(42 days)
The 16 Channel Shoulder Coil is to be used in conjunction with Magnetic Resonance Scanners to produce diagnostic images of the shoulder that can be interpreted by a trained physician.
The proposed 1.5T and 3.0T 16 Ch GE Shoulder Coils are designed for use with Magnetic Resonance Imaging (MRI) systems. The coil is designed to work in unison with the Body Coil of the MRI system, which will transmit the radio frequency (RF) signals, so that the coil may receive the resultant RF signal from the excited nuclei.
The proposed 1.5T and 3T 16Ch GE Shoulder Coils are identical to each other in construction with the exception that they are tuned to their respective frequencies and additional cable trap baluns are included on the 3T coil due to the shorter wavelengths associated with 3T. The proposed 1.5T and 3.0T 16 Ch GE Shoulder Coils are designed as receive-only coils for high resolution diagnostic imaging of shoulder. The coils provide unilateral images (Left and Right) of the anatomy of interest.
The provided text is a 510(k) premarket notification for magnetic resonance imaging (MRI) coils (1.5T and 3.0T 16CH GE Shoulder Coils). While it describes the device, its intended use, and its similarities to a predicate device to establish substantial equivalence, it does not contain information about acceptance criteria and a study proving the device meets those criteria in the context of an AI-powered diagnostic device.
This document is for a physical medical device (an MRI coil), and its "performance" is evaluated through non-clinical bench testing (SNR, image uniformity) and a clinical demonstration focusing on image quality for interpretation by a physician. It is not a document for an AI/ML-based diagnostic device where "acceptance criteria" would typically refer to metrics like sensitivity, specificity, or AUC, and "ground truth" would be established by expert consensus or biopsy.
Therefore, I cannot extract the requested information regarding acceptance criteria and a study proving the device (in the context of an AI diagnostic tool) meets those criteria, as the provided text describes a physical MRI coil and its FDA clearance process.
Here's why each point you requested is not applicable or not explicitly detailed in the provided text for an AI/ML context:
- Table of acceptance criteria and reported device performance: The document states "Non-clinical verification and validation test results demonstrate that the proposed 1.5T and 3.0T 16 Ch GE Shoulder Coils... Meets the acceptance criteria and is adequate for its intended use." However, it does not provide a specific table of quantitative acceptance criteria for diagnostic performance (like sensitivity/specificity thresholds) or the numerical results against these criteria. It mentions tests for SNR and image uniformity and that a clinical radiologist reviewed images to confirm adequate quality, but no numerical thresholds or results are given.
- Sample size for the test set and data provenance: The document mentions "clinical demonstrations" and "Clinical Images review by Radiologist" but does not specify the sample size of these clinical demonstrations (number of patients/cases) or the data provenance (country, retrospective/prospective).
- Number of experts and qualifications for ground truth: "a clinical radiologist" is mentioned as reviewing the DICOM images for adequacy. The number of radiologists is not specified (e.g., singular "a radiologist" could imply one, but is not definitive for a study), nor are their specific qualifications (e.g., years of experience). For an AI device, this would typically involve multiple, highly qualified experts.
- Adjudication method: Not applicable/not mentioned. Ground truth for an AI device involves multiple readers and an adjudication process. Here, it's a "clinical radiologist" reviewing images for overall adequacy, not to establish a precise diagnostic ground truth for an AI algorithm.
- MRMC comparative effectiveness study: Not done. This is not an AI-assisted device.
- Standalone performance: The performance mentioned (SNR, uniformity) is inherent to the coil's function, not a diagnostic decision made by an algorithm.
- Type of ground truth used: For image quality, it was radiologist review of image adequacy ("confirm the image quality is adequate"). This is different from establishing a diagnostic ground truth (e.g., presence/absence of disease confirmed by pathology) for an AI algorithm.
- Sample size for the training set: Not applicable. This is not an AI/ML device that requires training data.
- How ground truth for training set was established: Not applicable.
In summary, the provided document details the regulatory pathway for a conventional MRI coil, not an AI-powered diagnostic device. The concepts of "acceptance criteria" and "study" in the context of AI diagnostic performance metrics are not applicable to this document.
§ 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.