(203 days)
HyperSense is a software feature intended for use on GE MR 1.5T and 3.0T Systems. HyperSense is an acceleration technique based on sparse data sampling and iterative reconstruction that allows users to reduce scan times or increase scan resolution. HyperSense can be used for non-contrast enhanced imaging of the head, neck, spine, extremities, pelvis, and abdomen.
HyperSense is a software feature used on GE 1.5T and 3.0T MR systems. HyperSense is an acceleration technique based on sparse data sampling and iterative reconstruction, enabling faster imaging without the penalties commonly found with conventional parallel imaging. HyperSense is intended to be used with volumetric acquisitions, and can be combined with other methods of acceleration (ARC) for achieving high signal to noise ratio with shorter acquisition times. HyperSense can deliver higher spatial resolution images or reduced scan times.
HyperSense Device Acceptance Criteria and Study Details
The provided document describes the GE HyperSense, a software feature for MR systems that uses sparse data sampling and iterative reconstruction to reduce scan times or increase resolution.
Here's a breakdown of the acceptance criteria and study details:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Measured Metric) | Reported Device Performance (HyperSense with predicate) |
|---|---|
| Image quality (legibility of morphological features) | Comparable imaging performance |
| Signal to Noise Ratio (SNR) | Evaluated (results not explicitly stated, but "passing results" generally imply meeting predetermined criteria) |
| Spatial Resolution | Evaluated (results not explicitly stated, but "passing results" generally imply meeting predetermined criteria) |
Note: The document states that "the non-clinical testing was completed with passing results per the pass/fail criteria defined in the test cases" for SNR and spatial resolution. For clinical testing, it states "The clinical results demonstrated that HyperSense maintains comparable imaging performance results as its predicate devices."
2. Sample Size for Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated for either phantom or clinical studies.
- Data Provenance: Not explicitly stated for the clinical study. It mentions "sample clinical images are included in this submission," suggesting the data was likely from relevant GE MR systems. The study is referred to as "A clinical study has been performed," implying a prospective nature, though not explicitly stated.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Not explicitly stated.
- Qualifications of Experts: Not explicitly stated.
4. Adjudication Method
- Adjudication Method: Not explicitly stated.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study: No, an MRMC comparative effectiveness study is not mentioned. The clinical study focused on evaluating the impact of HyperSense on image quality compared to its predicate devices, not on human reader improvement with AI assistance.
6. Standalone Performance Study
- Standalone Study: Yes, a standalone performance study in the form of phantom testing was conducted to evaluate the impact of HyperSense on Signal to Noise Ratio (SNR) and spatial resolution. The "clinical study" also appears to be a standalone assessment of the device's image quality. The device is a "software only feature" that enhances image acquisition and reconstruction, implying its direct impact on the image itself, which is a standalone performance by the algorithm.
7. Type of Ground Truth Used
- Phantom Testing: Objective measurements of SNR and spatial resolution.
- Clinical Study: "Legibility of morphological features," which implies a qualitative assessment by experts (implicitly radiologists or medical professionals experienced with MRI interpretations). This would typically involve expert consensus or assessment against established diagnostic criteria. The document also mentions a "peer reviewed journal article describing a study of the HyperSense technique as supporting evidence," which would also likely rely on similar ground truth methodologies.
8. Sample Size for Training Set
- Sample Size for Training Set: Not mentioned. HyperSense is an acceleration technique and iterative reconstruction method. While it's a software feature, the process of developing and tuning such algorithms often involves various datasets for training and validation, but these details are not provided in the summary.
9. How Ground Truth for Training Set Was Established
- How Ground Truth for Training Set was Established: Not mentioned. Given the nature of an iterative reconstruction algorithm, "ground truth" for training would typically involve high-quality, fully sampled MR images that the algorithm aims to replicate or improve upon from undersampled data. The process would likely involve various forms of quantitative image metrics and expert review to optimize the reconstruction parameters.
§ 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.