K Number
K170840
Device Name
MAGNETOM Terra
Date Cleared
2017-10-12

(205 days)

Product Code
Regulation Number
892.1000
Panel
RA
Reference & Predicate Devices
Predicate For
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The MAGNETOM Terra system is indicated for use as a magnetic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional images and that displays the internal structure and/or function of the head or extremities. Other physical parameters derived from the images may also be produced. These images and the physical parameters derived from the interpreted by a trained physician vield information that may assist in diagnosis.

The device is intended for patients > 30 kg/66 lbs.

Device Description

MAGNETOM Terra is a 60 cm bore Magnetic Resonance Imaging system with an actively shielded 7T superconducting magnet. With the interplay of the magnetic field, gradients, radio frequency (RF) transmitter and receiver coil and software this magnetic resonance scanner produces transverse, sagittal, coronal and oblique cross sectional images that represent the spatial distribution of protons with spin. The MAGNETOM Terra uses two local coils 1Tx32Rx Head Coil 7T Clinic and 1Tx28Rx Knee Coil 7T Clinic for head and knee imaging.

AI/ML Overview

The provided text describes the Siemens MAGNETOM Terra, a 7T Magnetic Resonance Imaging (MRI) system. However, it focuses on demonstrating substantial equivalence to a predicate device (MAGNETOM Trio A Tim System with syngo MR B19A) rather than establishing novel safety and effectiveness through specific acceptance criteria and a dedicated study demonstrating the device meets those criteria for a new clinical indication or outcome.

The text outlines various non-clinical tests and a clinical study primarily to ensure the device's fundamental safety and performance within the established framework for MRI devices, especially given the increased magnetic field strength (7T). It does not present a study designed to prove the device meets specific acceptance criteria related to a new clinical performance claim or diagnostic accuracy.

Therefore, many of the requested sections (Table of acceptance criteria, device performance, sample size for test set, data provenance, number of experts for ground truth, adjudication method, MRMC study, standalone performance, type of ground truth used for test set, training set details) are not applicable or extractable from this document as the submission does not detail a study aimed at proving a specific clinical performance criterion for this device as a new clinical claim.

Below is a summary of the information that can be extracted or inferred based on the document's content:

1. A table of acceptance criteria and the reported device performance

No explicit "acceptance criteria" table for a specific clinical performance claim is provided. The submission focuses on demonstrating compliance with recognized standards and substantial equivalence to a predicate device. Performance is generally assessed via image quality and safety parameters.

Criteria/TestPerformance/Compliance
Sample clinical images acquiredAll available clinical pulse sequences and local coils
Image quality assessmentsCompleted during system test
Acoustic noise measurementsAccording to NEMA standard
Performance TestsAccording to IEC 62464-1
Surface heating test for local coilsCompleted
Software verification and validationIn accordance with FDA guidance "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices"
Nerve stimulation thresholdsSet based on clinical study, within required IEC 60601-2-33 limits
Risk managementIn compliance with ISO 14971:2007
Applicable standardsConforms to IEC, ISO, NEMA standards (e.g., IEC 60601-1, IEC 60601-1-2, IEC 60601-2-33, ISO 14971, IEC 62366-1, IEC 62304, NEMA MS 4-2010, NEMA PS 3.1-3.20, ISO 10993-1)
Local SAR estimationBased on computational modeling on FDTD algorithm using human models (Virtual Population and MIDA Model), mesh size 2mm
Substantial EquivalenceConsidered substantially equivalent to MAGNETOM Trio A Tim System (K123938)

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

  • Sample size for nerve stimulation threshold study: 35 individuals.
  • Data provenance: Not explicitly stated whether retrospective or prospective, or country of origin. It is a "clinical study" performed to set PNS thresholds.
  • Sample images for image quality assessment: Not specified beyond "sample clinical images were acquired for all available clinical pulse sequences and local coils."

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

  • For nerve stimulation threshold study: Not applicable, as this study determines physiological thresholds, not ground truth for diagnostic imaging interpretation.
  • For image quality assessment: "reports from two U.S. board-certified radiologists have been provided after the radiologists reviewed image pairs comparing the subject and the predicate device." Their specific experience level is not mentioned beyond "board-certified." This implies a qualitative assessment, not a formal ground truth establishment for a diagnostic study.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

  • For image quality review: Not explicitly detailed beyond "two U.S. board-certified radiologists... reviewed image pairs comparing the subject and the predicate device [and their] comments on any observed artifacts and concerns have also been included." This suggests a qualitative comparison rather than a formal adjudication process for diagnostic accuracy.

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

  • No MRMC comparative effectiveness study is mentioned, nor is there any AI component described in the device. This device is an MRI scanner, not an AI-powered diagnostic tool.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

  • Not applicable, as this is an MRI scanner, not an algorithm being evaluated for standalone diagnostic performance.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

  • For nerve stimulation threshold study: The "ground truth" is the empirically observed nerve stimulation thresholds in the 35 individuals, which defines the physiological limits for setting the PNS threshold level.
  • For image quality assessment: The "ground truth" or reference is implied to be the qualitative assessment and comparison by board-certified radiologists against the predicate device, focusing on image characteristics and artifacts. No objective ground truth (e.g., pathology, clinical outcomes) is stated as being used to assess diagnostic accuracy.

8. The sample size for the training set

  • Not applicable/provided. This submission does not describe a machine learning algorithm that requires a training set. The software development is based on an existing software line and adapted for 7T parameters. The SAR control software enhancements are based on simulations with human models.

9. How the ground truth for the training set was established

  • Not applicable, as no training set for a machine learning algorithm is described. The SAR control software relies on computational modeling and simulation data using established human models (Virtual Population, MIDA Model) to estimate local SAR.

§ 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.