Search Results

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.

The subject devices, MAGNETOM Aera (including MAGNETOM Aera Mobile), MAGNETOM Skyra, MAGNETOM Prisma, MAGNETOM Prisma™, MAGNETOM Vida, MAGNETOM Lumina with software syngo MR XA60A, consist of new and modified software and hardware that is similar to what is currently offered on the predicate device, MAGNETOM Vida with syngo MR XA50A (K213693).

This FDA 510(k) summary describes several updates to existing Siemens Medical Solutions MRI systems (MAGNETOM Vida, Lumina, Aera, Skyra, Prisma, and Prisma fit), primarily focusing on software updates (syngo MR XA60A) and some modified/new hardware components. The document highlights the evaluation of new AI features, specifically "Deep Resolve Boost" and "Deep Resolve Sharp."

Here's an analysis of the acceptance criteria and the study details for the AI features:

1. Table of Acceptance Criteria and Reported Device Performance

The document provides a general overview of the evaluation metrics used but does not explicitly state acceptance criteria in a quantitative format (e.g., "Deep Resolve Boost must achieve a PSNR of X" or "Deep Resolve Sharp must achieve Y SSIM"). Instead, it describes the types of metrics used and qualitative assessments.

• Impact characterized by PSNR and SSIM. | 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). Most importantly, the performance was evaluated by visual comparisons to evaluate e.g., aliasing artifacts, image sharpness and denoising levels. |
  | Deep Resolve Sharp | - Preservation of image quality (image sharpness) compared to original.
• Impact characterized by PSNR, SSIM, and perceptual loss.
• Verification and validation by visual rating and evaluation of image sharpness by intensity profile comparisons. | 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 inhouse tests. These tests include visual rating and an evaluation of image sharpness by intensity profile comparisons of reconstructions with and without Deep Resolve Sharp. |

2. Sample Size Used for the Test Set and Data Provenance

• Deep Resolve Boost: The document doesn't explicitly state a separate "test set" size. It mentions the "Training and Validation data" which includes:
  • TSE: more than 25,000 slices
  • HASTE: pre-trained on the TSE dataset and refined with more than 10,000 HASTE slices
  • EPI Diffusion: more than 1,000,000 slices
  • Data Provenance: The data covered a broad range of body parts, contrasts, fat suppression techniques, orientations, and field strength. No specific country of origin is mentioned, but the manufacturer (Siemens Healthcare GmbH) is based in Germany, and Siemens Medical Solutions USA, Inc. is the submitter. The data was "retrospectively created from the ground truth by data manipulation and augmentation."
• Deep Resolve Sharp: The document doesn't explicitly state a separate "test set" size. It mentions "Training and Validation data" from "on more than 10,000 high resolution 2D images."
  • Data Provenance: Similar to Deep Resolve Boost, the data covered a broad range of body parts, contrasts, fat suppression techniques, orientations, and field strength. Data was "retrospectively created from the ground truth by data manipulation." No specific country of origin is mentioned.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

Not specified. The document states that the acquired datasets "represent the ground truth." There is no mention of expert involvement in establishing ground truth for the test sets. The focus is on technical metrics (PSNR, SSIM) and "visual comparisons" or "visual rating" which implies expert review, but the number and qualifications are not provided.

4. Adjudication Method for the Test Set

Not explicitly stated. The document mentions "visual comparisons" for Deep Resolve Boost and "visual rating" for Deep Resolve Sharp. This suggests subjective human review, but no specific adjudication method (like 2+1 or 3+1 consensus) is detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, If So, What Was the Effect Size of How Much Human Readers Improve with AI vs without AI Assistance

No MRMC comparative effectiveness study is described for the AI features. The studies mentioned (sections 8 and 9) focus on evaluating the technical performance and image quality of the AI algorithms themselves, not on their impact on human reader performance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, standalone performance evaluation of the algorithms was conducted. The "Test Statistics and Test Results Summary" for both Deep Resolve Boost and Deep Resolve Sharp detail the evaluation of the network's impact using quantitative metrics (PSNR, SSIM, perceptual loss) and qualitative assessments ("visual comparisons," "visual rating," "intensity profile comparisons"). This represents the algorithm's performance independent of a human reader's diagnostic accuracy.

7. The Type of Ground Truth Used

The ground truth used for both Deep Resolve Boost and Deep Resolve Sharp was the acquired datasets themselves, representing the original high-quality or reference images/slices.

• For Deep Resolve Boost, input data was "retrospectively created from the ground truth by data manipulation and augmentation," including undersampling k-space lines, lowering SNR, and mirroring k-space data. The original acquired data serves as the target "ground truth" for the AI to reconstruct/denoise.
• For Deep Resolve Sharp, input data was "retrospectively created from the ground truth by data manipulation," specifically by cropping k-space data to create low-resolution input, with the original high-resolution data serving as the "output / ground truth" for training and validation.

8. The Sample Size for the Training Set

• Deep Resolve Boost:
  • TSE: more than 25,000 slices
  • HASTE: pre-trained on the TSE dataset and refined with more than 10,000 HASTE slices
  • EPI Diffusion: more than 1,000,000 slices
• Deep Resolve Sharp: more than 10,000 high resolution 2D images.

9. How the Ground Truth for the Training Set Was Established

The ground truth for the training set was established as the acquired, unaltered (or minimally altered, e.g., removal of k-space lines to simulate lower quality input from high quality ground truth) raw imaging data.

• For Deep Resolve Boost: "The acquired datasets (as described above) represent the ground truth for the training and validation. Input data was retrospectively created from the ground truth by data manipulation and augmentation." This implies that the original, high-quality scans were considered the ground truth, and the AI was trained to restore manipulated, lower-quality versions to this original quality.
• For 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. k-space data has been cropped such that only the center part of the data was used as input. With this method corresponding low-resolution data as input and high-resolution data as output / ground truth were created for training and validation." Similar to Boost, the original, higher-resolution scans served as the ground truth.

Ask a specific question about this device

Your MAGNETOM system is indicated for use as a magnetic device (MRDD) that produces transverse, sagittal, coronal, and oblique cross sectional images, spectroscopic images and that displays the internal structure and/or function of the head, body, or 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.

Your MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room display and MR-Safe biopsy needles.

The subject devices, MAGNETOM Vida with software syngo MR XA31A, and MAGNETOM Vida with syngo MR XA20A, with the new pulse sequence MR Fingerprinting (MRF) consists of slightly modified software that are similar to what is currently offered in the predicate devices, MAGNETOM Vida with syngo MR XA31A (K203443) and MAGNETOM Vida with syngo MR XA20A (K192924) respectively.

The subject devices MAGNETOM Vida with software syngo MR XA31A, and MAGNETOM Vida with synqo MR XA20A includes features that were cleared under K203443 and K192924 respectively. In addition to these features, the subject devices include a new pulse sequence type called MR Fingerprinting (MRF), a method that permits the simultaneous non-invasive quantification mapping of MRF-derived T1 and T2 relaxation times of brain tissue. The MRF is not intended to yield the ground truth T1 and T2 relaxation times of brain tissue.

The document describes the Siemens MAGNETOM Vida MRI system with a new pulse sequence called MR Fingerprinting (MRF). The acceptance criteria for this device and the study proving it meets these criteria are outlined as follows:

1. Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: 3 healthy volunteers were scanned multiple times using multiple systems. Additionally, several clinical patient cases demonstrating a longitudinal use case scenario (repeated scans from the same subject over time) were provided.
• Data Provenance: The document does not explicitly state the country of origin. The study appears to be prospective, as it involved actively scanning volunteers and collecting clinical patient cases for demonstration.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

The document does not specify the number of experts or their qualifications for establishing ground truth for the provided clinical patient cases or for interpreting the volunteer scans. It states that the device provides "information that may assist in diagnosis" when interpreted by a trained physician, but this is in the general "Indications for Use" and not directly about the ground truth establishment for the performance study.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for the test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly mentioned as being done to compare human readers with and without AI assistance. The study focuses on the technical performance of the MRF sequence itself.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done

Yes, a standalone performance evaluation of the MRF sequence was performed. The "Performance bench test" and "Software verification and validation" involved quantitative evaluation of MRF-derived T1 and T2 values in phantoms and volunteers, and testing to confirm stable and reproducible parametric values across systems. This assessment of the algorithm's output without human interpretation is a standalone evaluation.

7. The Type of Ground Truth Used

The ground truth used for the quantitative evaluation of T1 and T2 values came from:

• Quantitative Phantom: For confirming stability and reproducibility of parametric values.
• Healthy Volunteers: For evaluating quantitative performance in terms of precision (repeatability and reproducibility) for T1 and T2 maps.
• The document implies that for the "Sample clinical images" and "clinical patient cases," the assessment was based on whether the sequence executed successfully and produced images free of artifacts, rather than comparing against an external, independent "ground truth" for diagnosis. The MRF itself is described as "not intended to yield the ground truth T1 and T2 relaxation times of brain tissue."

8. The Sample Size for the Training Set

The document does not provide information on the sample size used for the training set for the MRF pulse sequence.

9. How the Ground Truth for the Training Set Was Established

The document does not provide information on how the ground truth for the training set was established, as details about a training set are not included.

Ask a specific question about this device

The MAGNETOM system is indicated for use as a magnetic 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 inages 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.

MAGNETOM Lumina and MAGNETOM Vida Fit with software syngo MR XA50A include new software compared to the predicate devices, MAGNETOM Vida Fit with software syngo MR XA20A (K192924) and MAGNETOM Lumina with syngo MR XA31A (K203443). This software and some hardware components are transferred from the reference device MAGNETOM Vida with software syngo MR XA50A (K213693) as well as an imaging feature from MAGNETOM Vida with software syngo MR XA11A (K181433). A high-level summary of the transferred hardware and software is provided below:

Hardware (Vida Fit only)
Transferred Hardware:

• The Nexaris Dockable Table is a new variant of the MR patient table which is used for intraoperative or interventional imaging. It enables the patient transfer between OR tables and the MR system without repositioning on the MR patient table and vice versa during interventional procedures and surgeries. Additionally, it can be used for diagnostic imaging.
• The Nexaris Head Frame holds up to two Ultra Flex Large 18 coils. It can be used for head imaging in combination with the Nexaris Dockable Table when the patient is positioned on the transfer board but not pinned in a head clamp.
• Transferred MaRS Computer
  Transferred Coil:
• The Nexaris Spine 36 is used in combination with and without transfer board for body imaging on the Nexaris Dockable Table.
  Transferred modifications for hardware:
• The Beat Sensor is a contact less method for generating cardiac triggers as an alternative to the already existing ECG or pulse triggers. It is based on a measurement of the modulation of a weak magnetic Pilot Tone, caused by conformation changes in conductive tissues.
  Software
  Transferred Features and Applications: Vida Fit only:
• SVS EDIT is a special variant of the SVS SE pulse sequence type, which acquires two different spectra (one with editing pulses on resonance, one with editing pulses off resonance) within a single sequence.
• BEAT FQ nav allows the user to make use of navigator echo based respiratory gating for flow imaging to acquire 4D flow data. Both navigator echo based respiratory gating as well as flow imaging are part of the predicate device already. New is merely the combination of both.
• The HASTE interactive pulse sequence type extends the existing HASTE pulse sequence type by offering the possibility to interactively change imaging parameters.
• GRE_WAVE is a special variant of the GRE pulse sequence type which allows larger acceleration factors, measuring one or two contrasts. GRE Wave results in higher signal-to-noise ratio for larger acceleration factors which can be leveraged to allow fast high-resolution 3D susceptibility-weighted imaging.
• The myExam Prostate Assist provides an assisted and quided workflow for prostate imaging. This automated workflow leads to higher reproducibility of slice angulation and coverage; this may support exams not having to be repeated.
• Iniector coupling is a software application that allows the connection of certain contrast agent injectors to the MR system for simplified, synchronized contrast injection and examination start.
  Lumina onlv:
• Compressed Sensing GRASP-VIBE is intended to be used in dynamic and/or non-contrast liver examinations to support patients who cannot reliably hold their breath for a conventional breath-hold measurement.
  Lumina and Vida Fit:
• Deep Resolve Swift Brain is a protocol for fast routine brain imaging primarily based on echo planar imaging (EPI) pulse sequences. Its main enablers are multi-shot (ms) EPI pulse sequence types and a deep learning-based image reconstruction.
• Deep Resolve Boost is a novel deep learning-based image reconstruction alqorithm for 2D TSE data, which reconstructs images from k-space raw-data.
• 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.
• HASTE diffusion (HASTE DIFF) is a single-shot imaging method based on TSE readout with diffusion preparation to enable diffusion weighted imaging with reduced sensitivity to B0 inhomogeneity.
  Transferred Modifications for Features and Applications:
  Vida Fit only:
• The AbsoluteShim mode is a shimming procedure based on a 3-echo gradient echo protocol.
• The 3D ASL sequence (tgse_asl) now provides relCBF maps, by implementing an additional M0 scan and performing the corresponding reconstruction method. It also provides BAT maps in multiple inversion time(multi-TI) imaging.
  Lumina and Vida Fit:
• Fast GRE RefScan: A speed-optimized reference scan for GRAPPA and SMS kernel calibration for echo planar imaging pulse sequence types.
• Static Field Correction is a reconstruction option reducing susceptibilityinduced distortions and intensity variations.
• Deep Resolve Sharp is an interpolation algorithm which increases the perceived sharpness of the interpolated images. Functionality is available for different pulse sequence types. (Newly transferred to Vida Fit)
• Deep Resolve Gain is a reconstruction option which improves the SNR of the scanned imaqes. Functionality is available for different pulse sequence types. (Newly transferred to Vida Fit)
• The myExam Angio Advanced Assist provides an assisted and quided workflow for peripheral angiography examination using care bolus. The main advantage of this new workflow is a simplified and improved planning procedure of multi-station peripherical angiography measurements.
  Other transferred Modifications and / or Minor Changes
  Vida Fit only:
• Elastography-AddIn synchronizes settings between the Elastography sequence and the active driver.
• HASTE MoCo is an image-based motion correction in the average-dimension for the HASTE pulse sequence type.
• Coil independent pulse sequences remove the coil information from the pulse sequences and generate this information during run-time from automatic coil detection and localization.
• The Needle Intervention AddIn provides a user interface for workflow improvement of MR-quided needle interventions under real-time imaging conditions. It supports planning a needle trajectory, laser-based localization of the entry point as well as automatic slice positioning.
• The PhaseRev Dot Addin/Component supports the measurement workflow of the user by automatically flipping the direction of the phase encoding gradient.
• The adjustment mode "offcenter" triggers a transmitter adjustment method that is specialized for offcenter imaging. The transmitter adjustment determines the RF voltage that is required to excite a certain B1 field.
  Lumina and Vida Fit:
• TSE MoCo is an image-based motion correction in the average-dimension for the TSE pulse sequence type.
• MR Breast Biopsy is improved with an automatic fiducial detection.

The provided text primarily focuses on the substantial equivalence of the MAGNETOM Lumina and MAGNETOM Vida Fit with syngo MR XA50A to predicate devices. It does not include detailed information regarding specific acceptance criteria, device performance metrics, or the study design (e.g., sample sizes, expert qualifications, ground truth methods) that would typically be found in a clinical or performance study report.

Therefore, I cannot extract the requested information about acceptance criteria and the study proving the device meets them from the given document.

The document states:

• "No additional clinical tests were conducted to support substantial equivalence for the subject devices." (Page 9)
• The primary testing conducted was "Verification and validation" of transferred hardware and software features against "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices / 21 CFR §820.30" (Page 9).
• The conclusion is that "the results from each set of tests demonstrate that the devices perform as intended and are thus substantially equivalent to the predicate devices to which they have been compared." (Page 9).

This indicates that the submission relies on demonstrating equivalence to previously cleared devices through non-clinical verification and validation, rather than presenting a de novo performance study with specific acceptance criteria.

Ask a specific question about this 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 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.

MAGNETOM Vida and MAGNETOM Sola with Nexaris Angio-MR include modified hardware compared to the predicate device, MAGNETOM Vida with software syngo MR XA31A (K203443). A high-level summary of the modified hardware is provided below:

Hardware

Modified Hardware

• The Nexaris Dockable Table is a variant of the MR patient table which is used for intraoperative or interventional imaging. It enables the patient transfer between OR/ARTIS tables and the MR system without repositioning on the MR patient table and vice versa during interventional procedures and surgeries. Additionally, it can be used for diagnostic imaging.

The provided text is a 510(k) Summary for a medical device (MAGNETOM Vida and MAGNETOM Sola with Nexaris Angio-MR). This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving the device meets specific performance acceptance criteria through clinical studies for novel claims.

Therefore, many of the requested details about acceptance criteria, specific performance metrics, sample sizes for test sets, expert ground truth establishment, MRMC studies, or standalone algorithm performance are not directly available in this document. The submission relies on demonstrating that the modified hardware of the new device maintains the safety and performance profile of the predicate device.

Here's an analysis based on the information provided, highlighting what is present and what is absent:

1. Table of Acceptance Criteria and Reported Device Performance

This document does not provide a table with specific acceptance criteria (e.g., sensitivity, specificity, accuracy targets) and corresponding reported device performance metrics for a novel diagnostic claim. Instead, the "acceptance criteria" are implied by compliance with recognized standards and successful verification and validation of modified hardware, demonstrating equivalent safety and performance to the predicate device.

The reported "performance" is that the device "perform[s] as intended" and "bear[s] an equivalent safety and performance profile to that of the predicate device."

2. Sample Size Used for the Test Set and the Data Provenance

• Sample Size: Not applicable/not provided. The submission focuses on hardware modifications and compliance with standards, not on a clinical test set for diagnostic performance.
• Data Provenance: Not applicable/not provided for a clinical test set. The data provenance described is related to non-clinical performance testing of modified hardware against engineering and safety standards.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts

Not applicable. As there was no clinical diagnostic test set evaluated for novel claims, there was no need for experts to establish ground truth in this context. The "truth" evaluated was compliance with engineering and safety standards.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

Not applicable. No adjudications were performed related to a diagnostic test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

No MRMC comparative effectiveness study was done, as this submission is for a Magnetic Resonance Diagnostic Device (MRDD) and not an AI-assisted diagnostic tool or software. The document explicitly states: "No additional clinical tests were conducted to support substantial equivalence for the subject devices."

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

No standalone performance study of an algorithm was done. This submission is for an MRDD system with modified hardware, not a standalone algorithm.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The "ground truth" for the nonclinical tests was based on engineering specifications, recognized safety standards (e.g., AAMI / ANSI ES60601-1, 21 CFR §820.30), and risk management principles (ISO 14971).

8. The Sample Size for the Training Set

Not applicable. This submission does not involve an AI algorithm that would require a training set.

9. How the Ground Truth for the Training Set was Established

Not applicable. This submission does not involve an AI algorithm or a training set.

Summary of the Study Proving Acceptance Criteria:

The study proving the device meets the "acceptance criteria" (which in this context are interpreted as demonstrating safe and equivalent performance to the predicate device) was a series of nonclinical performance tests focused on the modified hardware.

• Study Type: Nonclinical performance testing (verification and validation against established standards and engineering requirements).
• Focus: Evaluation of "modified hardware" (Nexaris Dockable Table) to ensure it performs as intended and maintains the safety and performance profile of the predicate device.
• Tests Conducted:
  • Electrical, mechanical, structural, and related system safety tests (utilizing AAMI / ANSI ES60601-1).
  • Verification and validation (in accordance with 21 CFR §820.30).
• Conclusion: The results of these nonclinical tests demonstrated that the modified features "bear an equivalent safety and performance profile to that of the predicate device." The device also conforms to various recognized standards including IEC 62304, ISO 14971, IEC 60601-1 series, and others listed in the document.

In essence, the "study" was a comprehensive engineering and regulatory compliance assessment of the hardware changes, leveraging industry standards and internal verification processes instead of clinical performance studies with diagnostic endpoints.

Ask a specific question about this 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 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.

MAGNETOM Vida with software syngo MR XA50A includes new and modified software compared to the predicate device, MAGNETOM Vida with software syngo MR XA31A. A high-level summary of the new and modified hardware and software is provided below:

Software
New Features and Applications

• Deep Resolve Swift Brain is a protocol for fast routine brain imaging primarily based on echo planar imaging (EPI) pulse sequences. Its main enablers are multi-shot (ms) EPI pulse sequence types and a deep learning-based image reconstruction.
• Deep Resolve Boost is a novel deep learning-based image reconstruction algorithm for 2D TSE data, which reconstructs images from k-space raw-data.
• 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.
• HASTE diffusion (HASTE DIFF) is a single-shot imaging method based on TSE readout with diffusion preparation to enable diffusion weighted imaging with reduced sensitivity to B0 inhomogeneity.

Modified Features and Applications

• Fast GRE RefScan: A speed-optimized reference scan for GRAPPA and SMS kernel calibration for echo planar imaging pulse sequence types.
• Static Field Correction is a reconstruction option reducing susceptibilityinduced distortions and intensity variations.
• Deep Resolve Gain is a reconstruction option which improves the SNR of the scanned images. The functionality has been extended to pulse sequence types SE and TSE DIXON.
• Deep Resolve Sharp is an interpolation algorithm which increases the perceived sharpness of the interpolated images. The functionality has been extended to pulse sequence types SE and TSE DIXON.
• The myExam Angio Advanced Assist provides an assisted and quided workflow for peripheral angiography examination using care bolus. The main advantage of this new workflow is a simplified and improved planning procedure of multi-station peripherical angiography measurements.

Other Modifications and / or Minor Changes

• TSE MoCo is an image-based motion correction in the average-dimension for the TSE pulse sequence type.
• MR Breast Biopsy is improved with an automatic fiducial detection.

This document describes regulatory approval for an MRI system and its software updates, rather than a device with specific performance criteria evaluated against a ground truth in the context of AI or advanced image analysis. Therefore, much of the requested information cannot be extracted from the provided text.

Here's why and what can be extracted:

Why most of the requested information cannot be provided:

• No specific "device" for performance claims: The submission is for a Magnetic Resonance Diagnostic Device (MRDD) system (MAGNETOM Vida) and its software updates (syngo MR XA50A). It's essentially an upgrade to an existing MRI machine, not a new AI/CADx device making specific diagnostic claims that would require detailed performance metrics like sensitivity, specificity, AUC, etc.
• Focus on Substantial Equivalence: The primary objective of this 510(k) summary is to demonstrate that the upgraded MRI system is "substantially equivalent" to a legally marketed predicate device (MAGNETOM Vida with syngo MR XA31A). This demonstration typically involves showing that the new features do not raise new questions of safety or effectiveness and perform as intended, rather than proving a superior or specific diagnostic accuracy against a clinical ground truth.
• "Acceptance Criteria" are not clinical performance metrics: The "acceptance criteria" discussed in the document are related to the successful completion of performance tests (e.g., image quality assessments, software verification and validation) to ensure the device performs as intended and conforms to relevant standards, not clinical performance acceptance thresholds for a diagnostic task.
• No detailed clinical study for performance claims: The document explicitly states: "No additional clinical tests were conducted to support substantial equivalence for the subject devices; however, as stated above, sample clinical images were provided." This confirms that a dedicated clinical study to prove diagnostic performance metrics (e.g., of an AI algorithm) was not performed or presented here. The "clinical publications" referenced are primarily previous research papers related to the underlying technologies (e.g., deep learning for reconstruction, new pulse sequences), not a study directly validating the clinical performance of this specific device's new features against a ground truth.

Information that can be extracted:

Here's what can be provided based on the text:

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

Based on the nature of this 510(k) for an MRI system upgrade, the "acceptance criteria" are related to the successful completion of engineering and non-clinical performance evaluations, demonstrating the device performs as intended and is safe and effective when compared to the predicate. No specific numerical performance metrics (e.g., sensitivity, specificity for a diagnostic task) are provided as acceptance criteria or reported performance for a "device" in the context of AI.

2. Sample sized used for the test set and the data provenance

• Sample Size: Not specified for any clinical performance evaluation, as no dedicated clinical study was performed. The document mentions "sample clinical images" were provided, but the quantity or characteristics of these images are not detailed for a statistical test set.
• Data Provenance: Not specified, as no formal clinical test set with defined provenance was used to demonstrate performance against acceptance criteria in the manner requested.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Not applicable. No formal expert-adjudicated ground truth for a test set was established for a clinical performance study of this upgraded MRI system. The interpretation of images is generally described as being by a "trained physician" as part of the Indications for Use.

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

• Not applicable. No formal adjudication methods were used for a clinical performance test set.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No. A multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not conducted or reported in this 510(k) summary. The new features like "Deep Resolve Swift Brain" and "Deep Resolve Boost" are described as deep learning-based reconstruction algorithms or methods for faster imaging, not diagnostic AI assistants for human readers.

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

• No. This submission is for an MRI system and its software, which includes deep learning for image reconstruction. It is not a standalone diagnostic algorithm that operates without human-in-the-loop for interpretation and performance evaluation. The "nonclinical tests" included "Image quality assessments by sample clinical images" and "Software verification and validation," which are typical for imaging device changes.

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

• Not applicable for performance claims of an AI algorithm against a diagnostic ground truth. The "ground truth" in the context of MRI system performance typically refers to physical phantom measurements, simulated data, or established image quality metrics, not clinical diagnostic outcomes adjudicated by experts or pathology for AI algorithm evaluation.

8. The sample size for the training set

• Not specified. While the document mentions "deep learning-based image reconstruction," it does not provide details about the training set size for these deep learning components. The referenced clinical publications (e.g., [2], [3], [4], [5], [6], [8], [9]) discuss deep learning for reconstruction and accelerated MRI but are not specific to the training data used for this particular device's integrated deep learning features.

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

• Not specified. For deep learning-based image reconstruction, the "ground truth" typically involves high-quality, fully sampled MRI data used to train models to reconstruct images from undersampled or noisy data. However, the exact methodology for establishing this ground truth for the incorporated deep learning models is not detailed in this regulatory summary.

Ask a specific question about this device

Your MAGNETOM system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and/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.

Your MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room displays and MR Safe biopsy needles.

MAGNETOM Vida, MAGNETOM Sola, MAGNETOM Lumina, MAGNETOM Altea with software syngo MR XA31A includes new and modified hardware and software compared to the predicate device, MAGNETOM Vida with software syngo MR XA20A.

This document describes the Siemens MAGNETOM MR system (various models) with syngo MR XA31A software, and it does not describe an AI device. The information provided is a 510(k) summary for a Magnetic Resonance Diagnostic Device (MRDD). The "Deep Resolve Sharp" and "Deep Resolve Gain" features are mentioned as using "trained convolutional neuronal networks" but the document does not provide details on acceptance criteria or studies specific to the AI components as requested.

Therefore, many of the requested items (e.g., sample sizes for training/test sets for AI, expert consensus for ground truth, MRMC studies) cannot be extracted from this document because it is primarily focused on the substantial equivalence of the overall MR system and its general technological characteristics, not a specific AI algorithm requiring detailed performance studies against a clinical ground truth.

However, I can extract the available information, especially concerning the "Deep Resolve Sharp" and "Deep Resolve Gain" features, and note where the requested information is not present.

Here's the breakdown of available information, with specific answers to your questions where possible:

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

The document does not specify quantitative acceptance criteria for the "Deep Resolve Sharp" or "Deep Resolve Gain" features, nor does it present a table of reported device performance metrics for these features in the context of clinical accuracy or diagnostic improvement specifically. The performance testing mentioned is general for the entire system ("Image quality assessments," "Performance bench test," "Software verification and validation"), concluding that devices "perform as intended and are thus substantially equivalent."

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

• Test Set Sample Size: Not explicitly stated for specific features like "Deep Resolve Sharp" or "Deep Resolve Gain." The document broadly mentions "Sample clinical images" were used for "Image quality assessments."
• Data Provenance (Country/Retrospective/Prospective): Not specified in the document.

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

Not specified. The document states "Image quality assessments by sample clinical images" and that the "images...when interpreted by a trained physician yield information that may assist in diagnosis," but it does not detail the number or qualifications of experts involved in these assessments for specific software features or for establishing ground truth for any AI component.

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

Not specified.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

An MRMC study was not described for the "Deep Resolve Sharp" or "Deep Resolve Gain" features or any other AI component. The document references clinical publications for some features (e.g., Prostate Dot Engine, GRE_WAVE, SVS_EDIT) but these are general publications related to the underlying clinical concepts or techniques, not comparative effectiveness studies of the system's AI features versus human performance. The statement "No additional clinical tests were conducted to support substantial equivalence for the subject devices" reinforces this.

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

While "Deep Resolve Sharp" and "Deep Resolve Gain" involve "trained convolutional neuronal networks," the document does not describe standalone performance studies for these algorithms. Their inclusion is framed as an enhancement to the overall MR system's image processing capabilities, rather than a separate diagnostic AI tool. The stated purpose of Deep Resolve Sharp is to "increases the perceived sharpness of the interpolated images" and Deep Resolve Gain "improves the SNR of the scanned images," both being image reconstruction/enhancement features.

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

Not specified for any AI-related features. For general image quality assessment, the "trained physician" is mentioned as interpreting images to assist in diagnosis, implying clinical interpretation, but no formal ground truth establishment process is detailed.

8. The sample size for the training set

Not specified for the "trained convolutional neuronal networks" used in "Deep Resolve Sharp" or "Deep Resolve Gain."

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

Not specified.

Ask a specific question about this device

Your MAGNETOM system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal, and oblique cross sectional mages, spectroscopic images and or spectra, and that displays the internal structure and/or function of the head, body, or extremittes. Other physical parameters derived from the images and or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These inages and or spectra and the plysical parameters derived from the images and/or spectra, when interpreted by a trained physician, yield information that may assist in diagnosis.

Your MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room display and MR-Safe biopsy needles.

MAGMETOM Vida, MAGNETOM Lumina, and MAGNETOM Vida Fit with software synqo MR XA20A include new and modified hardware and software compared to the predicate device, MAGNETOM Vida with syngo MR XA11B. A high level summary of the hardware and software is provided below:

Hardware: Computer, Coils (BM Body 18)

Software Features and Applications: SMS for TSE DIXON, GOLiver, Angio TOF with Compressed Sensing (CS), RT Respiratory self-gating for FL3D VIBE, SMS for RESOLVE and QDWI, SPACE with Compressed Sensing (CS), i SEMAC, TSE_MDME, TSE and GRE with Inline Motion Correction, EP SEG PHS, GRE PHS, GRE_Proj, GOKnee2D, BEAT_interactive, EP2D_SE_MRE, ZOOMit DWI, SPACE Flair Improvements, External Phase Correction Scan for EPI Diffusion, MR Breast Biopsy Workflow improvements, GOBrain / GOBrain+

Software / Platform: Dot Cockpit, i Access-i, Table positioning mode

Other Modifications and / or Minor Changes: MAGNETOM Vida Fit, i BM Body 12, Body 18, UltraFlex Large 18, UltraFlex Small 18, Broad band / narrow band online supervision, LiverLab Dot Engine - debundling

The Siemens Medical Solutions USA, Inc. 510(k) submission for the MAGNETOM Vida, MAGNETOM Lumina, and MAGNETOM Vida Fit with software syngo MR XA20A and new hardware (BM Body 18 Coil) does not include a study to determine specific acceptance criteria for device performance. Instead, the submission relies on non-clinical tests to demonstrate substantial equivalence to a predicate device (MAGNETOM Vida with syngo MR XA11B).

Here's an analysis of the provided information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not provide explicit acceptance criteria with quantitative targets for the device's performance in terms of diagnostic accuracy, sensitivity, specificity, or other clinical metrics. The "device performance" reported is largely in the context of demonstrating equivalence through image quality assessments and conformance to standards.

2. Sample Size Used for the Test Set and Data Provenance:

The submission does not specify a distinct "test set" in the context of a clinical study for measuring diagnostic performance. For image quality assessments:

• Sample size: Not explicitly stated. The document refers to "sample clinical images" and "comparison images."
• Data provenance: Not specified. It doesn't mention the country of origin or whether the images were retrospective or prospective.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:

Not applicable, as no formal clinical study with a defined test set and ground truth establishment by experts for diagnostic evaluation is described. The "interpretation by a trained physician" is mentioned in the Indications for Use, which refers to the end-user clinical interpretation of the images, not the establishment of ground truth for a study.

4. Adjudication Method for the Test Set:

Not applicable, as no formal clinical study with a defined test set and expert adjudication is described.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

No MRMC study was performed or reported in this submission to evaluate the effectiveness of human readers with vs. without AI assistance. The submission describes improvements to an MR diagnostic device and its software, not an AI-assisted diagnostic tool.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

Not applicable. This submission focuses on improvements to an MR imaging system and its software features, not a standalone AI algorithm for diagnosis. The device's output (images and spectra) is explicitly stated to require interpretation by a trained physician.

7. Type of Ground Truth Used:

Ground truth, in the context of diagnostic accuracy for a clinical study, was not used in this submission. The assessments focused on technical performance, image quality, and compliance with standards, often by comparing the new features/hardware to the predicate device or existing functionalities.

8. Sample Size for the Training Set:

Not applicable. The submission does not describe an AI/machine learning algorithm that requires a training set in the typical sense of a diagnostic AI product. The software updates are improvements to the MR imaging system itself, which do not inherently involve a "training set" for an AI model to learn from.

9. How the Ground Truth for the Training Set Was Established:

Not applicable, as there is no described training set or AI model in this context.

Summary of the Study:

The submission highlights non-clinical performance testing and refers to clinical publications for specific features. The "study" described is primarily a set of engineering and verification/validation tests to demonstrate that the new hardware (BM Body 18 coil) and software features (e.g., SMS for TSE DIXON, GOLiver, Angio TOF with Compressed Sensing, RT Respiratory self-gating) perform as intended and do not raise new questions of safety or effectiveness compared to the predicate device.

The non-clinical tests included:

• Sample clinical images with image quality assessments (sometimes compared to predicate device features).
• Performance bench tests for hardware.
• Software verification and validation (following FDA guidance).
• Biocompatibility testing (ISO 10993-1).
• Electrical, mechanical, structural, and related system safety tests (AAMI/ANSI ES60601-1, IEC 60601-2-33).
• Electrical safety and electromagnetic compatibility (EMC) tests (IEC 60601-1-2).

The conclusion of these tests was that the subject devices perform as intended and are substantially equivalent to the predicate device. No clinical studies demonstrating diagnostic accuracy or changes in human reader performance were part of this 510(k) submission.

Ask a specific question about this device

Your MAGNETOM system is indicated for use as a magnetic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectroscopic 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 yicld information that may assist in diagnosis.

Your MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room displays and MR Safe biopsy needles.

MAGNETOM Vida with software syngo MR XA11B includes new and modified component, features and software compared to the predicate device, MAGNETOM Vida with syngo MR XA11A. A high level summary of the new and modified features is provided below:

Hardware
New Hardware

• Nose Marker for Inline Motion Correction
  Software
  New Features and Applications
• TFL with Inline Motion Correction: Tracking of motion of the head during 3D MPRAGE head scans with a nose marker and a camera system. The MR system uses the tracking information to compensate for the detected motion.
• i GOLiver: GOLiver is a set of optimized pulse sequence for fast and efficient imaging of the abdomen / liver. It is designed to provide consistent exam slots and to reduce the workload for the user in abdominal / liver MRI.
• TSE_MDME: A special variant of the TSE pulse sequence type which acquires several contrasts (with different TI and TE, i.e. Multi Delay Multi Echo) within a single sequence.
• SEMAC: SEMAC is a method for metal artifact correction in ortho imaging of patients i with whole joint replacement. Using Compressed Sensing the acquisition can be accelerated.
• Angio TOF with Compressed Sensing: The Compressed Sensing (CS) functionality is now available for TOF MRA within the BEAT pulse sequence type. Scan time can be reduced by an incoherent undersampling of k-space data. The usage of CS as well as the acceleration factor and further options can be freely selected by the user.
• SMS for RESOLVE and QDWI: Simultaneous excitation and acquisition of multiple i slices with the Simultaneous multi-slice (SMS) technique for readout-segmented echo planar imaging (RESOLVE) and quiet diffusion weighted imaging (QDWI).
• i SPACE with Compressed Sensing: The Compressed Sensing (CS) functionality is now available for the SPACE pulse sequence type. Scan time can be reduced by the incoherent under-sampling 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.
• RT Respiratory self-gating for FL3D_VIBE: Non-contrast abdominal and thoracic i examination in free breathing with reduced blur induced by respiratory motion.
  Other Modifications and / or Minor Changes
• i Turbo Suite is a marketing bundle of components for accelerated MR imaging offered for the MAGNETOM Vida MR systems.
• i Noise masking: a mechanism to remove the noise floor in outer regions is now available for RESOLVE and QDWI.

The provided FDA 510(k) summary for the MAGNETOM Vida (K183254) does not contain the specific details for acceptance criteria and a study proving the device meets those criteria, as typically seen for AI/ML-based medical devices or devices with new diagnostic functionalities.

This 510(k) is for an updated version of an existing MRI system (MAGNETOM Vida with software syngo MR XA11B) compared to its predicate (MAGNETOM Vida with syngo MR XA11A). The changes primarily involve new hardware (1 mention) and several new or modified software features for image acquisition and processing (e.g., motion correction, optimized pulse sequences, metal artifact correction, accelerated imaging techniques).

The document states: "No clinical tests were conducted to support substantial equivalence for the subject device; however, sample clinical images were provided to support the new/modified component and software features per the FDA guidance document 'Submission of Premarket Notifications for Magnetic Resonance Diagnostic Devices', dated November 18, 2016."

This indicates that the primary focus of the submission was on demonstrating that the new features maintain the safety and performance profile of the predicate device through non-clinical testing (image quality assessments, software verification/validation) and by providing sample clinical images (not a formal clinical study with acceptance criteria).

Therefore, I cannot populate the requested table and answer many of the questions directly from the provided text because such a detailed study with acceptance criteria, ground truth, expert readers, and effect sizes was not performed or described in this 510(k) submission for this specific device clearance.

Below, I will indicate which information is not present in the document and briefly explain why, based on the nature of this 510(k) (which is for an updated MRI system, not an AI/ML diagnostic algorithm).

Acceptance Criteria and Study for MAGNETOM Vida (K183254)

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample size used for the test set and the data provenance:

• Sample Size for Test Set: NOT PRESENT. The document mentions "sample clinical images were provided," but it does not specify the number of images or patients used for these samples, nor does it describe a formal "test set" in the context of a diagnostic performance study.
• Data Provenance (country of origin, retrospective/prospective): NOT PRESENT. The origin of the "sample clinical images" is not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• NOT APPLICABLE/NOT PRESENT. Since no formal clinical study with a defined "test set" and "acceptance criteria" was described for diagnostic performance, there's no mention of experts establishing ground truth for such a study. The product is an MRI system, and interpretations are made by "trained physicians."

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

• NOT APPLICABLE/NOT PRESENT. No formal adjudication method is described, as no specific clinical diagnostic performance test set requiring such expert consensus was presented in this 510(k).

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• NO. An MRMC study was not conducted or described for this submission. This device is an MRI scanner with new and modified acquisition and processing features, not an AI-assisted diagnostic tool that directly aids human readers to improve diagnostic accuracy.

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

• NO. This is an MRI system. Its "performance" is inherently tied to image acquisition and quality, which are then interpreted by a human. It does not perform a standalone diagnostic function like an AI algorithm for disease detection.

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

• NOT APPLICABLE/NOT PRESENT. No formal ground truth definition is provided for a clinical performance study since one was not conducted for the purpose of demonstrating substantial equivalence. The device's performance was evaluated through non-clinical tests (e.g., image quality assessments).

8. The sample size for the training set:

• NOT APPLICABLE/NOT PRESENT. The document describes software modifications including some advanced imaging techniques (e.g., Compressed Sensing). While these might involve optimization based on data, the submission does not describe a traditional "training set" in the context of an AI/ML algorithm development or a diagnostic study. The software development and testing follow IEC 62304 and other relevant standards.

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

• NOT APPLICABLE/NOT PRESENT. As no "training set" in the context of diagnostic AI/ML was described, no information on its ground truth establishment is provided.

Ask a specific question about this device

Your MAGNETOM system is indicated for use as a magnetic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional 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 inages and/ or spectra and the physical parameters derived from the images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

Your MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room displays and MR Safe biopsy needles.

MAGNETOM Vida with software syngo MR XA11A includes new and modified hardware and software compared to the predicate device, MAGNETOM Vida with syngo MR XA10A. A high level summary of the new and modified features is provided below:

Hardware
New Hardware

• New coils:
• BM Body 12 |
• BM Spine 24 |
• | Head/Neck 16
• -Head 32 MR Coil 3T
• Other components:
• camera —
• computer
• Multi-Channel Interface —

Modified Hardware

• Main components such as 32 independent RF channels -
• -Other components such as Tx-Box / RF filter plate / transmit system

Software
New Features and Applications

• GOKnee3D (examination comprising the AutoAlign knee localizer and two SPACE with CAIPIRINHA sequences to support fast high-resolution 3D exams of the knee)
• SPACE with CAIPIRINHA (3D SPACE pulse sequence type with the iPAT mode CAIPIRINHA)
• GOBrain (brain examination in short acquisition time)
• GOBrain+ (adaptation of GOBrain pulse sequences)
• | MR Breast Biopsy (supports planning and execution of MR guided breast biopsies and wire localizations)
• | MRSim / Synthetic CT (provides MR pulse sequences for the creation of Synthetic CT images based on the MR image input)
• Cardiac Dot Flow Add-In (extension of Cardiac Dot Engine to support blood flow measurements)
• PCASL mode (extension of ASL pulse sequence types by a new blood labeling mode)
• SMS in TSE (Simultaneous Multi Slice (SMS) support for TSE)

Modified Features and Applications

• | SliceAdjust (the framework support was extended to include additional pulse sequence types)

• RetroGating (Compressed Sensing Cardiac Cine acquisitions which split the data acquisition over multiple heartbeats can now be configured to perform complete sampling of the cardiac cycle without prior definition of an acquisition window. Combination with arrhythmia rejection is possible.)

• iPAT / TSE Reference Scan (Changes in the TSE, FAST TSE and TSE DIXON pulse sequence types includes the possibility to use a reference scan "TSE/Separate" for GRAPPA acquisition and reconstruction)

• Care Bolus in Angio Dot Engine (workflow support for bolus administration (bolus detection))

• MRCP in SPACE (improvement of the image quality for MR Cholangiopancreatography (MRCP) acquisitions based on the SPACE pulse sequence type)

• MR Elastography:

• Replacement of existing masking by masking performed on the prescan images used within the prescan/normalize (PSN) functionality.

• Optimization of pulse sequence type timing. |

• Changes in MEG time period (no longer fixed to the wavelength of the | MEG and also implementation of a reduced MEG period)

• Respiratory Sensor Support (additional support for respiratory triggered measurements is provided in several SE-, GRE- and EPI-based pulse sequence types)

Modified (general) Software / Platform

• ー Single and dual monitor workflow (In the single monitor setup the features of the LHS monitor and RHS monitor are provided on separate tab-cards)
• Touch positioning (Select&GO 2.0) (extension to additional body area positions when dedicated coils are plugged in)
• Dot Cockpit (additional features for handling of scan pulse sequences and offline Dot Cockpit)
• MR View&GO (Addition of Mosaic View (view mode to scroll through dimensions | instead of space) and 4D Movie Toolbar (movie toolbar to navigate the 4th dimension))

Other Modifications and / or Minor Changes

• teamplay Protocols Interface (interface to support external pulse sequences | management systems)

• Unilateral Hip (added in Large Joint Dot Engine) (user workflow optimized, since information/settings are taken from the patient registration)

• GRE RefScan (external GRE RefScan has been extended to multiple pulse sequence types)

• Asymmetric saturation pulses (support for regional saturation with an asymmetric shape has been added for BOLD imaging)

• CP Mode modification ("RF Transmit Mode" is provided as part of the patient registration based on IEC 60601-2-33)

• SPAIR FatSat (new "SPAIR Breast" mode in several pulse sequence types and extension of "Abdomen&Pelvis" and "Thorax" modes)

• Compressed Sensing GRASP-VIBE (improvement of SPAIR fat saturation performance)

• MAGNETOM RT Pro Edition marketing bundle (extension of the bundle)

• Siemens "BioMatrix" (extension with additional components)

The provided text is a 510(k) Summary for the Siemens MAGNETOM Vida MRI system (K181433). It describes the device, its intended use, and compares it to a predicate device (MAGNETOM Vida with syngo MR XA10A). However, this document primarily focuses on establishing substantial equivalence based on non-clinical testing and adherence to standards, rather than clinical performance studies with acceptance criteria in the typical sense for AI/CADe devices.

Therefore, many of the requested details regarding acceptance criteria, clinical study design (sample size, expert qualifications, adjudication, MRMC studies, standalone performance), and ground truth establishment (especially for AI/ML models) are not present in this document. This is because this submission is for an MRI system, not an AI/CADe device. It focuses on hardware and software modifications of a diagnostic imaging machine, not on an algorithm that interprets images.

Based on the provided text, here's what can be inferred:

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

The document discusses "performance testing" but does not provide specific quantitative acceptance criteria or detailed reported performance in a table format as might be expected for an AI/CADe device. Instead, the "acceptance" is qualitative:

2. Sample sized used for the test set and the data provenance:

• Test Set Sample Size: Not explicitly stated. The document mentions "sample clinical images" were taken for the new coils and software features, but no specific number of patients or images is given.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective).
• Retrospective or Prospective: Not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Number of Experts: Not specified.
• Qualifications of Experts: The device's output is "interpreted by a trained physician," implying that physicians are involved in assessing the images, but their specific role in establishing "ground truth" for the non-clinical tests is not detailed. For this type of MRI system submission, ground truth isn't established in the same way as for an AI interpretation algorithm. The "truth" is the physical output of the MRI system.

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

• Not applicable/Not specified. This level of detail on ground truth adjudication is typically for AI/CADe clinical studies, not MRI system performance tests focused on image quality and safety.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No MRMC study was done. The document explicitly states: "No clinical tests were conducted to support substantial equivalence for the subject device". This is not an AI-assisted reading device, but a diagnostic imaging system.

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

• Not applicable. This is an MRI device, not an AI algorithm. "Performance tests" were done on the device itself and its components (e.g., image quality assessments).

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

• For an MRI system, the "ground truth" for non-clinical testing refers to the physical and technical performance of the device (e.g., image clarity, signal-to-noise ratio, spatial resolution, adherence to safety limits). It is not about diagnostic accuracy against a clinical ground truth like pathology. The comparison is made against prior versions/predicate devices and established industry standards for image quality and safety.

8. The sample size for the training set:

• Not applicable. This document does not describe an AI/ML algorithm that requires a training set.

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

• Not applicable. As above, no AI/ML training set is discussed.

In summary: The provided document is a 510(k) summary for a Magnetic Resonance Diagnostic Device (MRDD), the MAGNETOM Vida MRI system. Its purpose is to demonstrate substantial equivalence to a legally marketed predicate device based on non-clinical performance testing (e.g., image quality assessments, software verification/validation) and conformity to recognized standards (e.g., IEC, ISO, NEMA). It explicitely states that no clinical tests were conducted for this submission. Therefore, the detailed requirements for AI/CADe device performance studies (like MRMC, training/test set ground truth, expert adjudication, etc.) are not addressed in this document because they are not relevant to this specific type of medical device submission.

Ask a specific question about this device

Your MAGNETOM system is indicated for use as a magnetic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and that displays the internal structure and/or function of the head, body, or 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.

Your MAGNETOM system may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room displays and MR Safe biopsy needles.

Compressed Sensing GRASP-VIBE is intended to be used in dynamic and/or non-contrast liver examinations to support patients who cannot reliably hold their breath for a conventional breath-hold measurement.

The subject device, MAGNETOM Vida, is an MR system. The software syngo MR XA10A is the latest software for the Siemens MAGNETOM Vida and includes software sequences, applications, coils and other hardware for the MAGNETOM scanner. The software sequences, applications, coils and other hardware were previously cleared with K170396.

MAGNETOM Vida will be offered ex-factory (new production) with software syngo MR XA10A and Compressed Sensing GRASP-VIBE. Installed MAGNETOM Vida systems can be updated by activating the blocked license.

This filing describes the new imaging feature intended to be used with the MAGNETOM Vida. Compressed Sensing GRASP-VIBE is intended to be used in dynamic and/or non-contrast liver examinations to support patients who cannot reliably hold their breath for a conventional breath-hold measurement.

The provided text describes a 510(k) premarket notification for the Siemens MAGNETOM Vida with Compressed Sensing GRASP-VIBE. The document asserts substantial equivalence to a predicate device and does not detail specific acceptance criteria or a comprehensive study proving the device meets them in the way clinical trials typically do. Instead, it relies on demonstrating that the new feature does not introduce new safety or effectiveness concerns.

Therefore, many of the requested items (e.g., sample size for test set, number of experts for ground truth, adjudication method, MRMC study, sample size for training set, ground truth for training set) are not explicitly addressed or applicable in the context of this 510(k) submission, which focuses on device modifications and substantial equivalence to an already cleared predicate.

However, based on the limited information available, here's what can be extracted and inferred:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table of quantitative acceptance criteria for image quality or clinical performance that would typically be found in a clinical study report. Instead, the "acceptance criteria" are implicitly met by demonstrating substantial equivalence to the predicate device through non-clinical testing and qualitative assessment of sample clinical images.

2. Sample Size Used for the Test Set and the Data Provenance

• Sample Size: Not explicitly stated for a dedicated clinical "test set." The document mentions "sample clinical images" were included in the determination of substantial equivalence, but not the number of images or patients.
• Data Provenance: Not specified. Given it's a Siemens product, it's likely international data, but no country of origin is mentioned. The type of data (retrospective or prospective) is also not specified for these "sample clinical images."

3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts

• This information is not provided. The document states that the images and physical parameters, "when interpreted by a trained physician yield information that may assist in diagnosis." For the "sample clinical images" used, it does not specify how many experts reviewed them nor their qualifications or the process of establishing ground truth.

4. Adjudication Method for the Test Set

• Not specified. This level of detail is typically not included in a 510(k) summary focused on substantial equivalence through non-clinical data and general claims.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No MRMC comparative effectiveness study is mentioned. This submission focuses on the performance of the device itself (specifically the new imaging feature) in relation to a predicate device, not on comparing human reader performance with or without the device's assistance.

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

• The document implies a standalone assessment of the new imaging feature's technical performance. It states: "A comparison of the functionality was performed between the new feature and the reference device feature by detailed simulations with a numerical phantom." This indicates an algorithm-only evaluation for technical characteristics, though not a clinical standalone performance study in the sense of diagnostic accuracy.

7. The Type of Ground Truth Used

• For the "detailed simulations with a numerical phantom," the ground truth would be the known properties of the numerical phantom.
• For the "sample clinical images," the type of ground truth is not explicitly stated. However, medical image interpretation typically relies on expert consensus, clinical follow-up, or pathology reports for ground truth in diagnostic accuracy studies. This document only mentions "interpretation by a trained physician" assisting in diagnosis, without specifying how ground truth was established for comparison.

8. The Sample Size for the Training Set

• Not applicable/mentioned. This is a 510(k) submission for an MRI system and its software feature, not a machine learning algorithm that underwent a separate training phase with a distinct training set. The "Compressed Sensing GRASP-VIBE" is a technical imaging feature, not an AI diagnostic algorithm in the typical sense that would require a ground-truthed training set for learning.

9. How the Ground Truth for the Training Set was Established

• Not applicable/mentioned, as there is no indication of a "training set" in the context of an AI algorithm learning from data.

Ask a specific question about this device