(86 days)
i Field 1.5T Superconducting Magnetic Resonance Imaging device, which is intended to provide the physician with physiological and clinical information, obtained non-invasively and without the use of ionizing radiation. The MRI System produces transverse, sagittal, coronal, and oblique images that display the internal structure of the head, body, or extremities. The images produced by the MRI System reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin-latice relaxation time (T1), spin-spin relaxation time (T2) and flow. When interpreted by a trained-physician, these images provide information that can be useful in diagnosis determination.
i Field 1.5T Superconducting Magnetic Resonance Imaging System utilizes a 1.5 Tesla superconducting magnet in an open gantry design. i Field 1.5T Superconducting Magnetic Resonance Imaging System has been designed to enhance clinical utility as compared to the i_Space 1.5T by taking advantage of the imaging properties of the 1.5T magnet.
The provided document describes a 510(k) Summary for the i_Field 1.5T Superconducting Magnetic Resonance Imaging System, seeking substantial equivalence to a predicate device. This document is a regulatory submission to the FDA, not a clinical study report proving a device meets specific clinical performance acceptance criteria for an AI algorithm.
Therefore, many of the requested details regarding acceptance criteria for an AI device, sample sizes for test sets, expert adjudication methods, MRMC studies, standalone performance, and ground truth establishment for a training set are not applicable to this document. This submission focuses on demonstrating the substantial equivalence of a new MR scanner to an existing one, primarily through technological comparison and adherence to performance and safety standards, rather than proving the performance of an AI-powered diagnostic algorithm.
However, I can extract information related to the device specifications and non-clinical testing that serve as "acceptance criteria" for an MR imaging system itself, and how the manufacturer proves the device meets these criteria.
Non-AI Device Acceptance Criteria and Performance (Based on provided 510(k) Summary)
The "acceptance criteria" for this MRI system are primarily defined by adherence to recognized national and international standards for medical electrical equipment and specific MRI performance parameters, and by demonstrating substantial equivalence to a predicate device. The performance data provided is largely in the form of conformance to these standards and similar technical specifications.
Here's an attempt to structure the available information relevant to "acceptance criteria" for the MRI system, understanding that it's for the hardware and basic imaging functions, not an AI algorithm.
1. Table of Acceptance Criteria and Reported Device Performance
Given that this is a 510(k) submission for an MRI system, the "acceptance criteria" are the established performance and safety specifications for such devices, often set by regulatory guidance and industry standards. The "reported device performance" is the manufacturer's claim of compliance and comparability to the predicate.
| Acceptance Criteria Category | Specific Criteria/Standard | Reported Device Performance (Claimed) |
|---|---|---|
| Safety Parameters | Maximum Static Field | Conforms to FDA guidance |
| Rate of Change of Magnetic Field | Conforms to FDA guidance | |
| RF Power Deposition | Conforms to FDA guidance | |
| Acoustic Noise Levels | Conforms to FDA guidance (NEMA MS 4-2010 for measurement) | |
| Performance Levels | Specification Volume | Conforms to FDA guidance |
| Signal to Noise (SNR) | Conforms to FDA guidance (NEMA MS 1-2008 (R2020), NEMA MS 6-2008 (R2020)) | |
| Image Uniformity | Conforms to FDA guidance (NEMA MS 3-2008 (R2020), NEMA MS 6-2008 (R2020)) | |
| Geometric Distortion | Conforms to FDA guidance (NEMA MS 2-2008 (R2020), NEMA MS 12-2016) | |
| Slice Profile, Thickness and Gap | Conforms to FDA guidance (NEMA MS 5-2018) | |
| High Contrast Spatial Resolution | Conforms to FDA guidance | |
| General Safety & Performance Standards | Medical Electrical equipment (AAMI / ANSI ES60601-1, IEC 60601-1-2, IEC 60601-2-33, IEC 60601-1-6) | Complies with listed standards |
| Risk Management (ISO 14971) | Complies with standard | |
| Usability Engineering (IEC 62366-1) | Complies with standard | |
| Software Life Cycle Processes (IEC 62304) | Complies with standard | |
| MRI Equipment Image Quality (IEC 62464-1) | Complies with standard | |
| DICOM Compatibility (PS 3.1 - 3.20) | DICOM3.0 compatibility | |
| Biological Evaluation (ISO 10993-1) | Complies with standard | |
| RF Coil Heating (NEMA MS 14-2019) | Complies with standard | |
| Phased Array Coils (NEMA MS 9-2008 (R2020)) | Complies with standard | |
| Technological Characteristics | Magnet Type, Strength, Mass, Leakage flux | Same as predicate (Superconducting, 1.5T, 4.3ton, 2.5m x 4.0m) |
| Gradient Max Strength & Slew Rate | Same as predicate (33mT/m, 128mT/m/ms) | |
| RF System Power Amplifier | Same as predicate (20kW) | |
| Imaging Methods (SE, FSE, IRPS, GEPS, EPI) | Same as predicate | |
| Scan Matrix, Slice Plane, FOV, File Format, Image Processing functions | Same as predicate | |
| Patient-accessible bore dimension | Better than predicate (710mm vs 600mm) – noted as improvement | |
| Slice thickness (typical, minimum) | Same as predicate (5mm +/- 1mm; 0.05mm(3D) min) |
2. Sample size used for the test set and the data provenance
- Not applicable / Not specified in this document for clinical performance. This document describes the non-clinical testing and technical specifications of an MRI scanner. The testing relies on phantom measurements and engineering verification against standards, not a clinical test set with patient data for an AI algorithm.
- The "performance data provided" refers to engineering tests and measurements to confirm compliance with the listed standards (e.g., NEMA standards for SNR, uniformity, distortion), typically using phantoms rather than human patient data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not applicable. This document does not describe a study involving expert readers establishing ground truth for a diagnostic AI algorithm. The "ground truth" for the device's technical performance is defined by the physical properties measured in phantoms and the specifications in the standards.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable. There is no clinical test set requiring adjudication in this 510(k) submission.
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 does not describe an AI device, nor an MRMC study comparing human reader performance with and without AI.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- No. This is a submission for an MRI scanner, not a standalone AI algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- For the technical performance of the MRI system, the "ground truth" is established by:
- Validated physical phantom measurements: For parameters like SNR, image uniformity, geometric distortion, slice thickness, etc., as specified by NEMA and IEC standards.
- Engineering specifications and design documents: For hardware characteristics (e.g., magnet strength, gradient slew rate, RF power).
- Compliance with recognized standards: The "truth" is whether the device meets the thresholds and methodologies defined in standards like IEC 60601 series, ISO 14971, NEMA MS series, etc.
8. The sample size for the training set
- Not applicable. There is no AI training set described in this 510(k) submission for an MRI system.
9. How the ground truth for the training set was established
- Not applicable. As above, no AI training set is discussed.
In summary: The provided FDA 510(k) Summary is for an "i_Field 1.5T Superconducting Magnetic Resonance Imaging System," which is a medical imaging device (hardware and basic imaging software), not an AI algorithm. Therefore, the "acceptance criteria" and "proof" primarily revolve around demonstrating:
- Compliance with safety and performance standards for MRI systems (e.g., IEC, NEMA).
- Substantial equivalence in technological characteristics and intended use to a previously cleared predicate MRI device.
- Non-clinical testing (e.g., phantom studies, engineering validations) to verify these characteristics and compliance.
The document explicitly states: "The minor differences in technological characteristics do not constitute any safety and effectiveness issue, as indicated in performance data provided." and "i Field 1.5T Superconducting Magnetic Resonance Imaging System will conform to the FDA recognized NEMA Standards for the measurement of performance and safety parameters and the international IEC standard for safety issues with Magnetic Resonance Imaging Devices. This will assure that the performance of this device can be considered safe and effective with respect to currently available system." This underscores that the "proof" is largely attestations of compliance supported by manufacturer's internal testing against these established benchmarks.
§ 892.1000 Magnetic resonance diagnostic device.
(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.