(76 days)
The software comprising the syngo.MR post-processing applications is post-processing software/applications to be used for viewing and evaluating the designated images provided by a magnetic resonance diagnostic device. All of the software applications comprising the syngo.MR post-processing applications have their own indications for use.
syngo.MR General is a syngo based post-processing software for viewing, manipulating and evaluating MR images.
syngo.MR Cardiology is a syngo based post-processing software for viewing, manipulating and evaluating MR cardiac images.
syngo.MR Neurology is a syngo based post-processing software for viewing, manipulating, and evaluating MR neurological images.
The syngo.MR post-processing applications are synqo based post-processing software/applications to be used for viewing and evaluating' MR images provided by a magnetic resonance diagnostic device and enabling structured evaluation of MR images.
With SMRVB20 there are some new features, improvements and changes within the syngo.MR post-processing applications.
Within syngo.MR General VB20 there are the following new features and improvements:
- Arithmetic tools (new): Addition, Division, Multiplication
- Motion Correction (Elastic) (new): A Motion Correction algorithm can ● be used to perform elastic motion correction for angiography series (pre/post) or within 4D Breast datasets.
- MR Combine feature (new): Composing is also available for axial series. ●
- MR Prostate workflow provides PI-RADS™ v2 reporting (improved) ●
- Harmonized MR Basic workflow (improved): Several basic workflows . for routine reading are consolidated in one MR Basic workflow.
- . MR Neurology workflow: The MR Neurology workflow merges the already cleared workflows of MR Head, MR Neuro Perfusion, and MR Neuro Dynamics.
- Easy Reading Layout in all workflows (improved): All workflows now include a viewing step with Easy Reading Layout.
- Improved result management (improved): Multiple export options for . findings in the interactive Findings details dialog
Within syngo.MR Cardiology VB20 there are the following new features and improvements:
- Volume Quantification Tool (new): Volume Quant provides the . capability to evaluate lesion volumes in the myocardium.
- . Improved Result Distribution (improvement): Segmentation images can be exported as a result series.
Within syngo.MR Neurology VB20 there are the following new features, changes and improvements:
- MR Neuro 3D workflow:
- Offline BOLD (new): offers the capability to run the GLM ● evaluations on raw BOLD data to generate fMRI statistical maps.
- . Offline DTI (new): offers the capability to generate TENSOR data together with all other diffusion maps (including b0. ADC. TraceW, FA, AD, RD) from raw diffusion series.
- DTI evaluation (new): offers quantitative evaluation of diffusion . parameters (FA, RD, AD, ADC, ...) using ROI, VOI, or voxels.
- . Neuro-specific Mean Curve Tool (minor improvement): The application svngo.MR Neuro Dynamics described in K151353 (and cleared August 07, 2015) is only available within syngo.MR Neuro Perfusion (neurospecific Mean Curve Tool), but no longer as a single application.
The syngo.MR Neuro Perfusion Engine Pro, described in K151353 (and cleared August 07, 2015), is therefore obsolete within SMRVB20, as all applications are already part of syngo.MR Neuro Perfusion Engine.
This document describes the safety and effectiveness information supporting the Siemens syngo.MR post-processing applications (syngo.MR General, syngo.MR Cardiology, syngo.MR Neurology), in the context of a 510(k) premarket notification (K163294). The focus is on demonstrating substantial equivalence to previously cleared predicate devices, rather than a standalone clinical study to establish new acceptance criteria. Therefore, several of the requested categories (e.g., sample size for test/training sets, number of experts for ground truth, adjudication method, MRMC study, effect size) are not explicitly described in the provided text because a formal clinical study to prove new performance claims was not performed and not required for a substantial equivalence claim.
The submission focuses on new features and improvements to existing functionalities and does not define new "acceptance criteria" in terms of specific performance metrics (e.g., sensitivity, specificity, AUC) that a new device would need to meet. Instead, acceptance is based on demonstrating that the new features do not raise new questions of safety or effectiveness and that the device as a whole maintains substantial equivalence to its predicate devices, which are already legally marketed.
Here's a breakdown of the requested information based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
As this is a substantial equivalence submission for an updated software version rather than a de novo device, specific granular acceptance criteria (e.g., performance metrics like sensitivity, specificity, accuracy) are not defined in the document. The "acceptance criteria" are implicitly met by demonstrating that the new features conform to established safety and performance standards, and that the device's intended use and technological characteristics remain substantially equivalent to its predicate devices.
Acceptance Criteria (Implicitly based on Substantial Equivalence):
- Device functions as intended for viewing, manipulating, and evaluating MR images.
- New features do not introduce new questions of safety or effectiveness.
- Device adheres to relevant industry standards (ISO 14971, IEC 62366-1, IEC 62304, NEMA DICOM).
- Device maintains the same intended use as predicate devices.
Reported Device Performance (Implicit from Features and Conformity):
| Feature/Area | Reported Status/Performance (Implicit) |
|---|---|
| syngo.MR General (new/improved features) | |
| Arithmetic tools | New functionality for Addition, Division, Multiplication. Expected to be accurate for image manipulation. |
| Motion Correction (Elastic) | New capability for elastic motion correction in angiography and 4D Breast datasets. Expected to provide effective motion correction. |
| MR Combine feature (Composing for axial series) | New functionality. Expected to integrate axial series effectively. |
| MR Prostate workflow (PI-RADS™ v2 reporting) | Improved. Expected to facilitate standardized prostate MRI reporting. |
| Harmonized MR Basic workflow | Improved consolidated basic workflows for routine reading. Expected to streamline workflow. |
| MR Neurology workflow | Merges existing cleared workflows (MR Head, MR Neuro Perfusion, MR Neuro Dynamics). Expected to provide a unified, comprehensive neurological workflow. |
| Easy Reading Layout | Improved across all workflows. Expected to enhance user experience. |
| Improved result management | Multiple export options for findings. Expected to improve data handling and sharing. |
| syngo.MR Cardiology (new/improved features) | |
| Volume Quantification Tool | New tool for evaluating lesion volumes in the myocardium. Expected to provide accurate volumetric measurements. |
| Improved Result Distribution | Segmentation images can be exported as result series. Expected to improve data utility. |
| syngo.MR Neurology (new/improved features) | |
| Offline BOLD | New capability to run GLM evaluations on raw BOLD data for fMRI statistical maps. Expected to generate robust functional MR maps. |
| Offline DTI | New capability to generate TENSOR data and other diffusion maps from raw diffusion series. Expected to provide comprehensive DTI analysis. |
| DTI evaluation | New quantitative evaluation of diffusion parameters (FA, RD, AD, ADC, etc.) using ROI/VOI/voxels. Expected to provide accurate quantitative DTI metrics. |
| Neuro-specific Mean Curve Tool | Minor improvement, integrated into syngo.MR Neuro Perfusion. Expected to maintain functionality for mean curve analysis. |
| General Safety and Effectiveness | Labeling contains instructions, cautions, and warnings for safe use. Risk Management complies with ISO 14971:2007. Adherence to recognized industry standards (AAMI ANSI IEC 62366-1, ISO 14971, AAMI ANSI IEC 62304, NEMA DICOM PS 3.1-3.20). Operators are healthcare professionals. Device is substantially equivalent to predicate devices (K130749, K151353, K153343, K150843). |
2. Sample size used for the test set and the data provenance
The document does not describe specific test sets, sample sizes, or data provenance (e.g., country of origin, retrospective/prospective) for a clinical performance study. The evaluation focused on non-clinical data (software verification and validation, risk management, adherence to standards) to support the substantial equivalence claim for the updated software.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable, as no formal clinical test set requiring expert-established ground truth for performance metrics is described in this submission. The validation relies on demonstrating technical performance and equivalence to cleared predicate devices.
4. Adjudication method for the test set
Not applicable, as no formal clinical test set with an adjudication process is described in this submission.
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
Not applicable. This submission is for an update to a post-processing software that provides tools for clinicians, not an AI-assisted diagnostic tool that would typically undergo an MRMC study to show human reader improvement. The document does not describe AI components or MRMC studies.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document does not explicitly describe a standalone performance study for the algorithms. The "device" itself is software for viewing, manipulating, and evaluating MR images, serving as a tool for clinicians. The focus is on the software's ability to provide these functions accurately and safely as an aid to a human reader, implying a human-in-the-loop interaction for diagnostic purposes.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Not explicitly described in terms of a clinical ground truth for a performance study. The validation relies on technical verification and validation, ensuring the software performs its intended functions correctly and reliably, and that its outputs (e.g., measurements, processed images) are accurate based on engineering specifications and comparison against predicate device capabilities.
8. The sample size for the training set
Not applicable. This document describes an update to post-processing software, not a machine learning or AI model that would typically require a training set. The new features mentioned (e.g., arithmetic tools, motion correction, DTI evaluation) are standard image processing and analysis algorithms rather than models requiring large training datasets.
9. How the ground truth for the training set was established
Not applicable, as no training set for a machine learning model is mentioned.
Summary of Approach:
This 510(k) submission for the syngo.MR post-processing applications focuses on demonstrating substantial equivalence to predicate devices for an updated software version. The "study" proving the device meets its (implicit) acceptance criteria relies on:
- Detailed descriptions of new features and improvements.
- Verification and validation activities to ensure these features function as intended and do not introduce new safety or effectiveness concerns.
- Adherence to recognized industry standards (ISO 14971 for risk management, IEC 62366-1 for usability, IEC 62304 for software life cycle, NEMA DICOM for imaging communication).
- A comparison of intended use and technological characteristics with legally marketed predicate devices (K130749, K151353, K153343, K150843) to affirm that the fundamental equivalence remains.
The absence of specific clinical performance study details (e.g., test set sizes, expert reviews, MRMC studies) is consistent with a 510(k) pathway for software updates that are considered substantially equivalent to existing devices and do not introduce entirely new diagnostic capabilities requiring extensive clinical validation.
§ 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).