(125 days)
Your MAGNETOM system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and that displays the internal structure and/or function of the head, body, or extremittes. Other physical parameters derived from the images and or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These mages and or spectra and the physical parameters derived from the images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.
Your MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room displays and MR Safe biopsy needles.
MAGNETOM Vida with software syngo MR XA10A is similar to the previous cleared predicate device MAGNETOM Skyra with syngo MR E11C (K153343) but includes new and modified hardware and software compared to MAGNETOM Skyra.
Here's a breakdown of the acceptance criteria and study information for the MAGNETOM Vida device, based on the provided text:
Preamble: It's important to note that this document is a 510(k) summary for a premarket notification for a Class II medical device (Magnetic Resonance Diagnostic Device). The primary goal of a 510(k) submission is to demonstrate "substantial equivalence" to a legally marketed predicate device, not necessarily to prove absolute efficacy in a clinical setting in the same way a PMA (Premarket Approval) might require. Therefore, the "acceptance criteria" and "device performance" are primarily focused on meeting established standards and showing that changes do not negatively impact safety or effectiveness compared to the predicate.
Acceptance Criteria and Reported Device Performance
The general acceptance criteria are that the device performs as intended and is "substantially equivalent" to the predicate device, especially regarding safety and effectiveness. The specific performance reported largely revolves around conformance to recognized standards and successful completion of verification and validation.
Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria Category | Specific Criteria/Standards | Reported Device Performance |
|---|---|---|
| PNS (Peripheral Nerve Stimulation) Threshold | Set PNS threshold level required by IEC 60601-2-33 based on nerve stimulation thresholds. | A clinical study successfully determined nerve stimulation thresholds, and these parameters were used to set the PNS threshold level in accordance with IEC 60601-2-33. |
| Image Quality Assessment | Assessment for all new/modified pulse sequence types and algorithms; comparison to predicate features where applicable. | Image quality assessments were completed for all new/modified pulse sequence types and algorithms. Comparisons were made between new/modified features and predicate features in some cases. |
| Software Verification & Validation | Conformance to FDA guidance document: "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." | Software verification and validation testing was completed in accordance with the specified FDA guidance document. |
| Performance Tests | Conformance to FDA guidance document: "Submission of Premarket Notifications for Magnetic Resonance Diagnostic Devices" dated November 18, 2016. | Performance tests were completed in accordance with the specified FDA guidance document. |
| Risk Management | Risk analysis in compliance with ISO 14971:2007 (to identify and mitigate potential hazards). | Risk management was ensured via a risk analysis compliant with ISO 14971:2007. Risks are controlled via hardware/software development, testing, and labeling. |
| Electrical & Mechanical Safety | Conformance to IEC 60601-1 series (to minimize electrical and mechanical risk). | Siemens adheres to the IEC 60601-1 series and other recognized industry practices and standards. |
| Usability Engineering | Conformance to IEC 62366 Edition 1.0 2015. | Conforms to IEC 62366. |
| Software Life Cycle Processes | Conformance to IEC 62304:2006. | Conforms to IEC 62304:2006. |
| Acoustic Noise Measurement | Conformance to NEMA MS 4-2010. | Conforms to NEMA MS 4-2010. |
| Phased Array Coil Characterization | Conformance to NEMA MS 9-2008. | Conforms to NEMA MS 9-2008. |
| Digital Imaging & Communications in Medicine | Conformance to NEMA PS 3.1 - 3.20 (2016) (DICOM). | Conforms to NEMA PS 3.1 - 3.20 (2016). |
| Biocompatibility | Conformance to ISO 10993-1:2009/(R) 2013. | Conforms to ISO 10993-1:2009/(R) 2013 for biocompatibility. |
| Overall Substantial Equivalence | Device does not raise new questions of safety or effectiveness compared to the predicate device, MAGNETOM Skyra with syngo MR E11C (K153343). | Based on all verification and validation data, new/modified features bear an equivalent safety and performance profile to the predicate/reference devices. The device has the same intended use and different technological characteristics but is substantially equivalent. |
Study Information
-
Sample Size Used for the Test Set and Data Provenance:
- Clinical Study (PNS Threshold): 33 individuals. The document does not specify the country of origin or whether it was retrospective or prospective, but clinical studies for such thresholds are typically prospective.
- Nonclinical Tests (Image Quality, Software V&V, Performance Tests): The document does not specify a numerical sample size but mentions "sample clinical images were taken" for new coils and software features. It does not provide provenance (country, retrospective/prospective) for these samples specifically, but they would likely be internal studies.
-
Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
- The document does not explicitly state the number or qualifications of experts used to establish ground truth for the image quality assessments, software V&V, or performance tests. However, it indicates that the interpretation of images and spectra is done "by a trained physician." For image quality assessments, it's implied that Siemens' internal experts or qualified personnel performed these.
-
Adjudication Method for the Test Set:
- The document does not specify an adjudication method like 2+1 or 3+1 for any of the tests described.
-
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No MRMC comparative effectiveness study is mentioned for the entire device. The submission focuses on demonstrating substantial equivalence through compliance with standards, verification, and validation, rather than a direct comparison of reader performance with and without the new AI features (if any specific AI features are implied, they are integrated within the "new software" and not evaluated separately as AI-assisted reading).
- There is no mention of an effect size for human readers with vs. without AI assistance.
-
Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:
- No standalone performance study of an algorithm is explicitly described. The device is an MRI system, which always involves a human operator and physician interpretation. The "new software" features are part of the overall system performance, not presented as a discrete AI algorithm for standalone evaluation.
-
Type of Ground Truth Used:
- PNS Threshold Study: The ground truth would be the observed physiological response (nerve stimulation) in the 33 individuals, used to set the safety threshold.
- Image Quality Assessments: The ground truth would likely be internal Siemens expert assessment of expected image characteristics, clarity, and diagnostic interpretability against established quality metrics or comparisons to images from the predicate device.
- Software V&V/Performance Tests: Ground truth would be derived from specifications, expected functional outputs, and adherence to regulatory standards.
- General Diagnosis: The "Indications for Use" state that images and spectra, "when interpreted by a trained physician yield information that may assist in diagnosis." This implies physician interpretation is the ultimate ground truth for diagnostic purposes in clinical use, but not for the technical performance studies described in the 510(k).
-
Sample Size for the Training Set:
- The document does not provide information on a specific training set size. This type of 510(k) submission generally does not detail the internal development and training data for software components, especially when the changes are primarily updates to an existing system, rather than a de novo AI algorithm approval.
-
How the Ground Truth for the Training Set Was Established:
- Since no specific training set or study for algorithm training is described, the method for establishing its ground truth is not provided.
§ 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.