(69 days)
The Perfusion Package for MAGNETOM Vision and Symphony MR Systems is a software package which allows the display of temporal variations in dynamic MR Datasets, showing changes in contrast over time. Its purpose is to provide either time intensity curves or the creation of parametric images for parameters like time to peak that support the diagnostic process. These images when interpreted by a trained physician, yield information that may assist in diagnosis. One clinical application where this could be useful is the diagnosis of lesions by temporal analysis of tumor enhancement.
The Perfusion Package is a post processing option for the MAGNETOM VISION and SYMPHONY MR system.
The provided 510(k) summary for the Siemens Perfusion Package for Magnetom Vision and Symphony MR systems does not contain the detailed information requested regarding specific acceptance criteria, a quantitative study proving it meets those criteria, or a comparative effectiveness study.
Instead, the submission focuses on demonstrating substantial equivalence to existing devices and assuring that the new software package does not raise new questions of safety and effectiveness compared to the standard operation of the base MR system.
Here's an breakdown of what can be extracted or inferred, and what is explicitly missing based on the provided document:
Extracted/Inferred Information:
The core "acceptance criteria" here are implied by the FDA's substantial equivalence pathway, meaning the device must be as safe and effective as a legally marketed predicate device. The document explicitly states that the technological differences (the Perfusion Package) do not raise any new safety or effectiveness concerns.
1. A table of acceptance criteria and the reported device performance:
| Acceptance Criteria (Implied by Substantial Equivalence) | Reported Device Performance |
|---|---|
| Safety: | |
| - Maximum Static Field unaffected | - Unaffected |
| - Rate of Change of Magnetic Field unaffected | - Unaffected |
| - RF Power Deposition unaffected | - Unaffected |
| - Acoustic Noise Levels unaffected | - Unaffected |
| - Specification Volume unaffected | - Unaffected |
| Performance (Imaging): | |
| - Signal to Noise unaffected | - Unaffected |
| - Image Uniformity unaffected | - Unaffected |
| - Geometric Distortion unaffected | - Unaffected |
| - Slice Profile, Thickness and Gap unaffected | - Unaffected |
| - High Contrast Spatial Resolution unaffected | - Unaffected |
| Clinical Efficacy (Qualitative): | |
| - Provides time intensity curves to support diagnosis | - Product provides this feature |
| - Creates parametric images (e.g., time to peak) to support diagnosis | - Product provides this feature |
| - Assists in diagnosis of lesions by temporal analysis of tumor enhancement when interpreted by a trained physician | - Intended use claims this assistance |
| No New Safety/Effectiveness Questions | - Laboratory and clinical testing were performed to support this claim |
2. Sample size used for the test set and the data provenance:
- Not specified. The document mentions "Laboratory and clinical testing were performed," but provides no details on sample size, data origin (country), or whether it was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not specified. "Trained physician" is mentioned in the intended use, but there's no information on expert involvement in testing or ground truth establishment.
4. Adjudication method for the test set:
- Not specified.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:
- Not specified. There is no mention of an MRMC study or any comparison of human readers with vs. without AI assistance. The focus is on the software being equivalent to the standard operation of the MR system, not on improving human reader performance.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Partially addressed. The device is a "post processing option" and its "purpose is to provide either time intensity curves or the creation of parametric images...These images when interpreted by a trained physician, yield information that may assist in diagnosis." This implies it's an algorithm-only output that a human then interprets, rather than an AI assisting in real-time reading. However, the performance metrics are related to the MR system's underlying capabilities, not specific diagnostic accuracy of the generated curves/images.
7. The type of ground truth used:
- Not specified. The document implies the "ground truth" is primarily based on the functional equivalence of the MR system with and without the software package, as well as the qualitative ability to generate time-intensity curves and parametric images for interpretation by a physician. There's no mention of specific clinical ground truth (e.g., pathology, outcomes data) beyond supporting the diagnostic process.
8. The sample size for the training set:
- Not applicable / Not specified. This appears to be more of a post-processing software package applied to existing MR data rather than a machine learning model that requires a dedicated "training set" in the modern sense. If there was an ML component, its training data details are not provided.
9. How the ground truth for the training set was established:
- Not applicable / Not specified. (See point 8)
Conclusion:
This 510(k) summary, typical for its era (1999), focuses on demonstrating substantial equivalence by asserting that the Perfusion Package does not alter the fundamental safety and established performance of the Siemens MAGNETOM Vision and Symphony MR systems. It does not provide the kind of detailed quantitative performance study, sample sizes, expert qualifications, or ground truth methodologies that are common in submissions for AI/ML-based medical devices today. The "acceptance criteria" are predominantly those associated with maintaining the safety and performance standards of the base MR imaging system rather than a new diagnostic claim in itself.
§ 892.1000 Magnetic resonance diagnostic device.
(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.