(63 days)
The intended use of this PROCURE Array coil family is to provide high-quality images of the reproductive and urological anatomies in an easy-to-position, wearable, and very flexible design.
The coil is indicated for use by the order of a physician to be used as an accessory to a General Electric 1.5T or 3.0T magnetic resonance scanner for general human anatomy imaging as supported by the scanner. These images, when interpreted by a trained physician, may assist in medical diagnosis.
The PROCURE™ Coil Family interfaces with a 1.5T or 3.0T 8-channel GE MRI scanner and provides high-quality images of the reproductive and urological anatomies in an easy-to-position, wearable, and very flexible design. This lightweight SemiFlex™ design facilitates effortless and accurate positioning similar to wearing a diaper and positions the multiple antenna elements as close as possible to the target anatomies regardless of patient size. The enclosure for the antenna set is made of flexible liquid impermeable, biocompatible materials, and the coil is accompanied by disposable liners (USP Class 6 PET) easily changed between patients, should scanning without clothing be desired. The two coils in the product family are identical in design, construction, materials, and operation, with the exception of resonant frequency. The designs and materials used for manufacture of both coils are identical to standard MRI coil technology that has existed for several years. The coils use similar blocking networks and impedance matching circuits, and they do not transmit energy into the patient, neither predicate nor current submission.
This phased array coil also accommodates popular biopsy systems, both delivered via an opening near the anus and/or vagina, neither included in the scope of this submission as they are independently operated and cleared by the FDA
This device is an MRI coil, a non-AI medical device. The provided text is a 510(k) summary for a substantial equivalence determination, not a study evaluating acceptance criteria for an AI/ML powered device. As such, acceptance criteria, efficacy study, and information regarding ground truth and expert involvement are not applicable in the context of AI/ML evaluation.
The 510(k) summary details the "PROCURE™ Array Coil Family" and compares it to a predicate device (1.5T ScanMed® PV Array, K022395) to demonstrate substantial equivalence.
Here's an analysis based on the information provided, specifically addressing the non-AI nature:
1. Table of acceptance criteria and the reported device performance
For a non-AI device like an MRI coil, "acceptance criteria" for performance primarily revolve around meeting established safety standards and demonstrating image quality comparable to or better than a predicate device. The document does not present a formal table of quantitative acceptance criteria and reported device performance in the way one would for an AI/ML model's diagnostic accuracy. Instead, it relies on demonstrating equivalence through various engineering and scientific analyses.
The key performance metrics for an MRI coil typically involve Signal-to-Noise Ratio (SNR) and image uniformity.
| Criteria Category | Device Performance / Justification |
|---|---|
| Safety and Biocompatibility | |
| Biocompatibility | "Both predicate and modified devices have a successful biocompatibility track record, as demonstrated by cytotoxicity testing and by their history of use in previously cleared devices." The nylon fabric used has been "successfully used for over 10 years in the predicate device with no reported biocompatibility issues." |
| Mechanical & Electrical Safety | "Both modified and predicate devices have been tested for mechanical and electrical safety using IEC60601-1 3rd Edition." |
| Risk Management | "The predicate and current submission have been subject to similar risk management studies,...and determined to be substantially equivalent." (Included: Blocking Analysis, Heat Testing, Risk management (including hazard analysis and FMEA)) |
| Performance | |
| Image Quality | "SNR and uniformity analysis" was conducted. Clinical tests involved "Analyses in all 3 planes (sagittal, coronal and transverse) were run on the PROCURE Array product to show that the anatomies of the submitted and predicate coils have substantial equivalence". The device is intended to "provide high-quality images of the reproductive and urological anatomies." The comparison to the predicate device covering "very similar ranges of anatomy" suggests that the image quality is expected to be diagnostically equivalent. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document mentions "Clinical Tests" were performed with "Analyses in all 3 planes (sagittal, coronal and transverse) were run on the PROCURE Array product." However, it does not specify the sample size of these clinical tests (i.e., number of patients or imaging studies). The data provenance (country of origin, retrospective/prospective) is also not stated.
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. For MRI coils, the "ground truth" is not established in the same way as for AI models requiring expert annotation. Image quality is assessed based on physical properties and visual interpretation by a "trained physician" for diagnosis, but there's no mention of a formal expert panel to establish ground truth for a test set in the context of an efficacy study as would be seen for an AI product.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. As this is not an AI/ML product requiring diagnostic accuracy adjudication, no such method 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
Not applicable. This is not an AI-assisted device, and no MRMC study or AI-related comparative effectiveness study was performed. The comparison is between two physical MRI coils.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. This is a passive receive-only MRI coil, not an algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not applicable in the AI/ML sense. The "ground truth" for an MRI coil's performance typically refers to its ability to produce clinically usable images, which is assessed by "trained physicians" for "medical diagnosis." However, this is not a formal ground truth as required for validating an AI diagnostic algorithm.
8. The sample size for the training set
Not applicable. This is a hardware device, not an AI/ML model that requires training data.
9. How the ground truth for the training set was established
Not applicable, as there is no training set for an MRI coil.
§ 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.