(232 days)
The MAGNETOM 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. Additionally, the MAGNETOM system is intended to produce Sodium images for the head and Phosphorus spectroscopic images and/or spectra for whole body, excluding the head. These images 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.
MAGNETOM Terra and MAGNETOM Terra.X with software syngo MR XA60A include new and modified hardware and software compared to the predicate device, MAGNETOM Terra with software syngo MR E12U. A high level summary of the new and modified hardware and software is provided below: Hardware: New Hardware (Combiner (pTx to sTx), MC-PALI, GSSU control unit, 8Tx32Rx Head coil), Modified Hardware (Main components such as: Upgrade of GPA, New Host computer hardware, New MaRS computer hardware, Upgrade the SEP, The new shim cabinet ASC5 replaces two ACS4 shim cabinets; Other components such as: RFPA, Use of a common MR component which provides basic functionality that is required for all MAGNETOM system types, The multi-nuclear (MNO) option has been modified, OPS module, Cover with UI update on PDD). Software: New Features and Applications (Static B1 shimming, TrueForm (1ch compatibility mode), Deep Resolve Boost, Deep Resolve Gain, Deep Resolve Sharp, Bias field correction (marketing name: Deep RxE), The new BEAT pulse sequence type, BLADE diffusion, The PETRA pulse sequence type, TSE DIXON, The Compressed Sensing (CS) functionality is now available for the SPACE pulse sequence type, The Compressed Sensing (CS) functionality is now available for the TFL pulse sequence type, IDEA, The Scientific Suite), Modified Features and Applications (EP2D DIFF and TSE with SliceAdjust, The Turbo Flash (TFL)), Modified Software / Platform (Stimulation monitoring, "dynamic research labeling"), Other Modifications and / or Minor Changes (Intended use, SAR Calculation and Weight limit reduction for 31P/1H TxRx Flex Loop Coil, X-upgrade for MAGNETOM Terra to MAGNETOM Terra.X, Provide secure MR scanner setup for DoD (Department of Defense) -Information Assurance compliance).
The provided text describes the acceptance criteria and supporting study for the AI features (Deep Resolve Boost, Deep Resolve Sharp, and Deep RxE) within the MAGNETOM Terra and MAGNETOM Terra.X devices.
Here's a breakdown of the requested information:
1. Table of Acceptance Criteria and Reported Device Performance
| AI Feature | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Deep Resolve Boost | Characterization by several quality metrics such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Visual inspection to ensure potential artifacts are detected. Successful passing of quality metrics tests. Work-in-progress packages delivered and evaluated in clinical settings. (Implicit: No misinterpretation, alteration, suppression, or introduction of anatomical information, and potential for faster image acquisition and significant time savings). | The impact of the network has been characterized by several quality metrics such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Additionally, images were inspected visually to ensure that potential artifacts are detected that are not well captured by the metrics listed above. After successful passing of the quality metrics tests, work-in-progress packages of the network were delivered and evaluated in clinical settings with cooperation partners. In a total of seven peer-reviewed publications, the investigations covered various body regions (prostate, abdomen, liver, knee, hip, ankle, shoulder, hand, and lumbar spine) on 1.5T and 3T systems. All publications concluded that the work-in-progress package and the reconstruction algorithm can be beneficially used for clinical routine imaging. No cases have been reported where the network led to a misinterpretation of the images or where anatomical information has been altered, suppressed, or introduced. Significant time savings are reported. |
| Deep Resolve Sharp | Characterization by several quality metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and perceptual loss. Verification and validation by in-house tests including visual rating and evaluation of image sharpness by intensity profile comparisons. (Implicit: Increased edge sharpness). | The impact of the network has been characterized by several quality metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and perceptual loss. In addition, the feature has been verified and validated by in-house tests. These tests include visual rating and an evaluation of image sharpness by intensity profile comparisons of reconstruction with and without Deep Resolve Sharp. Both tests show increased edge sharpness. |
| Deep RxE | 1. During training, the loss (difference to ground truth) is monitored, and the training step with the lowest test loss is taken as the final trained network. 2. Automated unit-tests are set up to test the consistency of the generated output to a previously defined reference output. 3. During verification, the performance of the network is tested on a phantom against the ground truth with a maximal allowed NRMSE of 11% (for 2D network) and 8.7% (for 3D network). 4. The trained final network was used in the clinical study. (Implicit: Increases image homogeneity in a reproducible way on the receive profile, and images acquired with Deep RxE are rated better for image quality in the clinical study). | 1. During training, the loss, as the difference to a ground truth, is monitored and the training step with the lowest test loss is taken as the final trained network. 2. Automated unit-tests are set up to test the consistency of the generated output to a previously defined reference output. 3. During verification, the performance of the network is tested on a phantom against the ground truth with a maximal allowed NRMSE of 11% (11% for the 2D network and 8.7% for the 3D network were achieved). 4. The trained final network was used in the clinical study. The tests show that Deep RxE increases image homogeneity in a reproducible way on the receive profile. Images acquired with Deep RxE (DL bias field correction) are rated better for image quality than the ones acquired without it in the clinical study that was conducted. |
Note on Acceptance Criteria: The document directly states acceptance criteria for Deep RxE (e.g., NRMSE < 11%). For Deep Resolve Boost and Deep Resolve Sharp, the "acceptance criteria" are more implicitly derived from the described validation and evaluation metrics and outcomes (e.g., "successful passing of quality metrics tests," "increased edge sharpness," "no misinterpretation").
2. Sample Size Used for the Test Set and Data Provenance
| AI Feature | Test Set Sample Size | Data Provenance |
|---|---|---|
| Deep Resolve Boost | 1,874 2D slices (from validation set) | In-house measurements and collaboration partners. (Retrospective, as input data was retrospectively created from ground truth by data manipulation and augmentation). |
| Deep Resolve Sharp | 2,057 2D slices (from validation set) | In-house measurements. (Retrospective, as input data was retrospectively created from ground truth by data manipulation). |
| Deep RxE | 23,992 2D slices / 404 3D volumes (validation and test set) | All data from two 7T MR systems (MAGNETOM Terra and MAGNETOM Terra.X). (Implied retrospective, as data was separated into independent sets). |
Patient characteristics (Gender/Age) were recorded for Deep RxE: female: 56%, male: 41%, phantom: 3%. Age range 20-80 years. Not recorded for other features.
Ethnicity was not recorded for any feature. The document states that due to network architecture, attributes like gender, age, and ethnicity are not relevant to training data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Deep Resolve Boost & Deep Resolve Sharp: The document does not mention the use of experts for ground truth establishment for the test set regarding these features. Images were visually inspected and quality metrics were used.
- Deep RxE: The document mentions that images acquired with Deep RxE were "rated better for image quality than the ones acquired without it in the clinical study that was conducted." This implies expert evaluation, but the number of experts or their qualifications for the test set ground truth for Deep RxE is not explicitly stated.
- Separately, for the overall device clearance, "radiologist's evaluation reports from two U.S. board-certified radiologists have been provided" for software modifications and new hardware. This is a general statement for the device and not specifically linked to the ground truth of the AI features' test sets.
4. Adjudication Method for the Test Set
The document does not explicitly describe an adjudication method (like 2+1, 3+1) for establishing ground truth for the test sets of these AI features. For Deep Resolve Boost and Sharp, the ground truth was derived from the acquired datasets themselves, which were then manipulated to create input data. For Deep RxE, the ground truth for phantom testing was a "previously defined reference output" or the acquired data, and for the clinical study, images were "rated better" but the adjudication process for this rating isn't detailed.
5. Multi Reader Multi Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study is directly mentioned specifically for the AI features (Deep Resolve Boost, Deep Resolve Sharp, or Deep RxE) that compares human readers with vs. without AI assistance. The document alludes to radiologists evaluating images with new software features or comparing images from subject/predicate devices, and for Deep Resolve Boost, it mentions clinical settings and "seven peer-reviewed publications" concluding beneficial use for clinical routine, with reports of "significant time savings." For Deep RxE, images were "rated better for image quality," which implies a reader study, but no details on methodology, number of readers, or specific effect size are provided to quantify human reader improvement with AI assistance.
6. Standalone (Algorithm Only) Performance
Yes, standalone performance was conducted for all three AI features:
- Deep Resolve Boost: Characterized by PSNR and SSIM, and visual inspection.
- Deep Resolve Sharp: Characterized by PSNR, SSIM, perceptual loss, visual rating, and intensity profile comparisons.
- Deep RxE: Performance of the network tested on a phantom against ground truth (maximal allowed NRMSE of 11% for 2D, 8.7% for 3D achieved). Unit-tests and a two-step test procedure involving validation on unseen data and RMS error calculation against ground truth.
These indicate evaluation of the algorithm's performance without a human in the loop, beyond initial visual inspections by evaluators.
7. Type of Ground Truth Used
- Deep Resolve Boost: The acquired datasets themselves, retrospectively manipulated through data manipulation and augmentation (under-sampling, lowering SNR, mirroring k-space data) to create input data.
- Deep Resolve Sharp: The acquired datasets themselves, retrospectively manipulated through data manipulation (cropping k-space data) to create corresponding low-resolution input and high-resolution output/ground truth.
- Deep RxE: For phantom testing, a "previously defined reference output" was used, and for other evaluations, the acquired datasets themselves were used for comparison against bias field correction methods (homodyne filtering, N4, UNICORN).
8. Sample Size for the Training Set
| AI Feature | Training Set Sample Size |
|---|---|
| Deep Resolve Boost | 24,599 2D slices |
| Deep Resolve Sharp | 11,920 2D slices |
| Deep RxE | 119,955 2D slices / 2007 3D volumes |
9. How the Ground Truth for the Training Set Was Established
- Deep Resolve Boost: The "acquired datasets represent the ground truth for the training and validation." Input data was "retrospectively created from the ground truth by data manipulation and augmentation."
- Deep Resolve Sharp: The "acquired datasets represent the ground truth for the training and validation." Input data was "retrospectively created from the ground truth by data manipulation."
- Deep RxE: The document states that "During training the loss, as the difference to a ground truth, is monitored." The method of establishing this initial ground truth is implicitly the raw acquired data from the 7T MRI scanners, as the network aims to correct for B1 inhomogeneities. It also states "All data from the two MR systems were separated into independent training, validation and test datasets," implying the raw or processed raw data served as reference for training.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo features the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" and "ADMINISTRATION" in blue text.
March 22, 2024
Siemens Medical Solutions USA, Inc. Milind Dhamankar Clinical Affairs and Regulatory Professional 40 Liberty Boulevard Malvern, Pennsylvania 19355
Re: K232322
Trade/Device Name: MAGNETOM Terra; MAGNETOM Terra.X Regulation Number: 21 CFR 892.1000 Regulation Name: Magnetic Resonance Diagnostic Device Regulatory Class: Class II Product Code: LNH, LNI, MOS Dated: March 1, 2024 Received: March 1, 2024
Dear Milind Dhamankar:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you. however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
{1}------------------------------------------------
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Daniel M. Krainak, Ph.D, Assistant Director DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
{2}------------------------------------------------
Indications for Use
510(k) Number (if known) K232322
Device Name MAGNETOM Terra and MAGNETOM Terra.X
Indications for Use (Describe)
The MAGNETOM 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. Additionally, the MAGNETOM system is intended to produce Sodium images for the head and Phosphorus spectroscopic images and/or spectra for whole body, excluding the head. These images 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.
Type of Use (Select one or both, as applicable)
| ☑ Prescription Use (Part 21 CER 801 Subpart D) |
|---|
| ☐ Over The Counter Use (21 CER 801 Subpart C) |
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
Image /page/3/Picture/1 description: The image contains the logo for Siemens Healthineers. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the words is a graphic of orange dots arranged in a circular pattern.
510(k) Summary
This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of the Safe Medical Devices Act 1990 and 21 CFR § 807.92.
General Information 1.
| Establishment: | Siemens Medical Solutions USA, Inc.40 Liberty BoulevardMalvern, PA 19355, USARegistration Number: 2240869 |
|---|---|
| Date Prepared: | March 1, 2024 |
- Manufacturer: Siemens Healthcare GmbH Henkestrasse 127 91052 Erlangen Germany Registration Number: 3002808157
2. Contact Information
Milind Dhamankar, M.D. Clinical Affairs and Regulatory Professional Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard Malvern, PA 19355, USA Cell: +1 (610) 517-9484 Phone: +1 (610) 448-6467
Device Name and Classification 3.
| Device/ Trade name: | MAGNETOM Terra |
|---|---|
| Classification Name: | Magnetic Resonance Diagnostic Device (MRDD) |
| Classification Panel: | Radiology |
| CFR Code: | 21 CFR § 892.1000 |
| Classification: | II |
| Product Code: | Primary: LNHSecondary: LNI, MOS |
Device/ Trade name: MAGNETOM Terra.X Classification Name: Magnetic Resonance Diagnostic Device (MRDD)
{4}------------------------------------------------
| Classification Panel: | Radiology |
|---|---|
| CFR Code: | 21 CFR § 892.1000 |
| Classification: | II |
| Product Code: | Primary: LNHSecondary: LNI, MOS |
Legally Marketed Predicate Device ব
| Trade name: | MAGNETOM Terra |
|---|---|
| 510(k) Number: | K183222 |
| Clearance Date: | February 15, 2019 |
| Classification Name: | Magnetic Resonance Diagnostic Device (MRDD) |
| Classification Panel: | Radiology |
| CFR Code: | 21 CFR § 892.1000 |
| Classification: | II |
| Product Code: | Primary: LNHSecondary: LNI, MOS |
5. Intended Use / Indications for Use
The indications for use for the subject devices is modified compared to the predicate device to accurately represent the weight limits in individual coils' intended population compared to the predicate device:
Indications for Use:
The MAGNETOM system is indicated for use as a magnetic resonance diagnostic 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.
Additionally the MAGNETOM system is intended to produce Sodium images for the head and Phosphorus spectroscopic images and/or spectra for whole body. excluding the head. These images 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.
6. Device Description
MAGNETOM Terra and MAGNETOM Terra.X with software syngo MR XA60A include new and modified hardware and software compared to the predicate
{5}------------------------------------------------
device, MAGNETOM Terra with software syngo MR E12U. A high level summary of the new and modified hardware and software is provided below:
Hardware
New Hardware
- Combiner (pTx to sTx) (8Tx-1Tx Combiner Interface):
- Hardware component adaptor to connect single Tx local RF coils to the pTx system, combines the 8Tx channels to single channel mode.
- MC-PALI: New component for monitoring RF power on all transmit channels.
- GSSU control unit: The new GSSU including the new cardiac stimulation monitor board supports and enables the cardiac simulation monitoring separately and nearly independently from the OPS.
New Coil
-
The 8Tx32Rx Head coil is a 1H (proton) RF-coil with 8 transmit and 32 receive channels used for head applications usable in the 8ch pTx Mode. It features a 8TX transmit shell. There are enhancements to the software that controls SAR. By enabling B1 shimming or full 8ch pTx operation, the new 8TX array allows improved B1 transmit characteristics which increase both contrast and homogeneity in the brain.
Modified Hardware -
Main components such as: ।
- Upgrade of GPA to increase the gradient performance which leads to an improvement of the imaging.
- New Host computer hardware with increased performance and "dynamic i research labeling" in the GUI
- New MaRS computer hardware as successor of previous MaRS computer
- Upgrade the SEP to the newest cooling cabinet series
- The new shim cabinet ASC5 replaces two ACS4 shim cabinets. -
-
। Other components such as:
- RFPA: Modified to be used for 8ch pTx. Therefore, components for 1ch Tx i are obsolete and were removed and control- and power modules are combined in one module instead.
- Use of a common MR component which provides basic functionality that is required for all MAGNETOM system types. RFCEL 2G light houses common MR components compatible with the MR environment but no specific 7T functionality is implemented and it is reduced in its functionality.
- The multi-nuclear (MNO) option has been modified to be used in combination with the parallel transmit (pTx) technology. Therefore, components used for the SAR supervision are changed. Other components such as the coils are unchanged.
- OPS module: The OPS implements the SAFE model using digital filters now. The parametrization of the filters and the processes are independent and separate for the peripheral and cardiac stimulation supervision.
{6}------------------------------------------------
- Cover with UI update on PDD: The cover has been modified to bring the system up to the Siemens Healthineers Design incl. the Numaris/X platform on the patent data display interface.
Software
New Features and Applications
- Static B1 shimming: B1 Shimming is available for nearby all the sequences i and can be used offering an improved B1 homogeneity especially in the brain.
- TrueForm (1ch compatibility mode): Software function to run a multichannel pTx coil in a virtual single channel mode.
- Deep Resolve Boost is a novel deep learning-based image reconstruction algorithm for 2D TSE data, which reconstructs images from k-space raw-data.
- Deep Resolve Gain is a reconstruction option which enables targeted denoising, resulting in improved SNR of the scanned images. The functionality is available for specific pulse sequence types now.
- Deep Resolve Sharp is a deep learning-based interpolation algorithm which । increases the perceived sharpness of the interpolated images. The functionality has been ported from the reference device MAGNETOM Vida to the subject devices MAGNETOM Terra and MAGNETOM Terra.X.
- Bias field correction (marketing name: Deep RxE) is a deep learning image । filter. The intention is to correct images by reducing residual B1 inhomogeneities (similar to a pre-scan normalize) to improve image quality for head and extremity imaging.
- The new BEAT pulse sequence type provides a combination of Time-Of-Flight -(TOF) MR angiography and Compressed Sensing (CS) to reduce measurement time.
- BLADE diffusion is a multi-shot imaging method based on TSE or TGSE । (when EPI factor > 1) readout and a BLADE trajectory with diffusion preparation to enable diffusion weighted imaging with reduced sensitivity to B0 inhomogeneity and reduced T2 decay caused image blurring.
- -The PETRA pulse sequence type generates no additional perceivable noise above the general noise in the background.
- TSE DIXON is a modified TSE (turbo spin echo) pulse sequence type for Dixon imaqinq.
- The Compressed Sensing (CS) functionality is now available for the SPACE pulse sequence type. Scan time can be reduced by the incoherent undersampling of the k-space data. The usage of CS as well as the acceleration factor and other options can be freely selected by the user.
- The Compressed Sensing (CS) functionality is now available for the TFL pulse sequence type. Scan time can be reduced by the incoherent undersampling of the k-space data. The usage of CS as well as the acceleration factor and other options can be freely selected by the user.
{7}------------------------------------------------
Image /page/7/Picture/1 description: The image contains the logo for Siemens Healthineers. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the words is a graphic of orange dots in a cluster.
- । IDEA which is a set of tools for developing sequences, image reconstruction programs, etc. is now available as well.
- The Scientific Suite supports scientific users by providing easy access to application-specific data for further processing and advanced image calculus.
Modified Features and Applications
- EP2D DIFF and TSE with SliceAdjust: SliceAdjust is a framework which । allows applying adjustment settings dynamically for individual slice measures during the acquisition.
- The Turbo Flash (TFL) is a GRE-based pulse sequence type which generates T1w, and FWS images. With dynamic pTx more coverage and a homogenous contrast is possible.
Modified Software / Platform
- Stimulation monitoring: Peripheral nerve stimulation and cardiac stimulation limits are supervised via the SAFE model, but with separate parameterizations now. Both SAFE models run independently.
- "dynamic research labeling": new Host computer hardware with increased performance and "dynamic research labeling" in the GUI
Other Modifications and / or Minor Changes
- Intended use, SAR Calculation and Weight limit reduction for 31P/1H । TxRx Flex Loop Coil: Adaptation of the system intended use, by moving the weight limit from the system intended use to the RF coil intended use and adapting of SAR calculation. In addition, change of the intended population for the 31P/1H TxRx Flex Loop 7T coil.
- X-upgrade for MAGNETOM Terra to MAGNETOM Terra.X (marked as new device): The MAGNETOM Terra.X is a new 7T MRI System which is the result of an improvement of the MAGNETOM Terra - either ex-factory or by an upgrade on-site.
- Provide secure MR scanner setup for DoD (Department of Defense) -Information Assurance compliance.
7. Substantial Equivalence
MAGNETOM Terra and MAGNETOM Terra.X with software syngo MR XA60A are substantially equivalent to the following predicate device:
| Predicate Device | FDA Clearance Numberand Date | ProductCode | Manufacturer |
|---|---|---|---|
| MAGNETOM Terra withsyngo MR E12U | K183222,cleared February 15, 2019 | LNH | Siemens AG / SiemensHealthcare GmbH |
| LNI, MOS |
MAGNETOM Terra and MAGNETOM Terra.X with software syngo MR XA60A include hardware and software already cleared on the following reference devices:
Traditional Premarket Notification 510(k)
{8}------------------------------------------------
| Reference Devices | FDA Clearance Numberand Date | ProductCode | Manufacturer |
|---|---|---|---|
| MAGNETOM Vida withsoftware syngo MR XA50A | K213693,cleared February 25, 2022 | LNHLNI, MOS | Siemens HealthcareGmbH |
| MAGNETOM Prisma withsoftware syngo MR XA30A | K202014,cleared September 8, 2020 | LNHLNI, MOS | Siemens HealthcareGmbH |
| syngo.via VB40A | K191040,cleared May 16, 2019 | LLZ | Siemens HealthcareGmbH |
Comparison of technological Characteristics with the Predicate Device 8.
The subject devices, MAGNETOM Terra and MAGNETOM Terra.X with software syngo MR XA60A, are substantially equivalent to the predicate device with regard to the operational environment, programming language, operating system and performance.
The subject devices conform to the standard for medical device software (IEC 62304) and other relevant IEC and NEMA standards.
While there are some differences in technological characteristics between the subject devices and predicate device, including new and modified hardware and software, these differences have been tested and the conclusions from the nonclinical data suggest that the features bear an equivalent safety and performance profile to that of the predicate device.
9. Nonclinical Tests
The following performance testing was conducted on the subject devices.
| Performance Test | Tested Hardware or Software | Source/Rationale for test |
|---|---|---|
| Sample clinical images | coils, new and modifiedsoftware features | Guidance for Submission ofPremarket Notifications forMagnetic ResonanceDiagnostic Devices |
| Image quality assessments bysample clinical images. Insome cases a comparison ofthe image quality was made. | - new / modified pulsesequence types andalgorithms.- comparison images betweenthe new / modified featuresand the predicate devicefeatures | Guidance for the Content ofPremarket Submissions forSoftware Contained in MedicalDevices |
| Performance bench testSoftware verification andvalidation | new and modified hardware andsoftware features | |
| Electrical, mechanical,structural, and related systemsafety test | complete system MAGNETOMTerra and MAGNETOM Terra.X | - AAMI / ANSI ES60601-1- IEC 60601-2-33 |
| Electrical safety andelectromagnetic compatibility(EMC) | complete system MAGNETOMTerra.X | IEC 60601-1-2 |
Traditional Premarket Notification 510(k)
{9}------------------------------------------------
The results from each set of tests demonstrate that the subject devices perform as intended and are thus substantially equivalent to the predicate device to which it has been compared.
Below table shows an executive summary of training and validation dataset of Al features (Deep Resolve Boost, Deep Resolve Sharp and Deep RxE) in the subject devices.
| Deep Resolve Boost | Deep Resolve Sharp | Deep RxE | |
|---|---|---|---|
| General / additional information | n.a. | The same function as on reference deviceMAGNETOM Vida which was ported to the subject devicesMAGNETOM Terra and MAGNETOM Terra.Xwithout significant modifications. The training and testing from the reference devices still fits. | A 4-step approach was performed:1. During training the loss, as the difference to a ground truth, is monitored and the training step with the lowest test loss is taken as the final trained network.2. Automated unit-tests are set-up to test the consistency of the generated output to a previously defined reference output3. During verification, the performance of the network is tested on a phantom against the ground truth with a maximal allowed NRMSE of 11% (11% for the 2D network and 8.7% for the 3D network were achieved)4. The trained final network was used in the clinical study. |
| Test setup | Equipment: 7T MRI scanners (from the predicate device)Protocols: Representative protocols (T1, T2 and PD | Equipment: 1.5T and 3T MRI scannersProtocols: Representative protocols (T1, T2 and PD with and | Equipment: 7T MRI MAGNETOM Terra and MAGNETOM Terra.X scanners |
| with and without fatsaturation), which havebeen altered (e.g., toincrease SNR, increaseresolution or reducedacceleration).Body regions: head andknee | without fat saturation)which have been altered(e.g. to increase SNR,increase resolution orreduced acceleration).Body regions: a broadrange of different bodyregions | Protocols:Representativeprotocols (T1, T2 andPD with and without fatsaturation) which havebeen altered (e.g., toincrease SNR,increase resolution orusing accelerationtechniques or withoutacceleration).Body regions: head(44%) and knee (56%)Used coils:- 1Tx32Rx Head Coil7T Clinic / per system | |
| Sample size: 26,473 2Dslices (6206 2D slicesacquired at 7T) | - research 8Tx32RxHead / per system- 1Tx28Rx Knee Coil7T Clinic / per system- 23Na 1Tx32Rx Head7TSample size: | ||
| Sample size: 13,977 2Dslices | 143,947/2410 (2Dslices / 3D volumes) | ||
| Dataset split:- Training: 24,599 slices- Validation: 1,874 slices | Dataset split:- Training: 11,920 slices- Validation: 2,057 slices | Dataset split:- Training:119,955/2007 (2D/3D)- Validation and test:23,992/404 (2D/3D) | |
| Note: Data split maintained similar data distribution(e.g., contrast, orientation, field strength, ...) in bothtraining and validation datasets. | All data from the twoMR systems wereseparated intoindependent training,validation and testdatasets | ||
| Sample source: in-housemeasurements andcollaboration partners | Sample source: in-house measurements | ||
| PatientCharacteristics | Clinical subgroups: No clinical subgroups havebeen defined for the datasets. | Gender distribution:- female: 56%- male: 41%- phantom: 3% | |
| Age: group rangesfrom 20 - 80 years.Clinical subgroups: No | |||
| have been defined forthe datasets. | |||
| Please note: due to reasons of data privacy, we didnot record how many individuals the datasetsbelong to. Gender, age, and ethnicity distributionwere also not recorded during data collection. Dueto the network architecture, attributes like gender,age and ethnicity are not relevant to the trainingdata. | Please note: Due tothe networkarchitecture, attributeslike gender, age andethnicity are notrelevant to the trainingdata. | ||
| Confounder | The input and output variables of the network have been derived from thesame dataset so that no confounders exist for the training methodology. | ||
| Reference standard | The acquired datasetsrepresent the ground truthfor the training andvalidation. Input data wasretrospectively createdfrom the ground truth bydata manipulation andaugmentation. Thisprocess includes furtherunder-sampling of thedata by discarding k-space lines, lowering ofthe SNR level by additionof noise and mirroring ofk-space data. | The acquired datasetsrepresent the groundtruth for the training andvalidation. Input datawas retrospectivelycreated from the groundtruth by datamanipulation. k-spacedata has been croppedsuch that only the centerpart of the data wasused as input. With thismethod correspondinglow-resolution data asinput and high-resolutiondata as output / groundtruth were created fortraining and validation. | Applying three differentmethods for bias fieldcorrection to the data,homodyne filtering, N4and UNICORN. |
| Test statistics andtest results | The impact of the networkhas been characterizedby several quality metricssuch as peak signal-to-noise ratio (PSNR) andstructural similarity index(SSIM). Additionally,images were inspectedvisually to ensure thatpotential artefacts aredetected that are not wellcaptured by the metricslisted above.After successful passingof the quality metricstests, work-in-progresspackages of the networkwere delivered andevaluated in clinicalsettings with cooperationpartners. In a total ofseven peer-reviewed | The impact of thenetwork has beencharacterized by severalquality metrics such aspeak signal-to-noiseratio (PSNR), structuralsimilarity index (SSIM),and perceptual loss. Inaddition, the feature hasbeen verified andvalidated by inhousetests. These testsinclude visual rating andan evaluation of imagesharpness by intensityprofile comparisons ofreconstruction with andwithout Deep ResolveSharp. Both tests showincreased edgesharpness. | Two step testprocedure.1. During training, thetest data set wasused to validatehow the networkperformed onunseen data.2. During system tests,the standarddeviation wasdetermined, and theRMS error wascalculated (againstthe ground truth).The tests show thatDeep RxE increasesimage homogeneity ina reproduceable wayon the receive profile.Images acquired withDeep RxE (DL bias |
Training and validation dataset of Al features
Traditional Premarket Notification 510(k)
{10}------------------------------------------------
Traditional Premarket Notification 510(k)
{11}------------------------------------------------
Traditional Premarket Notification 510(k)
{12}------------------------------------------------
| were successfullyscanned on 1.5T and 3T.The investigationscovered following bodyregions: prostate,abdomen, liver, knee, hip,ankle, shoulder, hand,and lumbar spine. Allpublications haveconcluded that the work-in-progress package andthe reconstructionalgorithm can bebeneficially used forclinical routine imaging.No cases have beenreported where thenetwork led to amisinterpretation of theimages or whereanatomical informationhas been altered,suppressed, orintroduced. In most casesthe new algorithm hasbeen used to acquireimages faster andsignificant time savingsare reported. | field correction) arerated better for imagequality than the onesacquired without it inthe clinical study thatwas conducted. |
|---|---|
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
10. Clinical Tests / Publications
On the predicate device MAGNETOM Terra, a clinical study of 35 individuals was conducted to determine the nerve stimulation thresholds used to limit the gradient system output. The observed parameters were used to set the PNS (Peripheral Nerve Stimulation) threshold level which is required in IEC 60601-2-33. This study is still valid for the subject devices MAGNETOM Terra and MAGNETOM Terra.X as the same gradient coil is used.
In addition to providing clinical sample images for some software modifications and the new 8Tx32Rx Head of the subject device, radiologist's evaluation reports from two U.S. board-certified radiologists have been provided. Where necessary the radiologists compared the subject and the predicate / reference device images. The radiologist's evaluation reports have comments on any observed artifacts and concerns those have been communicated with the user via labeling material.
{13}------------------------------------------------
Image /page/13/Picture/1 description: The image shows the logo for Siemens Healthineers. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the words is a cluster of orange dots of varying sizes.
A clinical investigation was conducted that covered parallel transmission technique, applications with faster image acquisition, Deep learning approaches and additional methods to enhance the clinical application range and a report summarizing the results was provided. The conclusion of the test was that the subject device can be used in the clinical routine with all applications and protocols examined in the clinical investigation according to the investigation plan.
Clinical publications are referenced to provide information on the use of the following features and functions.
| Feature / Function | Clinical Publication |
|---|---|
| Cloos MA, Boulant N, Luong M, Ferrand G, Giacomini E, Le Bihan D,Amadon A. kT -points: short three-dimensional tailored RF pulses for flip-angle homogenization over an extended volume. Magn Reson Med. 2012Jan;67(1):72-80. doi: 10.1002/mrm.22978. Epub 2011 May 16. PMID:21590724. | |
| dynamic pTx for TFL(for MAGNETOMTerra.X only) | Majewski K. Simultaneous optimization of radio frequency and gradientwaveforms with exact Hessians and slew rate constraints applied to kT-points excitation. Journal of Magnetic Resonance. 2021 May 1;326:106941. |
| Herrler, J, Liebig, P, Gumbrecht, R, et al. Fast online-customized(FOCUS) parallel transmission pulses: A combination of universal pulsesand individual optimization. Magn Reson Med. 2021; 85: 3140-3153.https://doi.org/10.1002/mrm.28643 | |
| Tanner, Mark, Giulio Gambarota, Tobias Kober, Gunnar Krueger, DavidErritzoe, José P Marques, and Rexford Newbould. 2012. 'Fluid and WhiteMatter Suppression with the MP2RAGE Sequence.' Journal of MagneticResonance Imaging: JMRI 35 (5): 1063-70.https://doi.org/10.1002/jmri.23532. | |
| Weight limitreduction for 31P/1H | Parasoglou, P, et al., 3D-Mapping of Phosphocreatine Concentration inthe Human Calf Muscle at 7T: Comparison to 3T, Magn Reson Med.Author manuscript; available in PMC 2014 December 01, 2013December, 70(6) |
| TxRx Flex Loop Coil | Hooijmans M. T., et al., Spatially localized phosphorous metabolism ofskeletal muscle in Duchenne muscular dystrophy patients: 24±monthfollow-up, https://doi.org/10.1371/journal.pone.0182086, August 1, 2017 |
11. Safety and Effectiveness
The device labeling contains instructions for use and any necessary cautions and warnings to ensure safe and effective use of the device.
Risk Management is ensured via a risk analysis in compliance with ISO 14971. to identify and provide mitigation of potential hazards early in the design cvcle and continuously throughout the development of the product. Siemens Healthcare GmbH adheres to recognized and established industry standards,
{14}------------------------------------------------
such as the IEC 60601-1 series, to minimize electrical and mechanical hazards. Furthermore, the device is intended for healthcare professionals familiar with and responsible for the acquisition and post processing of magnetic resonance images.
MAGNETOM Terra and MAGNETOM Terra.X with software syngo MR XA60A conform to the following FDA recognized and international IEC, ISO and NEMA standards:
| RecognitionNumber | ProductArea | Title of Standard | ReferenceNumber and date | StandardsDevelopmentOrganization |
|---|---|---|---|---|
| 19-4 | General II(ES/EMC) | Medical electrical equipment -Part 1: General requirements forbasic safety and essentialperformance (IEC 60601-1:2005, MOD) | ES60601-1:2005/(R)2012and A1:2012,C1:2009/(R)2012andA2:2010/(R)2012(Consolidated Text) | ANSI AAMI |
| 19-8 | General | Medical electrical equipment -Part 1-2: General requirementsfor basic safety and essentialperformance - CollateralStandard: Electromagneticdisturbances - Requirementsand tests | 60601-1-2, Ed.4.0:2014 | IEC |
| 12-295 | Radiology | Medical electrical equipment -Part 2-33: Particularrequirements for the basicsafety and essentialperformance of magneticresonance equipment formedical diagnosis | 60601-2-33, Ed.3.2:2015 | IEC |
| 5-125 | General I(QS/RM) | Medical devices - Application ofrisk management to medicaldevices | 14971 Third edition2019-12 | ISO |
| 5-114 | General I(QS/RM) | Medical devices - Part 1:Application of usabilityengineering to medical devices[Including CORRIGENDUM 1(2016)] | 62366-1 Edition 1.02015-02 | IEC |
| 13-79 | Software/Informatics | Medical device software -Software life cycle processes | 62304 Edition 1.12015-06CONSOLIDATEDVERSION | IEC |
| 2-258 | Biocompatibility | Biological evaluation of medicaldevices - part 1: evaluation andtesting within a riskmanagement process | 10993-1 Fifthedition 2018-08 | ISO |
Traditional Premarket Notification 510(k)
{15}------------------------------------------------
Image /page/15/Figure/0 description: The image shows the Siemens Healthineers logo. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the word "Healthineers" is a graphic of orange dots arranged in a circular pattern.
| 12-342 | Radiology | Digital Imaging andCommunications in Medicine(DICOM) Set | PS 3.1 - 3.202021e | NEMA |
|---|---|---|---|---|
| 12-188 | Radiology | Determination of Signal-to-Noise Ratio (SNR) in DiagnosticMagnetic Resonance Images | MS 1:2008 (R2020) | NEMA |
| 12-196 | Radiology | Determination of Two-dimensional GeometricDistortion in DiagnosticMagnetic Resonance Images | MS 2:2008 (R2020) | NEMA |
| 12-187 | Radiology | Determination of ImageUniformity in DiagnosticMagnetic Resonance Images | MS 3:2008 (R2020) | NEMA |
| 12-232 | Radiology | Acoustic Noise MeasurementProcedure for DiagnosingMagnetic Resonance ImagingDevices | MS 4:2010 | NEMA |
| 12-322 | Radiology | Determination of SliceThickness in DiagnosticMagnetic Resonance Imaging | MS 5:2018 | NEMA |
| 12-195 | Radiology | Determination of Signal-to-Noise Ratio and ImageUniformity for Single-Channel,Non-Volume Coils in DiagnosticMagnetic Resonance Imaging(MRI) | MS 6:2008 (R2014) | NEMA |
| 12-315 | Radiology | Characterization of the SpecificAbsorption Rate for MagneticResonance Imaging Systems | MS 8:2016 | NEMA |
| 12-288 | Radiology | Standards PublicationCharacterization of PhasedArray Coils for DiagnosticMagnetic Resonance Images | MS 9-2008 (R2020) | NEMA |
| 12-298 | Radiology | Determination of Local SpecificAbsorption Rate (SAR) inDiagnostic Magnetic ResonanceImaging Systems | MS 10 - 2010 | NEMA |
| 12-306 | Radiology | Quantification and Mapping ofGeometric Distortion for SpecialApplications | MS 12 - 2016 | NEMA |
12. Conclusion as to Substantial Equivalence
MAGNETOM Terra and MAGNETOM Terra.X with software syngo MR XA60A have the same intended use (although it is corrected) and same basic technological characteristics than the predicate device system, MAGNETOM Terra with syngo MR E12U, with respect to the magnetic resonance features and functionalities. While there are some differences in technical features compared to the predicate device, the differences have been tested and the conclusions from all verification and validation data suggest that the features bear an
{16}------------------------------------------------
Image /page/16/Picture/1 description: The image contains the logo for Siemens Healthineers. The word "SIEMENS" is in teal, and the word "Healthineers" is in orange. To the right of the words is a graphic of orange dots in a circular pattern.
equivalent safety and performance profile to that of the predicate device and reference devices.
Siemens believes that MAGNETOM Terra and MAGNETOM Terra.X with software syngo MR XA60A are substantially equivalent to the currently marketed device MAGNETOM Terra with software syngo MR E12U (K183222, cleared on February 15, 2019).
§ 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.