(91 days)
The coils are indicated for use on the order of a physician, in conjunction with Philips 1.5T MR scanners as accessories to produce images of the head, spine and torso.
The SENSE Head-Spine-Torso (HST) MR Coil System includes 16 channel coil components that are designed for use with Philips 16-Channel 1.5T Magnetic Resonance Imaging (MRI) magnet systems. The coils work in unison with the Body Coil of the MRI system, which will transmit the radio frequency (RF) signals, so that the coils may receive the resultant RF signal from the excited nuclei. The coils are receive-only coils for high resolution imaging of thorax (including heart), abdomen, cervical, lumbar, and thoracic regions of the spine and the head, neck regions. The coils provide unilateral images of the anatomy of interest. The SENSE HST coils are designed to be used together and separately as follows:
| Coil Models | Comments |
|---|---|
| Head + Spine + Torso | All three coils may be used together. |
| Head + Spine | Head Coil does not function unless it is connected to the Spine Coil. |
| Spine + Torso | Spine and Torso may be used together without the Head Coil |
| Spine | Spine Coil may be used alone. |
The provided text describes a 510(k) submission for the SENSE Head-Spine-Torso (HST) MR Coils. The information focuses on demonstrating substantial equivalence to a predicate device rather than presenting a standalone study with specific acceptance criteria and performance metrics in the way one might expect for a diagnostic AI algorithm.
Therefore, many of the requested categories (sample size, experts, adjudication, MRMC, training set, etc.) are not applicable or not provided in the typical sense of a clinical performance study for an AI device. The submission primarily relies on non-clinical engineering and safety tests.
Here's an analysis of the provided information:
1. Table of Acceptance Criteria and Reported Device Performance
The submission does not explicitly state "acceptance criteria" for clinical performance in terms of sensitivity, specificity, accuracy, or similar metrics typically associated with AI diagnostic devices. Instead, it describes compliance with established engineering and safety standards as evidence of substantial equivalence.
| Acceptance Criteria Category | Reported Device Performance / Assessment |
|---|---|
| Non-Clinical Testing Standards (per FDA Guidance) | |
| Signal to Noise Ratio (SNR) | Performed as per NEMA MS 1-2008. (Specific performance values not provided, but implies satisfactory results for substantial equivalence.) |
| Image Uniformity | Performed as per NEMA MS 3-2008. (Specific performance values not provided, but implies satisfactory results for substantial equivalence.) |
| Characterization of Phased Array Coils (Image Quality) | Performed as per NEMA MS 9-2008. DICOM files from the subject device were reviewed by a radiologist who confirmed the image quality is suitable for clinical applications. (Specific performance metrics for image quality not provided, but expert qualitative assessment indicates suitability.) |
| IEC 60601 Safety Evaluation | Conformance to IEC 60601-1 (General Requirements for Safety), IEC 60601-1-2 (Electromagnetic Compatibility), and IEC 60601-2-33 (Particular Requirements for Safety of MR Equipment). (Implies successful completion of these safety tests, ensuring the device meets established safety profiles for medical electrical equipment and MR systems. Specific pass/fail criteria or quantitative safety metrics are not detailed in this summary.) |
| Comparison to Predicate Device | |
| Design Rationale | Substantially equivalent |
| Safety Features | Substantially equivalent (e.g., electrical isolation, housing material flammability rating UL94-HF-1 for Polycarbonate, Polyethylene) |
| Magnet System Compatibility | Substantially equivalent (Philips 1.5T MRI Systems) |
| Overall Intended Use | Substantially equivalent (Accessory to MRI Scanner, same FDA class II product code MOS, receive-only coils, 1.5T systems compatibility, multi-pin connector) |
2. Sample Size Used for the Test Set and Data Provenance
This is not a study measuring diagnostic performance on a patient test set in the traditional sense; it's a device submission for MR coils.
- Test Set Sample Size: Not applicable in the context of a "test set" for diagnostic performance. The "testing" involved phantoms for SNR, uniformity, and coil characterization, as well as qualitative review of DICOM images by a radiologist. The number of phantoms or images reviewed is not specified.
- Data Provenance: Not applicable for patient data. The tests were primarily engineering and safety evaluations, likely conducted in a lab setting.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: One radiologist is mentioned: "DICOM files from the 510(k) subject device were reviewed by a radiologist who confirmed the image quality is suitable for clinical applications."
- Qualifications of Experts: Only "radiologist" is specified. Further details (e.g., years of experience, subspecialty) are not provided in this summary.
- Ground Truth Establishment: For the qualitative image quality assessment, the single radiologist's confirmation of "suitability for clinical applications" served as the expert assessment.
4. Adjudication Method for the Test Set
Not applicable. Only one expert is mentioned for qualitative image review, so no adjudication process between multiple readers was necessary or stated.
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 device or a comparative effectiveness study involving human readers. It's a submission for MR coils.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. This is not an AI algorithm. The device itself (MR coil) is an accessory that generates images, and its "performance" is primarily defined by image quality characteristics and electrical/mechanical safety, rather than a diagnostic output.
7. The Type of Ground Truth Used
- For engineering metrics (SNR, Uniformity): Phantoms and established measurement protocols (NEMA standards) serve as the "ground truth" for these quantifiable technical specifications.
- For qualitative image quality: Expert opinion (judgment of the single radiologist) on suitability for clinical applications.
- For safety: Compliance with IEC standards derived from established safety requirements.
8. The Sample Size for the Training Set
Not applicable. This is not an AI device that undergoes training.
9. How the Ground Truth for the Training Set was Established
Not applicable.
§ 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.