provides automatic and manual tools to orient and segment the myocardium. The software calculates measurements of myocardial blood flow, and provides tools, such as a database comparison workflow, for the Clinician to assess these results.
The provided text describes modifications to the syngo.via MI Workflows software (specifically VB60A, Scenium VE40A, and syngo MBF VB30A versions) and asserts their substantial equivalence to a predicate device (syngo.via MI Workflows VB50A, Scenium VE30A, and syngo MBF VB20A, K201195). However, it does not contain a detailed description of acceptance criteria or a specific study proving the device meets those criteria in the typical sense of a clinical or performance validation study with quantitative metrics, expert adjudication, or MRMC data.
Instead, the document focuses on:
- Regulatory Compliance: Adherence to FDA regulations (21 CFR 892.2050, 21 CFR Part 807.87(h)), recognized standards (ISO 14971, EN ISO 13485, IEC 62304, NEMA PS 3.1-3.20, IEC 62366-1, ISO 15223-1), and cybersecurity guidelines.
- Functional Equivalence: Stating that the new features do not alter the existent technological characteristics or raise new issues of safety and effectiveness compared to the predicate device.
- Verification and Validation (V&V): A general statement that "Verification and Validation activities 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."
Without specific performance metrics and a detailed study design provided in the given text, it is not possible to fully populate all components of your request. I will extract what information is present and indicate where information is Not Provided (NP).
Acceptance Criteria and Device Performance (as inferred from the document)
The document broadly states that "All testing has met the predetermined acceptance values." However, it does not explicitly define these "predetermined acceptance values" in a quantitative table. The primary acceptance criteria appear to be substantial equivalence, functional correctness, and adherence to safety and quality standards.
| Acceptance Criteria (Inferred) | Reported Device Performance |
|---|---|
| Functional correctness of new features: | "functions work as designed" |
| - Updated syngo.CT LungCAD Integration | (Implied: Integrated correctly) |
| - Visualization of 4D data in all layouts | (Implied: Works as intended) |
| - FAST Ranges Enhancements | (Implied: Enhanced as intended) |
| - Auto Layout Improvements | (Implied: Improved as intended) |
| - Gaussian filtering of PET Data | (Implied: Works correctly) |
| - Interactive Spectral Imaging | (Implied: Works correctly) |
| - Usability Improvements | (Implied: Improved as intended) |
| - OpenApps framework for ISAs (Cedars, Corridor 4DM, syngo MBF) | (Implied: Framework supports ISAs) |
| - Spill-Over Factors (within syngo MBF) | (Implied: Implemented and works) |
| - Automatic window/level for each frame (within syngo MBF) | (Implied: Works correctly) |
| - Global Time Activity Curve (within syngo MBF) | (Implied: Works correctly) |
| - Calibrated I123-FP-CIT normal databases in Striatal Analysis | (Implied: Databases accurate and integrated) |
| Meet performance requirements and specifications | "performance requirements and specifications have been met" |
| Implement all hazard mitigations (ISO 14971) | "all hazard mitigations have been fully implemented" |
| Cybersecurity controls | "has specific cybersecurity controls to prevent unauthorized access, modifications, misuse or denial of use" |
| Compliance with relevant standards and regulations | "adheres to recognized and established industry standards," compliance with 21 CFR 820 |
| Not raise new issues of safety and effectiveness | "do not raise any new issues of safety and effectiveness as compared to the predicate device." |
Study Details:
-
Sample sizes used for the test set and the data provenance:
- Test Set Sample Size: NP (Not provided in the document. The document refers to "Verification and Validation activities" and "All testing" but does not specify the number of cases or datasets used for these tests.)
- Data Provenance: NP (Not provided. It is not stated where the data for testing originated from, e.g., country of origin, or if it was retrospective or prospective data.)
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: NP (Given the nature of the modifications described – mainly functional additions and improvements to existing workflows – it's unlikely a traditional "ground truth" for disease diagnosis was established for this specific submission beyond ensuring the software performs its intended technical functions. If expert review was part of the V&V, it is not detailed.)
- Qualifications of Experts: NP
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Adjudication Method: NP (This type of adjudication is typically for establishing diagnostic ground truth, which is not the focus of the described V&V for these software updates.)
-
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 document describes software workflow updates for viewing, manipulation, quantification, and analysis of medical images. It does not introduce an "AI" component intended to directly assist or change clinical decision-making in a way that would necessitate an MRMC study demonstrating improved human reader performance. The software is a tool for professionals, not an AI diagnostic assistant.
-
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Standalone Performance: The V&V activities would have included testing of the software's algorithms and functions in a standalone manner to ensure they work as designed and meet specifications. However, specific metrics (e.g., accuracy, sensitivity, specificity for automated tasks) are NP for any specific algorithm. The "syngo MBF" module, for instance, calculates quantitative blood flow measurements, and its accuracy would have been part of the V&V, but no specific performance statistics are provided.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Type of Ground Truth: For the nature of these software updates, the "ground truth" would likely be technical correctness and adherence to algorithmic specifications rather than clinical outcomes or pathology. For example, ensuring that a 4D visualization works as intended, or that quantitative measurements (e.g., SUV harmonization, blood flow measurements) are mathematically correct and consistent with reference values or established methodologies. Detailed information about exactly how this "ground truth" was established (e.g., through phantom studies, simulations, or comparison with established clinical software/manual calculations) is NP.
-
The sample size for the training set:
- Training Set Sample Size: NP. The document does not mention training sets, which implies that the updates are not based on a machine learning model that would require a distinct training phase. These are described as functional additions and improvements to existing software, not new AI/ML algorithms.
-
How the ground truth for the training set was established:
- Training Set Ground Truth: NP, as no specific training set for (ML/AI) models is implied.
§ 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).