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.

MAGNETOM Amira and MAGNETOM Sempra with syngo MR XA50M include new and modified features comparing to the predicate devices MAGNETOM Amira and MAGNETOM Sempra with syngo MR XA12M (K183221, cleared on February 14, 2019).

The provided document is a 510(k) summary for the Siemens MAGNETOM Amira and Sempra MR systems, detailing their substantial equivalence to predicate devices. It describes new and modified hardware and software features, including AI-powered "Deep Resolve Boost" and "Deep Resolve Sharp."

However, the document does not contain the detailed information necessary to fully answer the specific questions about acceptance criteria and a study proving the device meets those criteria, particularly in the context of AI performance. The provided text is a summary for regulatory clearance, not a clinical study report.

Specifically, it lacks:

• Concrete, quantifiable acceptance criteria for the AI features (e.g., a specific PSNR threshold that defines "acceptance").
• A comparative effectiveness study (MRMC) to show human reader improvement with AI assistance.
• Stand-alone algorithm performance metrics for the AI features (beyond general quality metrics like PSNR/SSIM, which are not explicitly presented as acceptance criteria).
• Details on expert involvement, adjudication, or ground truth establishment for a test set used for regulatory acceptance, as the "test statistics and test results" section refers to quality metrics and visual inspection, and "clinical settings with cooperation partners" rather than a formal test set for regulatory submission.

The "Test statistics and test results" section for Deep Resolve Boost mentions "After successful passing of the quality metrics tests, work-in-progress packages of the network were delivered and evaluated in clinical settings with cooperation partners." It also mentions "seven peer-reviewed publications" covering 427 patients which "concluded that the work-in-progress package and the reconstruction algorithm can be beneficially used for clinical routine imaging." This indicates real-world evaluation but does not provide specific acceptance criteria or detailed study results for the regulatory submission itself.

Based on the provided text, here's what can be extracted and what is missing:

1. Table of acceptance criteria and reported device performance:

The document does not explicitly state quantifiable "acceptance criteria" for the AI features (Deep Resolve Boost and Deep Resolve Sharp) that were used for regulatory submission. Instead, it describes general successful evaluation methods:

• Successful passing of quality metrics tests (PSNR, SSIM)
• Visual inspection to detect potential artifacts
• Evaluation in clinical settings with cooperation partners
• No misinterpretation, alteration, suppression, or introduction of anatomical information reported | Deep Resolve Boost:
• Impact characterized by PSNR and SSIM. Visual inspection conducted for artifacts.
• Evaluated in clinical settings with cooperation partners.
• Seven peer-reviewed publications (427 patients on 1.5T and 3T systems, covering prostate, abdomen, liver, knee, hip, ankle, shoulder, hand and lumbar spine).
• Publications concluded beneficial use for clinical routine imaging.
• No reported cases of misinterpretation, altered, suppressed, or introduced anatomical information.
• Significant time savings reported in most cases by enabling faster image acquisition. |
  | For Deep Resolve Sharp:
• Successful passing of quality metrics tests (PSNR, SSIM, perceptual loss)
• In-house visual rating
• Evaluation of image sharpness by intensity profile comparisons of reconstruction with and without Deep Resolve Sharp | Deep Resolve Sharp:
• Impact characterized by PSNR, SSIM, and perceptual loss.
• Verified and validated by in-house tests, including visual rating and evaluation of image sharpness by intensity profile comparisons.
• Both tests showed increased edge sharpness. |

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

The document mixes "training" and "validation" datasets. It doesn't explicitly refer to a separate "test set" for regulatory evaluation with clear sample sizes for that purpose. The "Test statistics and test results" section refers to general evaluations and published studies.

• "Validation" Datasets (internal validation, not explicitly a regulatory test set):
  • Deep Resolve Boost: 1,874 2D slices
  • Deep Resolve Sharp: 2,057 2D slices
• Data Provenance (Training/Validation):
  • Source: For Deep Resolve Boost: "in-house measurements and collaboration partners." For Deep Resolve Sharp: "in-house measurements."
  • Origin: Not specified by country.
  • Retrospective/Prospective: "Input data was retrospectively created from the ground truth by data manipulation and augmentation" (for Boost) and "retrospectively created from the ground truth by data manipulation" (for Sharp). This implies the underlying acquired datasets were retrospective.
• "Clinical Settings" / Publications (Implied real-world evaluation, not a regulatory test set):
  • Deep Resolve Boost: "a total of seven peer-reviewed publications 427 patients"
  • Data Provenance: Not specified by origin or retrospective/prospective for these external evaluations.

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. It mentions "visual inspection" and "visual rating," but does not detail the number or qualifications of experts involved in these processes for the "validation" sets or any dedicated regulatory "test set." For the "seven peer-reviewed publications," the expertise of the authors is implied but not detailed as part of the regulatory submission.

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

This information is not provided in the document.

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:

A formal MRMC comparative effectiveness study demonstrating human reader improvement with AI assistance is not described in this document. The document focuses on the technical performance of the AI features themselves and their general clinical utility as reported in external publications (e.g., faster imaging, no misinterpretation), but not a comparative study of human performance with and without the AI.

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

Yes, the sections on "Test statistics and test results" for both Deep Resolve Boost and Deep Resolve Sharp describe evaluation of the algorithm's performance using quality metrics (PSNR, SSIM, perceptual loss) and visual/intensity profile comparisons. This implies standalone algorithm evaluation. No specific quantifiable results for these metrics are provided as acceptance criteria, only that tests were successfully passed and showed increased sharpness for Deep Resolve Sharp.

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

The ground truth for the AI training and validation datasets is described as:

• Deep Resolve Boost: "The acquired datasets represent the ground truth for the training and validation. Input data was retrospectively created from the ground truth by data manipulation and augmentation." This implies that the original, full-quality MR images serve as the ground truth.
• 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." Similarly, the original, high-resolution MR images are the ground truth.

This indicates the ground truth is derived directly from the originally acquired (presumably high-quality/standard) MRI data, rather than an independent clinical assessment like pathology or expert consensus. The AI's purpose is to reconstruct a high-quality image from manipulated or undersampled input, so the "truth" is the original high-quality image.

8. The sample size for the training set:

• Deep Resolve Boost: 24,599 2D slices
• Deep Resolve Sharp: 11,920 2D slices

Note that the document states: "due to reasons of data privacy, we did not record how many individuals the datasets belong to. Gender, age and ethnicity distribution was also not recorded during data collection."

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

As described in point 7:

• Deep Resolve Boost: The "acquired datasets" (original, full-quality MR images) served as the ground truth. Input data for the AI model was then "retrospectively created from the ground truth by data manipulation and augmentation," including undersampling, adding noise, and mirroring k-space data.
• Deep Resolve Sharp: The "acquired datasets" (original MR images) served as the ground truth. Input data was "retrospectively created from the ground truth by data manipulation," specifically by cropping k-space data so only the center part was used as low-resolution input, with the original full data as the high-resolution output/ground truth.

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 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 images and/or spectra and the physical parameters derived from the images and/or spectra when interpreted by a trained physician vield information that may assist in diagnosis.

Your MAGNETOM MR 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.

Software syngo MR XA12M is the latest software version for MAGNETOM Amira and MAGNETOM Sempra. It supports the existing "A Tim+Dot system" configuration for MAGNETOM Amira and MAGNETOM Sempra, and the newly introducted "A BioMatrix system" configuration for MAGNETOM Amira. Software version syngo MR XA12M for MAGNETOM Amira and MAGNETOM Sempra includes software applications migrated from the secondary predicate device MAGNETOM Sola with syngo MR XA11A (K181322). Only minor adaptations were needed to support the system specific hardware and optimize the sequences/protocols. In addition, new software features, Segmented TOF, HASTE with variable flip angle, SMS in RESOLVE and QDWI, are also introduced in syngo XA12M. The device also includes hardware updates such as new/modified coils and other components.

This document describes the 510(k) premarket notification for the Siemens MAGNETOM Amira and MAGNETOM Sempra Magnetic Resonance Diagnostic Devices (MRDD) with software syngo MR XA12M. The submission aims to demonstrate substantial equivalence to previously cleared predicate devices.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for this device are not explicitly stated in terms of specific performance metrics (e.g., sensitivity, specificity, accuracy). Instead, substantial equivalence is claimed based on adherence to recognized standards, verification and validation testing, and image quality assessments. The reported device performance is broadly presented as performing "as intended" and exhibiting an "equivalent safety and performance profile" to the predicate devices.

The table below summarizes the technological changes and the general assessment of their performance as described in the submission:

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

The document does not specify a distinct "test set" with a quantifiable sample size (e.g., number of patients or images). The evaluation relies on "sample clinical images" for the new coils and software features. The provenance of this data (e.g., country of origin, retrospective or prospective collection) is also not detailed.

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

The document does not explicitly state the number of experts used or their specific qualifications for establishing ground truth for the "sample clinical images." The indication for use mentions that "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." This implies that the interpretation of images, including those used in performance testing, would be by a "trained physician," but no specific details are provided about the number or expertise of such individuals in the context of validating the device features.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for the "sample clinical images" used in performance testing.

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

No MRMC comparative effectiveness study is mentioned. The submission focuses on demonstrating substantial equivalence through non-clinical performance testing and adherence to standards, rather than evaluating the improvement of human readers with or without AI assistance.

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

The primary purpose of the device (MAGNETOM MR system) is to produce images, and the software features enhance image acquisition and processing. The performance testing described (image quality assessments, software verification and validation) evaluates the algorithm's output (images) in a standalone manner prior to a physician's interpretation. However, the device's indications for use inherently involve human interpretation ("when interpreted by a trained physician"). The document does not describe a purely "algorithm-only" performance assessment in the context of clinical decision-making, as the device's function is to aid diagnosis by a human.

7. The Type of Ground Truth Used

The type of ground truth for the "sample clinical images" is not explicitly stated. Given that no clinical trials were conducted, it's highly probable that qualitative "image quality assessments" were made by internal experts or against known phantom/in-vivo characteristics, and potentially compared to images from the predicate device. There is no mention of pathology, expert consensus (beyond general physician interpretation), or outcomes data being used as ground truth for this submission.

8. The Sample Size for the Training Set

The document does not mention a "training set" in the context of machine learning or AI algorithms. The changes are largely software and hardware updates, along with the integration of existing features from a predicate device. If any of the new features (e.g., Segmented ToF, HASTE with variable flip angle) involve learned components, the training set size and characteristics are not disclosed.

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

Since no training set is discussed or implied for machine learning, the method for establishing ground truth for a training set is not described. The software and hardware updates appear to be based on engineering development and optimization rather than machine learning model training.

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 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 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 when performed with MR compatible devices such as in-room displays and MR Safe biopsy needles.

The subject device, MAGNETOM Amira with syngo MR E11S, is a modification of the previously cleared predicate device, MAGNETOM Amira with syngo MR E11N (K152283). Software version syngo E11S for MAGNETOM Amira includes software applications migrated from the previously cleared MAGNETOM Aera systems with syngo MR E11C and E11C - AP02 (K153343 and K163312). Only minor adaptations were needed to support the system specific hardware and optimize the sequence/protocols. The following are the software applications migrated from previously cleared software to the subject device:

• . fast TSE
  • o Improvements in BLADE Imaging
• SMS EPI .
  • o Simultaneous Multi Slice Imaging
• Quiet DWI .
  • o Noise reduced sequence for diffusion weighted imaging
• GOBrain ●
  • o Supports brain examination in short acquisition time
• GOBrain+ ●
  • o GOBrain adaptation to support protocols developed for contrast enhanced imaging of the brain

Listed below are the hardware updates to the MAGNETOM Amira with syngo MR E11S:

• Updated MRAWP/MRWP (Syngo Acquisition Workplace/ Syngo Workplace) . based on the new host platform-HP Z440.
• Endorectal interface and adapter to connect the Endorectal Coil (to be ordered . separately) to the MAGNETOM Amira systems.

The MAGNETOM Amira with software version syngo MR E11S will be offered ex-factory (new production) as well as in-field upgrades for the currently installed MAGNETOM Amira systems.

This document describes the MAGNETOM Amira with software syngo MR E11S device. Based on the provided text, the device is a modification of a previously cleared Magnetic Resonance Diagnostic Device (MRDD) and no new acceptance criteria or new studies were performed to prove the device meets acceptance criteria. Instead, the manufacturer argues for substantial equivalence to existing predicate devices.

Here's an analysis based on the information provided and what can be inferred about the "acceptance criteria" through the lens of substantial equivalence for this type of device:

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

The provided document does not explicitly state specific acceptance criteria (e.g., in terms of sensitivity/specificity/accuracy) or quantitative performance metrics for the MAGNETOM Amira with software syngo MR E11S.

The "acceptance criteria" for this device, being a modification of an existing MRDD, are implicitly tied to demonstrating that it performs as intended and is as safe and effective as its predicate devices. This is shown through verification and validation activities (non-clinical performance testing) and by confirming that the technological characteristics and indications for use are substantially equivalent to cleared devices.

The reported device performance is that it "performs as intended" and demonstrates "equivalent safety and performance profile" as the predicate device.

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: The document mentions that "sample clinical images were taken for the endorectal coil." It does not specify the number of images or cases.
• Data Provenance: The document does not specify the country of origin of these "sample clinical images" or whether they were retrospectively or prospectively collected.

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)

This information is not provided in the document. Given that no clinical studies were performed to establish new performance metrics, it's unlikely that a formal ground truth establishment process involving multiple experts for a test set was undertaken for this substantial equivalence submission. The interpretation of images for diagnosis as mentioned in the Indications for Use is "by a trained physician," but this pertains to the general use of the device, not specific to establishing ground truth for a new performance study.

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

This information is not provided in the document.

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 stated: "No clinical tests were conducted to support the claim of substantial equivalence between the subject and predicate device." This device is a Magnetic Resonance Diagnostic Device, and the document doesn't indicate it incorporates AI for interpretation or assistance, thus the question of human reader improvement with AI is not applicable here.

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

This device is an MR system, a hardware and software diagnostic device for image acquisition and display. It is not an algorithm-only standalone diagnostic tool, and therefore, standalone algorithmic performance in the context of AI is not relevant or evaluated here. The performance is of the entire MR system.

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

Given that "No clinical tests were conducted," and the primary evaluation was for substantial equivalence through non-clinical performance testing and software verification/validation, a formal "ground truth" as typically established for new diagnostic accuracy claims (e.g., pathology-confirmed cases) was not used for this submission. The "sample clinical images" would likely have been used to subjectively confirm expected image quality and functionality, rather than for a quantitative ground truth comparison.

8. The sample size for the training set

This device is an MR diagnostic system, not an AI model that requires a distinct training set. The software updates are "migrated from previously cleared software," implying reuse and adaptation of existing, validated code and functionalities. Therefore, the concept of a "training set" in the context of machine learning does not apply here.

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

As the concept of a training set for an AI model is not applicable to this device as described, the establishment of ground truth for a training set is not relevant.

Ask a specific question about this device

MAGNETOM Amira 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.

MAGNETOM Amira 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 Amira (1.5T) is an MRI svstem that is substantially equivalent to the previously cleared primary predicate device MAGNETOM Aera (K141977, cleared November 19, 2014) and secondary predicate device MAGNETOM ESSENZA (K130262, cleared Mach 1, 2013).

The MAGNETOM Amira utilizes a superconducting magnet design. The open bore, whole body scanners are designed for increased patient comfort. They focus on ergonomics and usability to simplify the MR workflow.

The MAGNETOM Amira systems will be available in a fixed configuration.

This document describes the FDA 510(k) clearance for the Siemens MAGNETOM Amira with Software syngo MR E11, a magnetic resonance diagnostic device (MRDD). It does not contain information about acceptance criteria for an AI/ML powered device, nor does it detail a study proving such a device meets acceptance criteria.

The document primarily focuses on demonstrating substantial equivalence to previously cleared predicate devices (MAGNETOM Aera and MAGNETOM ESSENZA) based on its intended use and technological characteristics, not on the performance of an AI-powered component.

Therefore, I cannot extract the requested information regarding acceptance criteria, device performance, sample sizes, ground truth, or MRMC studies related to an AI component, as this information is not present in the provided text.

The information provided pertains to the device itself (MAGNETOM Amira) as a magnetic resonance diagnostic device, and not to an AI/ML algorithm within or associated with it.

Ask a specific question about this device