Search Results

MR-Touch™, is a software and hardware option intended for use with GE Signa® MR systems. It is indicated for magnetic resonance imaging of the human body.

MR-Touch™ generates transverse sectional information related to the relative stiffness of soft tissue. It consists of hardware as well as acquisition and reconstruction software. The hardware components induce vibrations into the scan subject. The MR-Touch™ acquisition software is an evolutionary improvement to the gradient echo sequence. The sequence synchronizes the induced vibrations to acquire a series of phase-contrast images over time. The phase-contrast imaging technique measures motion or displacement. The displacement from the induced vibrations is detected using the timeseries of phase-contrast images. The displacement information is reconstructed and presented as strain wave and relative stiffness images.

When used with a GE Signa® MR system, MR-Touch™ is capable of producing transverse images of internal body structures such as muscle and liver.

When interpreted by a trained physician, these images may provide information that can be useful in determining a diagnosis.

MR-Touch™ is a combined software and hardware accessory for use with a GE Signa® MR System. It is an evolutionary improvement of the existing phase-contrast imaging feature included with existing GE Signa® MR Systems. The Resoundant hardware component consists of an acoustic wave generator coupled through a length of flexible tubing with a passive transducer to induce small vibrations in the scan subject. The software includes both image acquisition and reconstruction components. The acquisition software is a gradient echo sequence that acquires a series of phase-contrast images over time. It also synchronizes the low frequency and low magnitude induced vibrations generated by Resoundant. The phase-contrast imaging technique measures motion or displacement. During reconstruction, the displacement from the induced vibrations is detected using the timeseries of phase-contrast images. MR-Touch™ then presents the reconstructed displacement information as strain wave and relative stiffness images (referred to as Elastograms).

The GE Healthcare MR-Touch™ Option for GE Signa® MR Systems is an accessory designed to generate transverse sectional information related to the relative stiffness of soft tissue. It comprises hardware for inducing vibrations and software for image acquisition and reconstruction. The primary claim is substantial equivalence to existing MR systems and elastography ultrasound systems.

1. Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria for the MR-Touch™ Option in terms of clinical performance metrics (e.g., sensitivity, specificity, accuracy) for a specific diagnostic task. Instead, the "acceptance" is based on demonstrating substantial equivalence to predicate devices and verifying certain functional aspects.

2. Sample Size and Data Provenance (for test set)

The document is unclear regarding a dedicated "test set" in the context of clinical performance evaluation. The "Summary of Studies" mentions "Sample images" and "confidence studies" but gives no specifics on:

• Sample Size: Not specified for any performance evaluation.
• Data Provenance: Not specified (e.g., country of origin, retrospective or prospective). It is common for 510(k) submissions, especially for accessories and evolutionary improvements, to rely on internal testing, phantoms, and existing predicate device performance rather than large-scale clinical studies.

3. Number and Qualifications of Experts for Ground Truth

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.
• Ground Truth Establishment: The document does not describe how ground truth was established for any "test set." The statement "When interpreted by a trained physician, these images may provide information that can be useful in determining a diagnosis" suggests diagnostic interpretation by a physician is the intended clinical use, but this is not defined as a ground truth mechanism for device validation.

4. Adjudication Method

Not discussed or specified. Given the nature of the submission (substantial equivalence based on technical and functional similarity rather than a new clinical claim requiring high-stakes diagnostic accuracy), a formal adjudication method for a test set is unlikely to have been implemented or required.

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

No MRMC comparative effectiveness study is mentioned. The submission focuses on the device's technical performance and equivalence to existing technologies, not on improving human reader performance with or without AI assistance. The "AI" component here is the image processing and reconstruction software, not a diagnostic AI intended to aid human readers.

6. Standalone Performance Study

The "Summary of Studies" section describes "confidence studies" that "prove that MR-Touch™ produces repeatable results and can reliably differentiate between tissues of different stiffness." This inherently evaluates the standalone performance of the algorithm in generating the strain wave and elastogram outputs. However, specific performance metrics (e.g., accuracy against a known stiffness standard, precision) are not provided. The study does not describe a "human-in-the-loop" component for these specific tests, making them standalone evaluations of the device's ability to produce consistent and differentiate images.

7. Type of Ground Truth Used

For the "confidence studies" demonstrating repeatability and differentiation of stiffness, the ground truth would most likely have been:

• Phantom Studies: Using materials with known and varied stiffness properties.
• Known Physical Properties: Measuring the physical properties of the materials used in the "confidence studies" (e.g., using a mechanical testing device to confirm differences in stiffness).
• The document implies the output (elastograms) themselves are the useful information, rather than a comparison to an external clinical ground truth like pathology or outcomes data.

8. Sample Size for the Training Set

The document does not mention any "training set" in the context of machine learning. The MR-Touch™ system is described as an "evolutionary improvement" to existing gradient echo sequences and phase-contrast imaging, implying traditional image processing and reconstruction algorithms rather than a deep learning model that requires a labeled training set.

9. How Ground Truth for the Training Set Was Established

Not applicable, as no training set for machine learning is described.

Ask a specific question about this device

The Optima MR450w is a whole body magnetic resonance scanner designed to support high resolution and high signal-to-noise ratio images in short exam times. It is indicated for use as a diagnostic imaging device to produce axial, sagittal, coronal, and oblique anatomical images, spectroscopic data, parametric maps, or dynamic images of the structures or functions of the entire body. The indication for use includes, but is not limited to, head, neck, TMJ, spine, breast, heart, abdomen, pelvis, joints, prostate, blood vessels, and musculoskeletal regions of the body. Depending on the region of interest being imaged, contrast agents may be used.

The images produced by the Optima MR450w reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance. These images and spectra, when interpreted by a trained physician yield information that may assist in diagnosis.

The 1.5T GE Optima MR450w features a superconducting magnet operating at 1.5 Tesla. The data acquisition system accommodates up to 32 independent receive channels in various increments, and multiple independent coil elements per channel during a single acquisition series. The system uses a combination of time-varying magnetic fields (gradients) and RF transmissions to obtain information regarding the density and position of elements exhibiting magnetic resonance. The system can image in the sagittal, coronal, axial, oblique and double oblique planes, using various pulse sequences and reconstruction algorithms.. The 1.5T GE Optima MR450w is designed to conform to NEMA DICOM standards (Digital Imaging and Communications in Medicine).

The GE Optima MR450w is a whole-body magnetic resonance scanner. The provided text, a 510(k) summary, outlines its safety and performance characteristics in comparison to a predicate device, the GE Discovery® MR450 System (K083147).

Here's an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly state quantitative acceptance criteria or a direct "reported device performance" table in the format usually seen for diagnostic algorithms. Instead, it refers to compliance with established standards (NEMA, IEC, ISO) and states that performance parameters were "measured and documented through testing to NEMA, IEC or ISO standards."

However, based on the Summary of Studies section, the performance parameters evaluated and implicitly deemed acceptable are:

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

The document does not specify a "test set" in the context of an algorithm or AI model evaluation. The studies described are physical performance and safety tests of the MR scanner itself. Therefore, sample sizes for medical images or patient data are not relevant or provided here. The tests are in accordance with NEMA, IEC, or ISO standards, which dictate the procedures and specifications for evaluating MR system performance and safety.

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

This information is not applicable. The studies concern the fundamental physical and electrical performance of the MR scanner, not the diagnostic accuracy of interpretations based on images from the device. Ground truth, in this context, would be established by validated measurement equipment and adherence to engineering and safety standards, rather than expert interpretation of medical images.

4. Adjudication Method for the Test Set:

Not applicable, as there's no "test set" of medical images or diagnostic interpretations being adjudicated. The tests are objective measurements against published standards.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size:

No, an MRMC comparative effectiveness study was not done. This document describes the substantial equivalence of a new MR scanner model to a predicate device, focusing on its physical and safety performance. It does not involve human readers interpreting images with or without AI assistance, nor does it measure the effect size of AI on human reader performance.

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

No, a standalone algorithm performance study was not done. The device is an MR imaging hardware system, not an AI algorithm.

7. The Type of Ground Truth Used:

The ground truth for the evaluations described is based on established engineering, safety, and performance standards as defined by organizations like NEMA, IEC, and ISO. These standards dictate acceptable ranges and methodologies for measuring parameters such as SNR, geometric distortion, SAR, and acoustic noise. The "truth" is whether the device's measured performance falls within the specified limits of these standards.

8. The Sample Size for the Training Set:

Not applicable. The document is about the hardware and core functionality of an MR scanner, not an AI or machine learning model. Therefore, there is no "training set."

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

Not applicable, for the same reasons as above.

Ask a specific question about this device

The Discovery MR450 is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan times. It is indicated for use as a diagnostic imaging device to produce axial, sagittal, coronal, and oblique images, spectroscopic images, parametric maps, and/or spectra, dynamic images of the structures and/or functions of the entire body, including, but not limited to, head, neck, TMJ, spine, breast, heart, abdomen, pelvis, joints, prostate, blood vessels, and musculoskeletal regions of the body. Depending on the region of interest being imaged, contrast agents may be used.

The images produced by the Discovery MR450 reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance. These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

The GE Discovery MR450 is a new MR system that is substantially equivalent to previously cleared 1.5T /3.0T MR systems. All utilize superconducting magnets, gradients, and radio frequency coils and electronics to acquire data in single voxel, two dimensional, or three dimensional datasets. The 1.5T GE Discovery MR450 features a superconductina magnet operating at 1.5 Tesla. The data acquisition system accommodates up to 32 independent receive channels in various increments, and multiple independent coil elements per channel during a single acquisition series. The system uses a combination of time-varying magnetic fields (aradients) and RF transmissions to obtain information regarding the density and position of elements exhibiting magnetic resonance. The system can image in the sagittal, coronal, axial, oblique and double oblique planes, using various pulse sequences and reconstruction algorithms.. The 1.5T GE Discovery MR450 is designed to conform to NEMA DICOM standards (Diaital Imagina and Communications in Medicine).

The provided text is a 510(k) Premarket Notification for the GE Discovery MR450. It does not contain information about acceptance criteria and a study proving the device meets those criteria in the typical format of a clinical or performance study evaluating an AI/diagnostic algorithm's accuracy, sensitivity, or specificity.

Instead, this document focuses on demonstrating substantial equivalence to predicate devices. The "performance" section refers to technical specifications and compliance with standards rather than clinical performance metrics against a defined ground truth.

Here's an analysis based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" for a diagnostic performance study, nor does it report specific "device performance" in terms of clinical accuracy, sensitivity, or specificity in the context of disease detection or diagnosis.

The "Performance" section outlines parameters that have been measured and documented through testing to NEMA, IEC, or ISO standards, suggesting the acceptance criteria are adherence to these technical standards.

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

This information is not provided in the document. The document refers to testing "to NEMA, IEC or ISO standards" for technical parameters, not a clinical test set with patient data.

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

This information is not provided. The document does not describe a test set that would require expert-established ground truth in a diagnostic context.

4. Adjudication Method for the Test Set

This information is not provided. An adjudication method is not applicable given the type of testing described.

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

No, an MRMC comparative effectiveness study was not done or described in this submission. The submission focuses on substantial equivalence based on technical specifications and indications for use, not on improving human reader performance with AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study was Done

This document describes a medical imaging device (MRI scanner), not an AI algorithm. Therefore, a standalone algorithm performance study is not applicable and was not done.

7. The Type of Ground Truth Used

The concept of "ground truth" as pathology, outcomes data, or expert consensus is not applicable to the type of technical performance testing described for an MRI scanner in this submission. The ground truth for parameters like "Signal-to-noise ratio" or "Geometric distortion" would be defined by the measurement standards themselves (e.g., specific phantoms and procedures).

8. The Sample Size for the Training Set

This information is not provided. The document describes an MRI system, not a device incorporating a machine learning or AI component that would have a "training set."

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

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

Summary of the Study for Substantial Equivalence:

The "study" described in the 510(k) is a comparison to predicate devices and technical testing to established industry standards (NEMA, IEC, ISO). The document states:

• "As stated in the FDA document 'Guidance for the Submission of Premarket Notifications for Magnetic Resonance Diagnostic Devices' the following parameters have been measured and documented through testing to NEMA, IEC or ISO standards..." (Section 3)

The parameters tested include:

• Performance: Signal-to-noise ratio (SNR), Geometric distortion, Image uniformity, Slice thickness, Spatial resolution
• Safety: Static field strength, Acoustic noise, dB/dt, RF heating (SAR), Biocompatibility

The conclusion is that the GE Discovery MR450 is substantially equivalent to the predicate GE 1.5T Signa® HDx MR System and GE Signa® MR750, based on similar indications for use, technical specifications, and compliance with relevant industry and safety standards. There is no mention of clinical accuracy or diagnostic performance studies involving patients or human readers.

Ask a specific question about this device

BrainStat is an automated post-processing software option that is designed to process a time-series of MR images acquired in the brain. BrainStat is indicated for use on dynamic magnetic resonance imaging data sets to depict parametric images that are calculated from the image intensity variations over time. These parametric images include the integrated-area of the signal intensity change, the time from the beginning of the change of intensity to the end of the intensity change, and the ratio of the integrated area to the time.

BrainStat provides information that when interpreted by a trained physician, can be useful in determining a diagnosis.

The BrainStat Software Option is a software application to be used on GE Signa MR scanners. It is an evolutionary improvement to the post-processing application known as FuncTool on the HDx 1.5T and 3.0T MRI scanners (K052293).

The provided text does not contain information about acceptance criteria or specific study details proving that the device meets those criteria. The document is a 510(k) summary and an FDA clearance letter, which primarily focuses on demonstrating substantial equivalence to a predicate device for market clearance, rather than detailing performance studies against specific acceptance criteria.

Therefore, I cannot provide the requested table or answer the questions regarding sample sizes, data provenance, expert involvement, adjudication methods, MRMC studies, standalone performance, or ground truth establishment.

The document states: "This premarket notification submission demonstrates that the BrainStat software option is substantially equivalent to an analogous feature in Esaote's Dynamic MRI Software Option for C-scan, E-scan XQ and E-scan Opera because it has the same intended use and functionality." This indicates that the primary "study" or justification for clearance was a comparison of intended use and functionality to a predicate device, rather than a separate performance study with defined acceptance criteria.

Ask a specific question about this device

The GE Signa® HDe MR system is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan times. The Signa® HDe MR system is indicated for use as a diagnostic imaging device to produce axial sagittal, coronal and oblique images, spectra, dynamic images of the internal structures and organs of the entire body, including, but not limited to, head, neck, TMJ, spine, breast, heart, abdomen, pelvis, joints, prostate, blood vessels, and musculoskeletal regions of the body. The images produced by the Signa® HDe system reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

The 1.5T Signa® HDe MR systems are a modification to the previously cleared MR systems K052293 which utilizes a superconducting magnet to acquire 2D single-slice and multi-slice, and 3D volume images. The 1.5T Signa® HDe Magnetic Resonance System features a superconducting magnet operating at 1.5T. The data acquisition system supports 1, 4, 8 independent receive channels and multiple independent coil elements per channel during a single acquisition series. The system can image in the sagittal, coronal, axial, oblique and double oblique planes, using various pulse sequences. Images are acquired and reconstructed using 2D and 3D Fourier transformation techniques. The system is intended for high-resolution anatomical applications and short scan times. The 1.5T Signa® HDe MR system is also compatible in a mobile configuration.

The provided document is a 510(k) summary for the GE 1.5T Signa HDe MR System. It describes the device, its indications for use, and its substantial equivalence to a predicate device. However, it does not include detailed studies with acceptance criteria, reported device performance, sample sizes, ground truth establishment, or expert information typically associated with AI/ML device evaluations.

This document is for an MR system, a hardware device, and not an AI/ML software device. Therefore, the questions related to AI/ML specific evaluation metrics (sample sizes for test and training sets, expert ground truth, adjudication methods, MRMC studies, standalone performance) are not applicable to the information provided in this 510(k) summary.

The summary references evaluation to NEMA performance standards and IEC 60601-1 safety requirements, which are typical for hardware medical devices. These standards would have their own established acceptance criteria for various physical and electrical performance parameters, as well as safety, but the specific details of these criteria and the reported performance are not included in this high-level summary.

Based on the provided text, I can extract the following limited information:

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

Specific acceptance criteria and reported performance metrics in quantitative terms are not available in the provided 510(k) summary. The summary generally states that the device was "evaluated to the appropriate NEMA performance standards as well as the IEC 60601-1 International Medical Equipment Safety requirements" and concludes that the device is "substantially equivalent" to its predicate device. This implies that it met implicit performance and safety criteria relevant to an MR system.

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

• Sample Size for Test Set: Not applicable/not provided. This document is for an MR hardware system, not an AI/ML software where a test set of data would be evaluated.
• Data Provenance: Not applicable/not provided. The evaluation focuses on the hardware's adherence to engineering standards and safety.

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

Not applicable. Ground truth establishment by experts for image interpretation is not relevant for the evaluation of an MRI hardware system as described in this 510(k) summary.

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

Not applicable. Adjudication methods are typically for evaluating diagnostic accuracy of interpretations, which is not the focus of this MR system's 510(k).

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

Not applicable. This is not an AI-assisted device.

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

Not applicable. This is a hardware device, not an algorithm.

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

Not applicable. For hardware, "ground truth" would relate to physical measurements and engineering specifications, not clinical diagnostic accuracy based on patient data.

8. The sample size for the training set:

Not applicable. There is no AI/ML model for which "training set" would apply.

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

Not applicable.

In summary, the provided 510(k) documentation for the GE 1.5T Signa HDe MR System focuses on demonstrating substantial equivalence to a predicate MR system based on design modifications and compliance with established performance and safety standards for hardware. It does not contain the types of studies or data points typically associated with the evaluation of AI/ML software devices.

Ask a specific question about this device