(208 days)
NEONA 1.5T MRI system is indicated for use as a magnetic resonance diagnostic device (MRDD) which produces transverse, sagittal, coronal and oblique cross-sectional images, and those display the internal structure and/or function of the head, body, or extremities. Depending on the region of interest, contrast agents may be used. These images when interpreted by trained physician yield information that may assist medical diagnosis.
The NEONA 1.5T MRI System is a 1.5T superconducting magnet MRI system which produces transverse, sagittal, coronal and oblique cross-sectional images, and those display the internal structure and/or function of the head, body, or extremities. It is composed of Magnet, Magnet Enclosure, Patient Table, Gradient Coil, Transmission Coil, Receiver Coil, Client PC, and Imaging Cabinet. The system software, Prodiva, a Windows-based software, is an interactive program with user friendly interface. The device is conformed to IEC and DICOM standards.
The sponsor, Time Medical Limited, has demonstrated the substantial equivalence of their NEONA 1.5T MRI System to a legally marketed predicate device (EMMA 1.5T MRI System, K183621) through non-clinical performance data and clinical images.
Here's a breakdown of the requested information based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document doesn't explicitly state "acceptance criteria" in a quantified manner for comparison. Instead, it focuses on demonstrating that the NEONA 1.5T MRI System performs as well as the predicate device and complies with recognized standards, indicating that meeting these standards and achieving comparable image quality to the predicate serves as the de facto acceptance.
The "Performance Data" section in the comparative table (page 9) implicitly suggests the acceptance criteria are compliance with:
- NEMA MS standards
- IEC standards: IEC 60601-1, IEC60601-1-2, IEC60601-2-33
The reported device performance is demonstrated by the non-clinical testing results and the sample clinical images.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Compliance with AAMI / ANSI ES60601-1 | Complied |
| Compliance with IEC 60601-1-2 | Complied |
| Compliance with IEC 60601-2-33 | Complied |
| Compliance with NEMA MS-1 (SNR) | Complied (performance testing results demonstrate safety and performance as expected) |
| Compliance with NEMA MS-2 (Geometric Distortion) | Complied |
| Compliance with NEMA MS-3 (Image Uniformity) | Complied |
| Compliance with NEMA MS-4 (Acoustic Noise) | Complied |
| Compliance with NEMA MS-5 (Slice Thickness) | Complied |
| Compliance with NEMA MS-6 (SNR and Uniformity for Single Coils) | Complied |
| Compliance with NEMA MS-8 (SAR) | Complied |
| Compliance with NEMA MS-9 (Phased Array Coils) | Complied |
| Compliance with NEMA MS-14 (RF Coil Heating) | Complied |
| Compliance with ISO 10993-1 (Biological Evaluation) | Complied |
| Compliance with ISO 10993-5 (Cytotoxicity) | Complied |
| Compliance with ISO 10993-10 (Irritation/Sensitization) | Complied |
| Capability in generating images for diagnostic purposes | Verified (Sample clinical images provided) |
| Substantial equivalence in clinical images to predicate device | Demonstrated (Sample clinical image sets from filing device and predicate device on same pulse sequences provided to justify substantial equivalence in medical diagnosis results) |
2. Sample size used for the test set and the data provenance
The document states: "Sample clinical images are provided to verify the claim of filing device's capability in generating images for diagnostic purposes." and "Sample clinical image sets from filing device and predicate device on same pulse sequences are provided to demonstrate the substantial equivalence of filing device to legally marketed predicate device."
- Sample Size: The exact number of clinical images or cases used in the test set is not specified in the provided document. It refers to "sample clinical images" and "sample clinical image sets."
- Data Provenance: The document does not specify the country of origin of the data nor whether the data was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document states that images are "interpreted by trained physician" to "assist medical diagnosis." However, it does not specify how many experts were involved in evaluating the sample clinical images for the substantial equivalence demonstration, nor does it detail their qualifications (e.g., years of experience, specific certifications).
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
The document does not specify any adjudication method used for establishing ground truth or evaluating the clinical image sets. The phrasing "interpreted by trained physician" suggests individual interpretation but doesn't detail a consensus process.
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, an MRMC comparative effectiveness study was not done.
- The device in question, NEONA 1.5T MRI System, is a Magnetic Resonance Diagnostic Device (MRDD), which is the hardware system that produces images. It is not an AI-powered diagnostic software designed to assist human readers. Therefore, the concept of "human readers improving with AI vs without AI assistance" is not applicable to this submission. The comparison is between the performance of the new MRI system and a predicate MRI system.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Not applicable. The NEONA 1.5T MRI System is an imaging device, not an algorithm, and its output (images) is explicitly intended to be "interpreted by trained physician." Therefore, a standalone algorithm-only performance assessment is not relevant in this context.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the evaluation of the clinical images, the implicit ground truth appears to be the diagnostic information derived from the images when interpreted by trained physicians. The comparison of images from the filing device and the predicate device on the same pulse sequences suggests a direct visual and interpretive comparison, implying that the diagnostic conclusions reached from both sets of images should be comparable. However, no specific method like "pathology" or "outcomes data" is mentioned to serve as an independent, definitive ground truth reference beyond physician interpretation of the images themselves.
8. The sample size for the training set
This information is not applicable to the submission for the NEONA 1.5T MRI System. This device is a hardware MRI system, not an AI or machine learning algorithm that requires a "training set" in the conventional sense. The "training" for such a device would relate to its manufacturing, calibration, and quality control processes to ensure image quality, not to a dataset for an AI model.
9. How the ground truth for the training set was established
This information is not applicable for the same reasons as point 8.
§ 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.