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

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

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

Hardware
Modified Hardware

• -Gradient system with XK gradient engine (36/200): Reduction in GPA performance with unchanged hardware components
• -Cover: Adapted system design
• Tim [180x32] configuration: patient table with 180 simultaneous connectable coil elements

Software
New Features and Applications

• GOLiver: Set of optimized pulse sequences 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.
  Other Modifications and / or Minor Changes
• Turbo Suite marketing bundle: Turbo Suite is a marketing bundle of components for accelerated MR imaging offered for the MAGNETOM Lumina MR system.

Here's a breakdown of the acceptance criteria and study information for the MAGNETOM Lumina device, based on the provided document:

This document does not describe the specific acceptance criteria or a detailed clinical study demonstrating the device's performance in a way that typically includes metrics like sensitivity, specificity, or AUC, as would be expected for an AI/algorithm-based diagnostic tool. Instead, this 510(k) summary focuses on demonstrating substantial equivalence to a predicate device (MAGNETOM Vida) through non-clinical testing and adherence to recognized standards.

The "device" in question (MAGNETOM Lumina) is a Magnetic Resonance Diagnostic Device (MRDD), an MRI scanner, not an AI-powered diagnostic algorithm in the sense of providing specific disease detection or quantification with performance metrics. The new software feature "GOLiver" within the MAGNETOM Lumina is described as a set of optimized pulse sequences for imaging, designed to improve workflow, not an AI for diagnosis.

Therefore, many of the requested elements (like effect size of AI assistance, sample size for test set with ground truth, expert qualifications for ground truth, adjudication methods) are not applicable or not provided in the context of this 510(k) submission, which is for an MRI scanner itself.

However, I can extract information related to the closest aspects of acceptance criteria and testing that are present:

Acceptance Criteria and Device Performance for MAGNETOM Lumina

Given that the device is an MRI system (not an AI diagnostic algorithm), the acceptance criteria and performance evaluation are centered on safety, functionality, and image quality compared to a predicate device, rather than diagnostic accuracy metrics of an AI.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not explicitly stated as a number of patients or cases in the typical sense for an AI diagnostic study. The document mentions "Sample clinical images were taken for the hardware and software feature." This implies a set of images, but the quantity or characteristics of these images are not detailed.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The phrase "Sample clinical images were taken" suggests existing data, but further details are absent.

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

• Not applicable/not provided in the context of this submission. The "image quality assessment" was performed by implicitly qualified personnel comparing images, but there is no mention of a formal "ground truth" establishment by multiple experts with specific qualifications to evaluate diagnostic accuracy metrics typically derived from AI output.

4. Adjudication Method for the Test Set

• Not applicable/not provided. No formal adjudication method like 2+1 or 3+1 is mentioned, as this is not a study assessing diagnostic accuracy outcomes from an AI.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and Effect Size

• No MRMC comparative effectiveness study was explicitly done to evaluate how human readers improve with AI vs. without AI assistance. The document refers to "MAGNETOM Lumina" as an MRI system, not an AI-assisted diagnostic tool for interpretation. The software feature (GOLiver) is for optimized image acquisition, minimizing user workflow in abdominal/liver MRI, not for diagnostic assistance to human readers.

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

• Not applicable. The MAGNETOM Lumina is an MRI device, which acquires images for a human to interpret. It is not a standalone algorithm meant to provide a diagnosis without human interaction.

7. The Type of Ground Truth Used

• For the "Image quality assessment of the new set of pulse sequences (GOLiver)," the "ground truth" implicitly referred to was a comparison against the image quality produced by the pulse sequences of the predicate device. This is a comparison of technical image characteristics rather than a clinical ground truth (e.g., pathology, surgical findings, long-term outcomes for disease presence).

8. The Sample Size for the Training Set

• Not applicable/not provided. The device is an MRI scanner. While there is software, the document doesn't describe an AI model that underwent "training" in the machine learning sense with a specific training set to learn diagnostic patterns. The "GOLiver" feature is described as "optimized pulse sequences," which implies engineering and parameter tuning, not machine learning model training.

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

• Not applicable/not provided. As there's no mention of a traditional "training set" for an AI model, the concept of establishing ground truth for it is not relevant to this document.

Ask a specific question about this device