Seven peer-reviewed publications involving 427 patients were used to evaluate the clinical utility and performance of the 'Deep Resolve' AI reconstruction algorithms in routine clinical settings.
AI/ML; Deep Resolve; Clinical routine imaging; Peer-reviewed literature
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Peer-reviewed clinical evaluations of Deep Resolve Boost; Retrospective clinical evaluation / Literature review
427 patients across various body regions (prostate, abdomen, liver, knee, hip, ankle, shoulder, hand, lumbar spine); Sample Size: 427
Not applicable for this study
Clinical utility, image quality, and acquisition time savings in routine clinical imaging
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Image reconstruction (Deep Resolve Boost)
Deep learning reconstruction algorithm
—
—
Training: 24,599 slices; Validation: 1,874 slices
—
—
—
Image reconstruction (Deep Resolve Sharp)
Deep learning reconstruction algorithm
—
—
Training: 11,920 slices; Validation: 2,057 slices
—
—
—
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, spectroscopic images and/or spectra, and that displays the internal structure and/or function of the head, body, or extremities. 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 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. The 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.
Device Story
MAGNETOM Amira and Sempra are MRI systems using magnetic resonance to generate diagnostic images/spectra of human anatomy. Systems utilize RF coils, gradient systems, and computer processing to acquire and reconstruct data. New software (syngo MR XA50M) introduces AI-based reconstruction (Deep Resolve Boost/Sharp) to improve SNR and sharpness. Operated by healthcare professionals in clinical settings. Output is viewed by physicians to assist in diagnosis. AI features use deep learning to process raw k-space data, reducing scan time and enhancing image quality. Benefits include faster acquisition and improved diagnostic clarity. Hardware additions include new Flex coils for Sempra. System supports interventional procedures with MR-safe accessories.
Clinical Evidence
No clinical trials conducted. Evidence consists of bench testing, software verification/validation, and sample clinical images. AI features (Deep Resolve Boost/Sharp) validated using retrospective datasets (26,473 and 13,977 slices respectively) with PSNR, SSIM, and visual sharpness metrics. Peer-reviewed literature (7 publications, 427 patients) supported clinical utility for various body regions.
Technological Characteristics
MR diagnostic device; 1.5T/3T field strengths. Includes RF coils (Flex series), gradient systems, and syngo MR XA50M software. Connectivity via DICOM. Software includes AI-based reconstruction (Deep Resolve). Conforms to IEC 60601-1, 60601-2-33, 62304, 62366, and ISO 14971/10993 standards.
Indications for Use
Indicated for use as an MRDD to produce cross-sectional images, spectroscopic images, and spectra of the head, body, or extremities for diagnostic purposes. Applicable to patients requiring MR imaging, including interventional procedures using MR-compatible devices.
Regulatory Classification
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).
Special Controls
*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.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health and Human Services logo. To the right of that is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
March 28, 2023
Siemens Medical Solutions USA, Inc. % Alina Goodman Regulatory Affairs Professional 40 Liberty Boulevard MALVERN PA 19355
Re: K223343
Trade/Device Name: MAGNETOM Amira; MAGNETOM Sempra Regulation Number: 21 CFR 892.1000 Regulation Name: Magnetic Resonance Diagnostic Device Regulatory Class: Class II Product Code: LNH, MOS, LNI Dated: March 3, 2023 Received: March 3, 2023
Dear Alina Goodman:
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 (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 located 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.
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
{1}------------------------------------------------
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 803) for devices or postmarketing safety reporting (21 CFR 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 (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 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 Magnetic Resonance and Nuclear Medicine Team 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
Enclosure
{2}------------------------------------------------
# Indications for Use
Submission Number (if known)
#### K223343
Device Name
MAGNETOM Amira; MAGNETOM Sempra
Indications for Use (Describe)
The 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/or spectra, and that displays the internal structure and/or function of the head, body, or extremities. 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 images and/or spectra and the physical parameters derived from the images and/or spectra when interpreted by a trained physician vield information that may assist in diagnosis.
The 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.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 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}------------------------------------------------
# 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.
#### 1. General Information
| Establishment: | Siemens Medical Solutions USA, Inc.<br>40 Liberty Boulevard<br>Malvern, PA 19355, USA<br>Registration Number: 2240869 |
|----------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Date Prepared: | October 31, 2022 |
| Manufacturer: | Siemens Shenzhen Magnetic Resonance Ltd.<br>Siemens MRI Center, Gaoxin C. Ave., 2nd<br>Hi-Tech Industrial Park<br>518057 Shenzhen<br>PEOPLE'S REPUBLIC OF CHINA<br>Registration Number: 3004754211<br>Siemens Healthcare GmbH |
Henkestrasse 127 91052 Erlangen Germany Registration Number: 3002808157
## 2. Contact Information
Alina Goodman Regulatory Affairs Professional Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard Malvern, PA 19355, USA Phone: +1(224)526-1404 E-mail: alina.goodman@siemens-healthineers.com
#### 3. Device Name and Classification
| Device/ Trade name: | MAGNETOM Amira<br>MAGNETOM Sempra |
|-----------------------|---------------------------------------------|
| Classification Name: | Magnetic Resonance Diagnostic Device (MRDD) |
| Classification Panel: | Radiology |
| CFR Code: | 21 CFR § 892.1000 |
| Classification: | II |
| Product Code: | Primary: LNH<br>Secondary: LNI, MOS |
| 4.1 Predicate Device | |
| Trade name: | MAGNETOM Amira |
| 510(k) Number: | K183221 |
| Classification Name: | Magnetic Resonance Diagnostic Device (MRDD) |
| Classification Panel: | Radiology |
| CFR Code: | 21 CFR § 892.1000 |
| Classification: | II |
| Product Code: | Primary: LNH<br>Secondary: LNI, MOS |
| Trade name: | MAGNETOM Sempra |
| 510(k) Number: | K183221 |
| Classification Name: | Magnetic Resonance Diagnostic Device (MRDD) |
| Classification Panel: | Radiology |
| CFR Code: | 21 CFR § 892.1000 |
| Classification: | II |
| Product Code: | Primary: LNH<br>Secondary: LNI, MOS |
| 4.2 Reference Device | |
| Trade name: | MAGNETOM Sola |
| 510(k) Number: | K221733 |
| Classification Name: | Magnetic Resonance Diagnostic Device (MRDD) |
| Classification Panel: | Radiology |
| CFR Code: | 21 CFR § 892.1000 |
| Classification: | II |
| Product Code: | Primary: LNH<br>Secondary: LNI, MOS |
| Trade name: | MAGNETOM Free.Max |
| 510(k) Number: | K220575 |
| Classification Name: | Magnetic Resonance Diagnostic Device (MRDD) |
| Classification Panel: | Radiology |
| CFR Code: | 21 CFR § 892.1000 |
| Classification: | II |
| Product Code: | Primary: LNH<br>Secondary: MOS |
{4}------------------------------------------------
#### 4. Legally Marketed Predicate Device
#### 5. Intended Use
The indications for use for the subject devices are the same as that of the predicate device:
The 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/or spectra, and that displays the internal structure and/or function of the head, body, or extremities. 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 images and/or spectra and the physical parameters derived from the
{5}------------------------------------------------
images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.
The 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.
# 6. Device Description
MAGNETOM Amira and MAGNETOM Sempra with syngo MR XA50M include new and modified features comparing to the predicate devices MAGNETOM Amira and MAGNETOM Sempra with syngo MR XA12M (K183221, cleared on February 14, 2019).
Below is a high-level summary of the new and modified hardware and software features comparing to the predicate devices MAGNETOM Amira and MAGNETOM Sempra with syngo MR XA12M:
# Hardware
Dedicated coils only for MAGNETOM Sempra with syngo MR XA50M:
- -Flex Large 8 Coil
- Flex Small 8 Coil -
- Flex 8 Coil Interface -
# Software
New Features and Applications:
- SMS TSE DIXON -
- SE EPI MRE (EP2D_SE_MRE) -
- ZOOMit PRO -
- High bandwidth inversion recovery -
- WAVE-CAIPI SWI (GRE) WAVE) -
- Deep Resolve Sharp -
- Deep Resolve Gain -
- -Deep Resolve Boost
- -Table positioning mode
- Coil independent pulse sequences -
- BLADE Diffusion -
- -TSE MoCo
- MR protocols module (new name for "MR Protocol Manager") -
- Automatic fiducial detection -
- Access-i -
- myExam Brain Autopilot
- SMS Averaging -
Modified Features and Applications:
- 3D ASL (TGSE_ASL) -
- myExam LiverLab Assist
{6}------------------------------------------------
Below Table 1 shows an executive summary of training and validation dataset of Al features (Deep Resolve Boost and Deep Resolve Sharp) in subject devices:
| | Deep Resolve Boost | Deep Resolve Sharp |
|----------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Sample size | 26,473 2D slices | 13,977 2D slices |
| | Note: due to reasons of data privacy, we did not record how many<br>individuals the datasets belong to. Gender, age and ethnicity distribution<br>was also not recorded during data collection. Due to the network<br>architecture, attributes like gender, age and ethnicity are not relevant to<br>the training data. | |
| Sample source | in-house measurements<br>and collaboration partners | in-house measurements |
| Dataset slipt | Training: 24,599 slices<br>Validation: 1,874 slices | Training: 11,920 slices<br>Validation: 2,057 slices |
| | Note: Data split maintained similar data distribution (e.g. contrast,<br>orientation, field strength, ...) in both training and validation datasets. | |
| Equipments | 1.5T and 3T MRI scanners | |
| Protocols | Representative protocols (T1, T2 and PD with and without<br>fat saturation) which have been altered (e.g. to increase<br>SNR, increase resolution or reduced acceleration). | |
| Body regions | a broad range of different body regions | |
| Clinical<br>subgroups | No clinical subgroups have been defined for the datasets. | |
| Counfouders | The input and output variables of the network have been<br>derived from the same dataset so that no confounders exist<br>for the training methodology. | |
| Test statistics<br>and test<br>results | The impact of the network has<br>been characterized by several<br>quality metrics such as peak<br>signal-to-noise ratio (PSNR)<br>and structural similarity index<br>(SSIM). Additionally, images<br>were inspected visually to<br>ensure that potential artefacts<br>are detected that are not well<br>captured by the metrics listed<br>above.<br>After successful passing of the<br>quality metrics tests, work-in-<br>progress packages of the<br>network were delivered and<br>evaluated in clinical settings<br>with cooperation partners. In a<br>total of seven peer-reviewed<br>publications 427 patients were<br>successfully scanned on 1.5T<br>and 3T. The investigations<br>covered following body<br>regions: prostate, abdomen, | The impact of the network has<br>been characterized by several<br>quality metrics such as peak<br>signal-to-noise ratio (PSNR),<br>structural similarity index<br>(SSIM), and perceptual loss. In<br>addition, the feature has been<br>verified and validated by<br>inhouse tests. These tests<br>include visual rating and an<br>evaluation of image sharpness<br>by intensity profile comparisons<br>of reconstruction with and<br>without Deep Resolve Sharp.<br>Both tests show increased edge<br>sharpness. |
| | liver, knee, hip, ankle,<br>shoulder, hand and lumbar<br>spine. All publications have<br>concluded that the work-in-<br>progress package and the<br>reconstruction algorithm can<br>be beneficially used for clinical<br>routine imaging. No cases<br>have been reported where the<br>network led to a<br>misinterpretation of the images<br>or where anatomical<br>information has been altered,<br>suppressed, or introduced. In<br>most cases the new algorithm<br>has been used to acquire<br>images faster and significant<br>time savings are reported. | |
| Reference<br>standard | The acquired datasets<br>represent the ground truth for<br>the training and validation.<br>Input data was retrospectively<br>created from the ground truth<br>by data manipulation and<br>augmentation. This process<br>includes further under-<br>sampling of the data by<br>discarding k-space lines,<br>lowering of the SNR level by<br>addition of noise and mirroring<br>of k-space data. | The acquired datasets represent<br>the ground truth for the training<br>and validation. Input data was<br>retrospectively created from the<br>ground truth by data<br>manipulation. k-space data has<br>been cropped such that only the<br>center part of the data was used<br>as input. With this method<br>corresponding low-resolution<br>data as input and high-resolution<br>data as output / ground truth<br>were created for training and<br>validation. |
Table 1. Training and validation dataset of Al features
{7}------------------------------------------------
# 7. Substantial Equivalence
MAGNETOM Amira and MAGNETOM Sempra with software syngo MR XA50M are substantially equivalent to the predicate devices list in Table 2:
| Predicate Device | FDA Clearance Number and Date | Product<br>Code | Manufacturer |
|------------------------------------------|----------------------------------------|---------------------|------------------------------------------------|
| MAGNETOM Amira with<br>syngo MR XA12M | K183221, cleared on February 14, 2019 | LNH,<br>LNI,<br>MOS | Siemens Shenzhen<br>Magnetic Resonance<br>Ltd. |
| MAGNETOM Sempra with<br>syngo MR XA12M | K183221, cleared on February 14, 2019 | LNH,<br>LNI,<br>MOS | Siemens Shenzhen<br>Magnetic Resonance<br>Ltd. |
| Reference Device | FDA Clearance Number and Date | Product<br>Code | Manufacturer |
| MAGNETOM Sola with<br>syngo MR XA51A | K221733, cleared on September 13, 2022 | LNH,<br>LNI,<br>MOS | Siemens Healthcare<br>GmbH |
| MAGNETOM Free.Max with<br>syngo MR XA50A | K220575, cleared on June 24, 2022 | LNH,<br>MOS | Siemens Shenzhen<br>Magnetic Resonance<br>Ltd. |
Table 2. Predicate devices and reference devices.
{8}------------------------------------------------
## 8. Technological Characteristics
The subject devices, MAGNETOM Amira and MAGNETOM Sempra with software syngo MR XA50M, are substantially equivalent to the predicate devices 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.
There are some differences in technological characteristics between the subject devices and predicate devices, including new and modified hardware and software features. Please see below Table 3 and Table 4 for the comparison between subject devices and predicate/ reference devices.
| | Subject Device | Predicate Device | Subject Device | Predicate Device |
|---------------------------|------------------------------------------------------|-------------------------------------------------------------------|-----------------------------------------------------------------------------|--------------------------------------------------------------------|
| Feature | MAGNETOM<br>Amira with<br>software syngo<br>MR XA50M | MAGNETOM<br>Amira with<br>software syngo<br>MR XA12M<br>(K183221) | MAGNETOM<br>Sempra with<br>software syngo<br>MR XA50M | MAGNETOM<br>Sempra with<br>software syngo<br>MR XA12M<br>(K183221) |
| Magnet<br>System | same | same | same | same |
| RF System | same | same | same | same |
| Transmission<br>Technique | same | same | same | same |
| Gradient<br>System | same | same | same | same |
| Patient Table | same | same | same | same |
| Computer | same | same | same | same |
| Coils | same | same | New coils:<br>-Flex Large 8,<br>-Flex Small 8,<br>-Flex 8 Coil<br>Interface | - |
| Other HW<br>components | same | same | same | same |
Table 3. Hardware Comparison
Comparison results: new local coils are introduced to MAGNETOM Sempra with syngo MR XA50M comparing to the predicate device. These differences have been tested and non-clinical data concluded no impact on safety and effectiveness of the device.
{9}------------------------------------------------
| | Table 4. Software Features Comparison |
|--|---------------------------------------|
| | |
| | Subject Device | Subject Device | Reference<br>Device | Predicate<br>Device | Predicate<br>Device |
|-----------------------------------------|---------------------------------------------|----------------------------------------------|---------------------------------------------------------|----------------------------------------------------------|-----------------------------------------------------------|
| Feature | MAGNETOM<br>Amira with<br>syngo MR<br>XA50M | MAGNETOM<br>Sempra with<br>syngo MR<br>XA50M | MAGNETOM<br>Sola with<br>syngo MR<br>XA51A<br>(K221733) | MAGNETOM<br>Amira with<br>syngo MR<br>XA12M<br>(K183221) | MAGNETOM<br>Sempra with<br>syngo MR<br>XA12M<br>(K183221) |
| SMS for TSE<br>DIXON | | same | | No | No |
| SE EPI MRE | | same | | No | No |
| ZOOMit PRO | | same | | No | No |
| High bandwidth<br>inversion<br>recovery | | same | | No | No |
| WAVE-CAIPI SWI | | same | | No | No |
| Deep Resolve<br>Sharp | | same | | No | No |
| Deep Resolve<br>Gain | | same | | No | No |
| Deep Resolve<br>Boost | | same | | No | No |
| Table positioning<br>mode | | same | | No | No |
| Coil independent<br>pulse sequences | | same | | No | No |
| BLADE Diffusion | | same | | No | No |
| TSE MoCo | | same | | No | No |
| MR Protocols<br>Module | | same | | No | No |
| Automatic fiducial<br>detection | | same | | No | No |
| Access-i | | same | | No | No |
| myExam Brain<br>Autopilot | | same | | No | No |
| SMS Averaging [1] | | same | No | No | No |
| 3D ASL | | same, modified comparing to predicate device | | Yes | Yes |
| myExam LiverLab<br>Assist | | same, modified comparing to predicate device | | Yes | Yes |
[1] SMS Averaging for TSE was cleared in reference device MAGNETOM Free.Max with syngo MR XA50A (K220575). SMS Averaging is made available for both TSE and TSE DIXON pulse sequence in subject devices.
Comparison results: new and modified software features are introduced to subject devices comparing to the predicate devices. These differences have been tested and non-clinical data concluded no impact on safety and effectiveness of the devices.
{10}------------------------------------------------
# 9. Nonclinical Tests
| Performance Test | Tested Hardware or Software | Source/Rationale for test |
|-----------------------------------------|---------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------|
| Sample clinical images | New local coils, new and<br>modified software features,<br>pulse sequence types | Guidance for Submission of<br>Premarket Notifications for<br>Magnetic Resonance<br>Diagnostic Devices |
| Software verification and<br>validation | mainly new and modified<br>software features | Guidance for the Content of<br>Premarket Submissions for<br>Software Contained in Medical<br>Devices |
The following performance testing was conducted on the subject devices:
The following performance testing for local coils was conducted on the predicate devices and can be reused for the subject devices:
| Performance Test | Tested Hardware or Software | Source/Rationale for test |
|------------------------|---------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------|
| Performance bench test | - SNR and image uniformity<br>measurements for coils<br>- Heating measurements for<br>coils | Guidance for Submission of<br>Premarket Notifications for<br>Magnetic Resonance<br>Diagnostic Devices |
The results from each set of tests demonstrate that the devices perform as intended and are thus substantially equivalent to the predicate device to which it has been compared.
## 10.Clinical Tests / Publications
No clinical tests were conducted to support substantial equivalence for the subject device; however, as stated above, sample clinical images were provided.
## 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 cycle and continuously throughout the development of the product. Siemens adheres to recognized and established industry standards, such as the IEC 60601-1 series, to minimize electrical and mechanical hazards. Furthermore, the devices are intended for healthcare professionals familiar with and responsible for the acquisition and post processing of magnetic resonance images.
MAGNETOM Amira and MAGNETOM Sempra with software syngo MR XA50M conform to the following FDA recognized and international IEC, ISO and NEMA standards:
{11}------------------------------------------------
| Recogniti<br>on<br>Number | Product<br>Area | Title of Standard | Reference<br>Number and date | Standards<br>Development<br>Organization |
|---------------------------|----------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------|------------------------------------------|
| 19-4 | General | Medical electrical equipment - part<br>1: general requirements for basic<br>safety and essential performance | ES60601-<br>1:2005/(R) 2012<br>and A1:2012 | AAMI / ANSI |
| 19-8 | General | Medical electrical equipment - Part<br>1-2: General requirements for basic<br>safety and essential performance -<br>Collateral Standard:<br>Electromagnetic disturbances -<br>Requirements and tests | 60601-1-2 Edition<br>4.0:2014-02 | IEC |
| 12-295 | Radiology | Medical electrical equipment - Part<br>2-33: Particular requirements for the<br>basic safety and essential<br>performance of magnetic resonance<br>equipment for medical diagnosis | 60601-2-33 Ed.<br>3.2:2015 | IEC |
| 5-40 | General | Medical devices - Application of risk<br>management to medical devices | 14971:2019 | ISO |
| 5-96 | General | Medical devices - Application of<br>usability engineering to medical<br>devices | 62366 Edition 1.0<br>2015 | AAMI ANSI<br>IEC |
| 13-32 | Software | Medical device software - Software<br>life cycle processes | 62304 Edition 1.1<br>2015-06 | AAMI<br>ANSI<br>IEC |
| 12-195 | Radiology | NEMA MS 6-2008 (R2014)<br>Determination of Signal-to-Noise<br>Ratio and Image Uniformity for<br>Single-Channel Non-Volume Coils<br>in Diagnostic MR Imaging | MS 6-2008<br>(R2014) | NEMA |
| 12-300 | Radiology | Digital Imaging and<br>Communications in Medicine<br>(DICOM) Set 03/16/2012 Radiology | PS 3.1 - 3.20<br>(2016) | NEMA |
| 2-156 | Biocompati<br>bility | Biological evaluation of medical<br>devices - part 1: evaluation and<br>testing within a risk management<br>process. (Biocompatibility) | 10993-1:2018/(R)<br>2013 | AAMI<br>ANSI<br>ISO |
# 12.Conclusion as to Substantial Equivalence
MAGNETOM Amira and MAGNETOM Sempra with software syngo MR XA50M have the same intended use and same basic technological characteristics as the predicate devices system, MAGNETOM Amira and MAGNETOM Sempra with syngo MR XA12M (K183221, cleared on February 14, 2019), with respect to the magnetic resonance features and functionalities. While there are some differences in technical features compared to the predicate devices, the differences have been tested and the conclusions from all verification and
{12}------------------------------------------------
validation data suggest that the features bear an equivalent safety and performance profile to that of the predicate device and reference device.
Siemens believes that MAGNETOM Amira and MAGNETOM Sempra with software syngo MR XA50M are substantially equivalent to the currently marketed devices MAGNETOM Amira and MAGNETOM Sempra with syngo MR XA12M.
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.