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 device, MAGNETOM Avanto Fit with software syngo MR XA70A, consists of new and modified software and hardware that is similar to what is currently offered on the predicate device, MAGNETOM Avanto Fit with syngo MR XA50A (K220151).

A high-level summary of the new and modified hardware and software is provided below:

For MAGNETOM Avanto Fit with syngo MR XA70:

Hardware

New Hardware:
myExam 3D Camera
BM Head/Neck 20

Modified Hardware:
Sanaflex (cushions for patient positioning)

Software

New Features and Applications:
myExam Autopilot Brain
myExam Autopilot Knee
3D Whole Heart
HASTE_interactive
GRE_PC
Open Recon
Deep Resolve Gain
Fleet Reference Scan
Physio logging
complex averaging
AutoMate Cardiac
Ghost Reduction
BLADE diffusion
Beat Sensor
Deep Resolve Sharp
Deep Resolve Boost and Deep Resolve Boost (TSE)
Deep Resolve Boost HASTE
Deep Resolve Boost EPI Diffusion

Modified Features and Applications:
SPACE improvement (high band)
SPACE improvement (incr grad)
Brain Assist
Eco power mode
myExam Angio Advanced Assist (Test Bolus)

The subject device, MAGNETOM Skyra Fit with software syngo MR XA70A, consists of new and modified software and hardware that is similar to what is currently offered on the predicate device, MAGNETOM Skyra Fit with syngo MR XA50A (K220589).

A high-level summary of the new and modified hardware and software is provided below:

For MAGNETOM Skyra Fit with syngo MR XA70:

Hardware

New Hardware:
myExam 3D Camera

Modified Hardware:
Sanaflex (cushions for patient positioning)

Software

New Features and Applications:
Beat Sensor
HASTE_interactive
GRE_PC
3D Whole Heart
Deep Resolve Gain
Open Recon
Ghost Reduction
Fleet Reference Scan
BLADE diffusion
HASTE diffusion
Physio logging
complex averaging
Deep Resolve Swift Brain
Deep Resolve Sharp
Deep Resolve Boost and Deep Resolve Boost (TSE)
Deep Resolve Boost HASTE
Deep Resolve Boost EPI Diffusion
AutoMate Cardiac
SVS_EDIT

Modified Features and Applications:
SPACE improvement (high band)
SPACE improvement (incr grad)
Brain Assist
Eco power mode
myExam Angio Advanced Assist (Test Bolus)

The subject device, MAGNETOM Sola Fit with software syngo MR XA70A, consists of new and modified software and hardware that is similar to what is currently offered on the predicate device, MAGNETOM Sola Fit with syngo MR XA51A (K221733).

A high-level summary of the new and modified hardware and software is provided below:

For MAGNETOM Sola Fit with syngo MR XA70:

Hardware

New Hardware:
myExam 3D Camera

Modified Hardware:
Sanaflex (cushions for patient positioning)

Software

New Features and Applications:
GRE_PC
3D Whole Heart
Ghost Reduction
Fleet Reference Scan
BLADE diffusion
Physio logging
Open Recon
Complex averaging
Deep Resolve Sharp
Deep Resolve Boost and Deep Resolve Boost (TSE)
Deep Resolve Boost HASTE
Deep Resolve Boost EPI Diffusion
AutoMate Cardiac
Implant suite

Modified Features and Applications:
SPACE improvement (high band)
SPACE improvement (incr grad)
Brain Assist
Eco power mode

The subject device, MAGNETOM Viato.Mobile with software syngo MR XA70A, consists of new and modified software and hardware that is similar to what is currently offered on the predicate device, MAGNETOM Viato.Mobile with syngo MR XA51A (K240608).

A high-level summary of the new and modified hardware and software is provided below:

For MAGNETOM Viato.Mobile with syngo MR XA70:

Hardware

New Hardware:
n.a.

Modified Hardware:
Sanaflex (cushions for patient positioning)

Software

New Features and Applications:
GRE_PC
3D Whole Heart
Ghost Reduction
Fleet Reference Scan
BLADE diffusion
Physio logging
Open Recon
Complex averaging
Deep Resolve Sharp
Deep Resolve Boost and Deep Resolve Boost (TSE)
Deep Resolve Boost HASTE
Deep Resolve Boost EPI Diffusion
AutoMate Cardiac
Implant suite

Modified Features and Applications:
SPACE improvement (high band)
SPACE improvement (incr grad)
Brain Assist
Eco power mode

Furthermore, the following minor updates and changes were conducted for the subject devices:

Low SAR Protocol minor update (for all subject devices but MAGNETOM Skyra Fit): the goal of the SAR adaptive protocols was to be able to perform knee, spine, heart and brain examinations with 50% of the max allowed SAR values in normal mode for head and whole-body SAR. The SAR reduction was achieved by parameter adaptations like Flip angle, TR, RF Pulse Type, Turbo Factor, concatenations. For cardiac clinically accepted alternative imaging contrasts are used (submitted with K232494).

Implementation of image sorting prepare for PACS (submitted with K231560).

Implementation of improved DICOM color support (submitted with K232494).

Needle intervention AddIn was added all subject device (submitted with K232494).

Inline Image Filter switchable for users: in the subject device, users have the ability to switch the "Inline image filter" (implicite Filter) on or off. This filter is an image-based filter that can be applied to specific pulse sequence types. The function of the filter remains unchanged from the previous device MAGNETOM Sola with syngo MR XA61A (K232535).

SVS_EDIT is newly added for MAGNETOM Skyra Fit, but without any changes (submitted with K203443)

Brain Assist received an improvement and is identical to that of snygo MR XA61A (K232535)

Open Recon is introduced for all systems. The function of Open Recon remains unchanged from the previous submissions (submitted with K221733).

Lock TR and FA in Bold received a minor UI update

Implant Suite is newly introduced for MAGNETOM Sola Fit and MAGNETOM Viato.Mobile, but without any changes (submitted with K232535)

myExam Autopilot Brain and myExam Autopilot Knee are newly introduced for the subject device MAGNETOM AVANTO Fit and are unchanged from previous submissions (submitted with K221733).

myExam Angio Advanced Assist (Test Bolus) received a bug fixing and minimal UI improvements.

The provided text is an FDA 510(k) clearance letter for various MAGNETOM MRI Systems. While it details new and modified software and hardware features, it does not include specific acceptance criteria or a study that "proves the device meets the acceptance criteria" in terms of performance metrics like sensitivity, specificity, or accuracy for a diagnostic task.

Instead, the document focuses on demonstrating substantial equivalence to predicate devices. This is achieved by:

• Stating that the indications for use are the same.
• Listing numerous predicate and reference devices.
• Detailing hardware and software changes.
• Mentioning non-clinical tests like software verification and validation, sample clinical images, and image quality assessment to show that the new features maintain an "equivalent safety and performance profile" to the predicate devices.
• Referencing scientific publications for certain features to support their underlying principles and utility.
• Briefly describing the training and validation data for two AI features: Deep Resolve Boost and Deep Resolve Sharp, but without performance acceptance criteria or detailed results.

Therefore, much of the requested information cannot be extracted from this document because it is not a study report detailing clinical performance against predefined acceptance criteria for a specific diagnostic outcome.

However, I can extract the information related to the AI features as best as possible from the "AI Features/Applications training and validation" section (Page 16).

Acceptance Criteria and Study Details (Limited to AI Features)

1. Table of Acceptance Criteria and Reported Device Performance

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

• Deep Resolve Boost:
  • Test Set Sample Size: Not explicitly stated as a separate "test set" size. The document mentions "training and validation data" for over 25,000 TSE slices, over 10,000 HASTE slices (for refinement), and over 1,000,000 EPI Diffusion slices. It's unclear what proportion of this was used specifically for final testing, or if the "validation" mentioned includes the final performance evaluation.
  • Data Provenance: Retrospective, described as "Input data was retrospectively created from the ground truth by data manipulation and augmentation." Country of origin is not specified.
• Deep Resolve Sharp:
  • Test Set Sample Size: Not explicitly stated as a separate "test set" size. The document mentions "training and validation" on more than 10,000 high resolution 2D images. Similar to Deep Resolve Boost, it's unclear what proportion was specifically for final testing.
  • Data Provenance: Retrospective, described as "Input data was retrospectively created from the ground truth by data manipulation." Country of origin is not specified.

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 in the document. The definition of "ground truth" for the AI features refers to the acquired datasets themselves rather than expert-labeled annotations. Visual comparisons are mentioned as part of the evaluation, but without details on expert involvement or qualifications.

4. Adjudication method for the test set

This information is not provided in the document. While "visual comparisons" and "visual rating" are mentioned, no specific adjudication method (e.g., 2+1, 3+1) is described.

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 MRMC comparative effectiveness study demonstrating human reader improvement with AI assistance is not described in this document. The focus of the AI features (Deep Resolve Boost and Deep Resolve Sharp) is on image quality enhancement (denoising, sharpness) and reconstruction rather than assisting human readers in a diagnostic task that can be quantified by an effect size.

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

Yes, the evaluation of Deep Resolve Boost and Deep Resolve Sharp, based on metrics like PSNR, SSIM, and perceptual loss, and "visual comparisons" or "visual rating" appears to be an assessment of the algorithm's performance in enhancing image quality in a standalone capacity, without direct human-in-the-loop interaction for diagnosis.

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

• Deep Resolve Boost: "The acquired datasets (as described above) represent the ground truth for the training and validation." This implies the original, full-quality, unaltered MRI scan data. Further, "Input data was retrospectively created from the ground truth by data manipulation and augmentation. This process includes further under-sampling of the data by discarding k-space lines, lowering of the SNR level by addition Restricted of noise and mirroring of k-space data."
• Deep Resolve Sharp: "The acquired datasets represent the ground truth for the training and validation." Similar to Boost, this refers to original, high-resolution MRI scan data. For training, "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."

8. The sample size for the training set

• Deep Resolve Boost:
  • TSE: more than 25,000 slices
  • HASTE (for refinement): 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

• Deep Resolve Boost: The ground truth was established by the "acquired datasets" themselves (full-quality MRI scans). The training input data was then derived from this ground truth by simulating degraded images (e.g., under-sampling, adding noise).
• Deep Resolve Sharp: Similarly, the ground truth was the "acquired datasets" (high-resolution MRI scans). The training input data was derived by cropping k-space data to create corresponding low-resolution inputs.

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.

The subject devices, MAGNETOM Avanto® and MAGNETOM Skyra™ with software syngo MR XA61A, consist of new and modified software and hardware that is similar to what is currently offered on the predicate device, MAGNETOM Sola with syngo MR XA51A (K221733) and MAGNETOM Vida with syngo MR XA50A (K213693).

The provided text is a 510(k) summary for MRI devices (MAGNETOM Avanto fit; MAGNETOM Skyra fit) and does not contain detailed acceptance criteria or a study proving that a specific device meets those criteria in the typical sense for an AI/ML medical device.

This document describes hardware and software updates to existing MR systems, which are general Magnetic Resonance Diagnostic Devices (MRDD). The "acceptance criteria" here are mainly related to maintaining substantial equivalence to predicate devices and conforming to recognized standards for safety and performance (e.g., IEC 60601-1, ISO 14971, NEMA standards for SNR and uniformity, and software validation guidance).

Here's a breakdown based on the information provided, highlighting why it doesn't fit the typical AI/ML device study request:

1. Table of Acceptance Criteria and Reported Device Performance

Instead of specific quantitative performance metrics for a diagnostic task (like sensitivity/specificity for disease detection), the acceptance criteria for these MR systems are based on demonstrating that new and modified components maintain safety and performance comparable to their predicate devices and adhere to relevant standards.

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

The document mentions "sample clinical images" were used for image quality assessment. However, it does not specify the sample size, country of origin, or whether the data was retrospective or prospective.

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 devices are intended for use by "healthcare professionals familiar with and responsible for the acquisition and post processing of magnetic resonance images," and the images are "interpreted by a trained physician" to assist in diagnosis, but it does not detail an expert ground truth establishment process for a specific test set.

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

This information is not provided.

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 such study was mentioned. This submission is for an MR system, not an AI/ML-assisted diagnostic device, so a comparative effectiveness study of human readers with/without AI assistance would not be applicable here.

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

This is not an AI/ML algorithm-only device; it's a general MR system. Therefore, a standalone algorithm performance study is not applicable or mentioned.

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

Given the nature of the device (an MR system), the "ground truth" for image quality assessment would typically be visual comparison by trained MR physicists or radiologists, ensuring that the new sequences or hardware components produce images of diagnostic quality, comparable to, or better than, existing methods. However, the exact type of ground truth (e.g., specific metrics, qualitative expert assessment) is not explicitly stated beyond "image quality assessment by sample clinical images."

8. The sample size for the training set

This information is not applicable. The document describes updates to an MR system, not a machine learning model that requires a training set.

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

This information is not applicable as there is no mention of a training set for a machine learning algorithm.

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/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 Avanto Fit with software syngo MR XA50A includes new and modified hardware and software compared to the predicate device. MAGNETOM Sola with software syngo MR XA31A. A high level summary of the new and modified hardware and software is provided below:

Hardware
Modified Hardware

• Cover: The cover has been modified to bring the system up to the Siemens Healthineers Design incl. all BioMatrix components and interfaces.
• EPC (Electronic Cabinet and Measurement Control / Electronic Power Cabinet): upgrade of components to upgrade the EPC to the newest electronic cabinet series

Software
New Features and Applications

• TSE MoCo: TSE MoCo is an image-based motion correction in the averagedimension for the TSE pulse sequence type.
• Automatic fiducial detection: MR Breast Biopsy is improved with an automatic fiducial detection.
• AbsoluteShim: The AbsoluteShim mode is a shimming procedure based on a 3-echo gradient echo protocol.

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.
  Other Modifications and / or Minor Changes
• The MAGNETOM Avanto Fit is a new MRI System which is the result of an upgrade from a MAGNETOM Avanto

This document describes the regulatory clearance for the Siemens MAGNETOM Avanto Fit, a Magnetic Resonance Diagnostic Device (MRDD). The submission is a 510(k) premarket notification, which demonstrates substantial equivalence to a legally marketed predicate device. This type of submission generally does not require extensive clinical studies or acceptance criteria tables with numerical thresholds, as the focus is on demonstrating that the new device is as safe and effective as an existing one, not necessarily proving novel clinical performance beyond the predicate.

Therefore, the requested information on "acceptance criteria," "study that proves the device meets the acceptance criteria," "sample size," "number of experts," "adjudication method," "MRMC study," "standalone performance," and "ground truth" (as typically defined for AI/CADe device submissions) is not applicable to this 510(k) submission for a conventional MRDD.

This submission focuses on demonstrating that modifications and new features (TSE MoCo, Automatic fiducial detection, AbsoluteShim, Fast GRE RefScan) on the MAGNETOM Avanto Fit do not change its fundamental safety or effectiveness compared to the predicate MAGNETOM Sola.

Here's an explanation based on the provided text, addressing why most of the requested points are not present:

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

• Not applicable in this context. For a 510(k) of a conventional MRDD, "acceptance criteria" are generally met by demonstrating compliance with recognized standards and showing that changes do not introduce new safety concerns or degrade performance compared to the predicate. There isn't a specific performance metric table with numerical targets as would be seen for, say, an AI-driven diagnostic algorithm with a quantifiable output like sensitivity/specificity for a particular disease.
• The performance demonstration implicitly relies on:
  • Image quality assessments: "Image quality assessments by sample clinical images. In some cases a comparison of the image quality / quantitative data was made."
  • Performance bench tests: For new/modified hardware.
  • Software verification and validation: Ensuring new software features function as intended and meet design specifications.
  • Safety tests: Electrical, mechanical, structural, and related system safety tests (compliance with AAMI / ANSI ES60601-1, IEC 60601-2-33).

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

• Not explicitly stated for a dedicated "test set" in the context of clinical performance evaluation. The document mentions "sample clinical images" were used for image quality assessments. These are likely images acquired during internal testing or from a small cohort, but not a large, controlled, prospective dataset for a formal clinical trial of diagnostic accuracy.
• Data Provenance: Not specified, but generally, such internal testing images would be from Siemens' development or internal research facilities.

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

• Not applicable/specified. As no formal clinical trial with an established "ground truth" (e.g., pathology-confirmed diagnosis for a specific disease) was conducted or needed, expert reads for ground truth establishment are not detailed. Image quality assessments would be done by qualified internal personnel, but this isn't the same as clinical ground truth.

4. Adjudication method for the test set:

• Not applicable/specified. No formal adjudication process is described because a clinical diagnostic performance study requiring expert consensus for ground truth was not performed.

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:

• Not applicable. This device is a Magnetic Resonance Diagnostic Device (MRDD), not an AI-assisted diagnostic software. It produces images and spectra that are then interpreted by a trained physician. The new features mentioned (TSE MoCo, Automatic fiducial detection, AbsoluteShim, Fast GRE RefScan) are technical improvements to image acquisition and processing, not AI algorithms intended to directly assist or influence human reader performance in a diagnostic task that would typically be evaluated with an MRMC study.

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

• Not applicable. This refers to a medical imaging device itself, not a separate standalone algorithm.

7. The type of ground truth used:

• Not explicitly defined as a "ground truth" dataset in the clinical sense. For MRDDs, performance is often assessed against engineering specifications, phantom measurements, and the visual quality of clinical images, rather than against a disease-specific "ground truth" (like biopsy results for a target lesion). The "ground truth" for showing substantial equivalence relies on demonstrating that the output (MR images) remains clinically acceptable and safe.

8. The sample size for the training set:

• Not applicable. This device is an MR scanner with modified hardware and software for image acquisition and reconstruction, not an AI algorithm that requires a "training set."

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

• Not applicable. See point 8.

Summary of Device Performance (Based on the document):

The document states:

• "The results from each set of tests demonstrate that the subject device performs as intended and is thus substantially equivalent to the predicate device to which it has been compared."
• "While there are some differences in technical features compared to the predicate device, the differences have been tested and the conclusions from all verification and validation data suggest that the features bear an equivalent safety and performance profile to that of the predicate device and reference devices."

Key tests performed (Nonclinical Tests Section 9):

• Sample clinical images (for image quality assessments)
• Performance bench tests (for new/modified hardware)
• Software verification and validation (for new/modified software features)
• Electrical, mechanical, structural, and related system safety tests (compliance with AAMI / ANSI ES60601-1, IEC 60601-2-33)

In conclusion, this 510(k) submission for a conventional Magnetic Resonance Diagnostic Device (MRDD) primarily relies on non-clinical engineering, software, and image quality testing to demonstrate substantial equivalence, rather than extensive clinical performance studies with specific patient "ground truth" evaluations as would be required for novel AI/CADe devices.

Ask a specific question about this device

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

The subject device, MAGNETOM Avanto® with software syngo MR E11E. is a modification of the previously cleared predicate device, MAGNETOM Avanto" with software syngo MR E11C-AP04 (K173592). The software version syngo E11E for MAGNETOM Avanto™ has been modified to include the software application "Compressed Sensing (CS) Cardiac Cine." This software application was migrated unchanged from the previously cleared MAGNETOM Skyra and Aera systems with syngo MR E11C-AP02 (K163312).

The provided document is a 510(k) summary for the Siemens MAGNETOM Avanto® with software syngo MR E11E. It details the device's substantial equivalence to a predicate device, focusing on a new software feature. However, this document does not contain the specific information required to answer your detailed questions about acceptance criteria and a study proving the device meets those criteria.

The 510(k) summary states:

• No clinical tests were conducted to support the claim of substantial equivalence between the subject and predicate device (page 7).
• Nonclinical performance testing was conducted, including software verification and validation, and performance testing in accordance with FDA guidance documents (page 6). However, it does not provide details of acceptance criteria for these tests or specific results in numerical form that can be presented in a table against a predefined "acceptance criteria."
• The document implies that the "new" feature (Compressed Sensing (CS) Cardiac Cine) was migrated unchanged from a previously cleared device (MAGNETOM Skyra and Aera systems with syngo MR E11C-AP02 (K163312)). This suggests that the performance and safety of this feature were established in the clearance of the reference device, not necessarily re-tested as a new standalone study for this specific 510(k).

Therefore, based solely on the provided text, I cannot extract the following information:

1. A table of acceptance criteria and the reported device performance: This document reports that testing was done and standards were conformed to, but not the specific metrics, thresholds, or measured values.
2. Sample size used for the test set and the data provenance: Clinical test data with sample sizes are not present, and for nonclinical tests, specific "test sets" in the sense of patient data are not detailed.
3. Number of experts used to establish the ground truth and their qualifications: As no clinical study is reported, this information is not applicable to the data provided.
4. Adjudication method for the test set: Not applicable without a clinical study.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and effect size: The document explicitly states "No clinical tests were conducted."
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: While "performance testing" was mentioned for nonclinical data, the specifics of an algorithm-only standalone study with human-level metrics are not provided.
7. The type of ground truth used: Not specified, as clinical data and ground truth establishment methods are not detailed.
8. The sample size for the training set: This is a 510(k) for a hardware/software system, not an AI/ML device that typically has a "training set" in the context of deep learning. The new feature is a "Compressed Sensing (CS) Cardiac Cine" software application, which is a signal processing technique, not necessarily a machine learning algorithm that requires a "training set" in the conventional AI sense.
9. How the ground truth for the training set was established: Not applicable for the reasons mentioned above.

Conclusion based on the provided document:

The 510(k) summary focuses on demonstrating substantial equivalence through:

• Confirmation that the device's indications for use are the same as the predicate device.
• Confirmation that the new software feature ("Compressed Sensing (CS) Cardiac Cine") was migrated unchanged from an already cleared reference device (K163312).
• Compliance with recognized standards (IEC, ISO, NEMA) for safety and software development.
• Software verification and validation testing, and general device performance testing, all non-clinical.

The document does not contain the details of a study with specific acceptance criteria, reported performance metrics, or clinical ground truth establishment as requested in your prompt. This type of detailed performance data is typically found in accompanying test protocols and reports, which are part of the larger 510(k) submission but not always fully summarized in the publicly available 510(k) summary.

Ask a specific question about this device

The MAGNETOM systems are indicated for use as magnetic resonance diagnostic devices (MRDD) that produce transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and or spectra, and that display 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 the physical parameters derived from the inages and/or spectra when interpreted by a trained physician, yield information that may assist in diagnosis.

The MAGNETOM systems described above 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 device, synqo MR E11B system software, is being made available for the following MAGNETOM MR Systems:

• MAGNETOM Aera (24-channel configuration), .
• MAGNETOM Avanto™ ●
• MAGNETOM Skyra™, ●
• . MAGNETOM Prisma and
• . MAGNETOM Prisma™

Two new coils, Body 30/60 and Body 6 long, will be available for the subject device systems. The feature FREEZEit will be extended to other body regions. In addition to the abdomen region, FREEZEit will be extended to other regions such as the head, head and neck, pelvis, and chest region. . The syngo MR E11B SW also includes new sequences as well as minor modifications of already existing features. A high level summary of the new sequences can be viewed below:

DSI
With software version syngo MR E11B Siemens offers DSI for MAGNETOM Prisma, Prismall and Skyra" systems. The DSI option allows diffusion-weighted images to be acquired according to a DSI-compatible q-space sampling scheme.

QISS evaluation
QISS (Quiescent-Interval Single-Shot) MR Angiography is a technique for non-contrastenhanced MR Angiography (non-CEMRA) that is particularly suited for examinations of patients with PAD. Since patients with PAD may also suffer from additional impairments such as renal dysfunction, the administration of contrast agent may often be unadvisable in this patient group. Siemens provides a manageable and optimized QISS workflow for imaging peripheral arteries, which can be easily adapted by the customer based on the patient's needs.

A new "Dot Engine" is provided to ease MRI acquisitions in Radiation Therapy.

RT Dot Engine
RT Dot Engine is a new Dot Engine for aiding in Radiation Therapy planning. The RT Dot Engine does not provide new functionality, but collects and displays existing system information for the user. The RT Dot Engine comprises existing protocols, enhanced with the RT Planning Dot Add-in and the "MPR Planning" interaction step. The RT (Radiation Therapy) Dot Engine is used to ease MRI acquisitions of the head and the head/neck region with stereotactic frames or mask-based fixation techniques. RT Dot Engine is a workflow solution for acquiring MR images intended to aid in Radiation Therapy Planning. RT Dot engine helps streamline acquisition of MR images to be used along with any RT planning software that uses MR images in addition to CT images.

The provided text is a 510(k) summary for a medical device and does not contain the level of detail typically found in a clinical study report regarding acceptance criteria and performance studies for an AI-powered device.

This document describes a Magnetic Resonance Diagnostic Device (MRDD) software upgrade (syngo MR E11B) for existing Siemens MAGNETOM MR systems. The submission is a 510(k) premarket notification, which seeks to demonstrate substantial equivalence to a legally marketed predicate device, rather than proving performance against specific acceptance criteria for a novel AI algorithm.

Therefore, many of the requested details about acceptance criteria, clinical study design, sample sizes, ground truth establishment, and expert adjudication are not present in this type of regulatory document.

However, I can extract the information that is available and clarify what is missing based on the context of a 510(k) submission for an MRI system software upgrade:

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

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

• Sample Size for Test Set: Not explicitly stated as a formal "test set" in the context of an algorithm evaluation. The document mentions "clinical images were provided to support the new coils as well as the new software features," but the number of images or patients is not specified.
• Data Provenance: Not specified. Given the nature of a 510(k) for a software upgrade to an MRI machine, the "clinical images" likely came from internal testing or routine clinical acquisitions.

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)

• The document states "These images and the physical parameters derived from the images and/or spectra when interpreted by a trained physician, yield information that may assist in diagnosis." However, it does not specify the number or qualifications of experts used to establish a formal ground truth for testing the software's performance, as this is an MRI system software upgrade, not a diagnostic AI algorithm.

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

• No adjudication method is mentioned.

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 conducted or reported. This device is a software upgrade for an MRI system, not an AI diagnostic assistant tool.

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

• Not applicable in the context of this device. The software "produces transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and or spectra," which are then "interpreted by a trained physician." It is not a standalone diagnostic algorithm.

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

• For the nonclinical tests (SNR, uniformity, heating, acoustic noise), the "ground truth" would be established by technical specifications and phantom measurements.
• For image quality assessments, a "ground truth" (e.g., against specific diagnostic findings) is not detailed. The assessment likely involved expert review of image quality (e.g., resolution, artifact reduction, diagnostic clarity) rather than a comparison to a definitive clinical ground truth established by pathology or long-term outcomes. The primary focus is on demonstrating that the images produced are diagnostically acceptable and equivalent to the predicate.

8. The sample size for the training set

• Not applicable. This document describes a software upgrade for an MRI system, which includes new sequences and features (e.g., DSI, QISS, RT Dot Engine). It is not an AI algorithm that would typically have a "training set" in the machine learning sense. The software development follows traditional engineering and quality assurance practices.

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

• Not applicable, as no training set (in the AI/ML context) is mentioned for this device.

Ask a specific question about this device

The MAGNETOM Avanto" and the MAGNETOM Skyra" systems are indicated for use as a maqnetic 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 Avanto® and the MAGNETOM Skyra® MR systems 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.

MAGNETOM Avanto® (1.5 T) and MAGNETOM Skyra® (3 T) are similar to the previously cleared MAGNETOM Aera (1.5 T) and MAGNETOM Skyra (3 T) systems utilizing a superconducting magnet design. The open bore, whole body scanners are designed for increased patient comfort. They focus on ergonomics and usability to reduce complexity of the MR workflow.

The MAGNETOM Avanto® and the MAGNETOM Skyra® systems will be offered as an upgrade to the currently installed MAGNETOM Avanto and MAGENTOM Verio systems. The MAGNETOM Avanto® will also be offered as ex-factory (new production).

The provided text describes a 510(k) premarket notification for Siemens' MAGNETOM Avanto-Fit and MAGNETOM Skyra-Fit MR systems. This document primarily focuses on establishing substantial equivalence to previously cleared predicate devices rather than providing detailed acceptance criteria and a specific study proving the device meets those criteria, as one would expect for an AI/ML powered device.

The devices in question are magnetic resonance diagnostic devices (MRDDs), which are hardware systems, not AI models. Therefore, the typical "acceptance criteria" and "study" an AI/ML device would undergo (e.g., performance metrics like sensitivity, specificity, AUC, human reader improvement) are not applicable here.

However, based on the information provided, I can extract the safety and performance measurements that serve as the "acceptance criteria" for these MRI systems and how their equivalence was asserted rather than "proven through a study" in the AI/ML sense.

1. Table of Acceptance Criteria and Reported Device Performance

For an MRI device, acceptance criteria are generally related to safety and imaging performance standards. These are listed as "General Safety and Effectiveness Concerns" and "measurements of performance and safety data."

Explanation of "Reported Device Performance": The document does not provide specific numerical outcomes for each of these criteria for the new devices. Instead, it asserts that "Operation of the MAGNETOM Avanto™ (1.5T) and the MAGNETOM Skyra™ (3T) systems with syngo® MR VD13B software is substantially equivalent to the commercially available MAGNETOM Aera (1.5T) and MAGNETOM Skyra (3T) Systems with syngo® MR VD13A SW (K121434)." And, "performance measurements have been done on the predicate devices MAGNETOM Avanto and MAGNETOM Verio to show that the performance of the MAGNETOM Avanto® and MAGNETOM Skyra™ with syngo® MR VD 13B Software is equivalent with respect to the predicate devices." This implies that the new devices were tested against the same standards that the predicate devices met, demonstrating equivalence.

The subsequent questions (2-9) are highly specific to AI/ML device studies involving ground truth establishment, expert review, and sample sizes for training/test sets. Since the provided text describes a submission for an MRI hardware system and not an AI/ML algorithm, these questions are largely not applicable or cannot be answered from the provided text.

Here's why and what can be inferred:

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

• Not applicable for a hardware device in this context. The "test set" for an MRI hardware system typically involves phantom measurements and potentially human volunteer studies for safety and performance, not a dataset of medical images for AI performance evaluation. The document mentions "performance measurements have been done on the predicate devices" to show equivalence, but specific "sample sizes" (e.g., number of patients/scans in an image dataset) are not provided as it's not an AI evaluation.

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 applicable. Ground truth in the AI/ML sense (e.g., disease presence/absence for image interpretation) is not established for the device's performance itself in this submission. The device produces images, which are then interpreted by a trained physician (as stated in the "Intended Use"). This refers to the end-user clinical interpretation, not ground truth for algorithm training/testing.

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

• Not applicable. No adjudication method for a test set is described as this is a hardware device submission, not an AI algorithm study.

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. This document explicitly concerns the MRI hardware system itself, not an AI-assisted diagnostic tool. Therefore, no MRMC study or effect size related to AI assistance is presented.

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

• No. This is a hardware device. The concept of an "algorithm only" performance study is not relevant here.

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

• Not applicable. For an MRI hardware system, "ground truth" relates to physical measurements (e.g., geometric accuracy measured against known phantoms, signal-to-noise ratios in controlled environments), not clinical pathology or outcomes data in the context of an AI algorithm's diagnostic accuracy.

8. The sample size for the training set

• Not applicable. This submission is for MRI hardware. There is no AI model "training set" described in the context of this document.

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

• Not applicable. No AI model training set is mentioned.

Ask a specific question about this device