(46 days)
The Swoop® Portable MR Imaging System™ is a bedside magnetic resonance imaging device for producing images that display the internal structure of the head where full diagnostic examination is not clinically practical. When interpreted by a trained physician, these images provide information that can be useful in determining a diagnosis.
The Swoop system is a portable MRI device that allows for patient bedside imaging. The system enables visualization of the internal structures of the head using standard magnetic resonance imaging contrasts. The main interface is a commercial off-the-shelf device that is used for operating the system, providing access to patient data, exam setup, exam execution, viewing MRI image data for quality control purposes, and cloud storage interactions. The system can generate MRI data sets with a broad range of contrasts. The Swoop system user interface includes touch screen menus, controls, indicators, and navigation icons that allow the operator to control the system and to view imagery. The Swoop System image reconstruction algorithm utilizes deep learning to provide improved image quality for T1W, T2W, and FLAIR sequences, specifically in terms of reductions in image noise and blurring.
The subject Swoop System described in this submission includes software modifications related to the device pulse sequences; retrained advanced reconstruction models; service and support features; and adds an audible scanner startup tone.
The provided text describes the regulatory clearance of the Hyperfine Swoop® Portable MR Imaging System™ and mentions non-clinical performance testing. However, it does not contain the specific details required to complete all sections of your request, particularly a table of acceptance criteria and reported device performance based on a study, sample sizes, expert qualifications, or details of a multi-reader multi-case (MRMC) study.
The document indicates that the device's image reconstruction algorithm utilizes deep learning to provide improved image quality for T1W, T2W, and FLAIR sequences, specifically in terms of reductions in image noise and blurring. It also states that the subject device includes retrained advanced reconstruction models. The non-clinical performance section states "Testing to verify the subject device meets all image quality criteria" and references various NEMA and ACR standards for image performance. It also mentions a "Validation study to ensure the device meets user needs and performs as intended."
Given the limitations of the provided text, I can only fill in the information that is explicitly stated or can be reasonably inferred. Many sections will be marked as "Not provided in the text".
Here's a summary of the available information:
1. Table of Acceptance Criteria and Reported Device Performance
The document mentions that "Testing to verify the subject device meets all image quality criteria" was performed against various NEMA and ACR standards. However, the specific quantitative acceptance criteria or the reported device performance metrics (e.g., specific SNR values, resolution, etc.) are not provided in the text.
2. Sample size used for the test set and the data provenance
Not provided in the text. The document mentions "non-clinical performance" and "verification and validation testing" but does not specify details about a clinical test set, sample size, or data provenance for these image quality assessments.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not provided in the text. The document mentions that the images, "When interpreted by a trained physician, ... provide information that can be useful in determining a diagnosis," but this refers to the intended use of the device, not the ground truth establishment for a specific test set within the regulatory submission.
4. Adjudication method for the test set
Not provided in the text.
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 provided in the text. The document focuses on regulatory clearance based on substantial equivalence and non-clinical testing. While the device uses deep learning for image reconstruction, a MRMC study is not mentioned.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Partially addressed: The text states, "The Swoop System image reconstruction algorithm utilizes deep learning to provide improved image quality for T1W, T2W, and FLAIR sequences, specifically in terms of reductions in image noise and blurring." This implies an algorithm-only component focusing on image quality improvement. The non-clinical performance section includes "Image Performance" testing against NEMA and ACR standards, which would primarily assess the standalone algorithm's output image quality. However, a standalone diagnostic performance study (e.g., sensitivity/specificity for detecting pathologies) is not explicitly detailed.
7. The type of ground truth used
Partially addressed / Inferred: For "Image Performance" testing (which includes assessments against NEMA and ACR standards), the ground truth is typically based on phantom measurements and known physical properties, not clinical outcomes or pathology directly. For the "Validation study to ensure the device meets user needs and performs as intended," the type of ground truth is not specified, but it would likely involve expert evaluation of image quality and usability, rather than a clinical ground truth like pathology.
8. The sample size for the training set
Not provided in the text. The document mentions "retrained advanced reconstruction models," indicating a training process, but no details about the training data size.
9. How the ground truth for the training set was established
Not provided in the text.
Summary Table of Available Information based on the Provided Text:
| Criteria | Information from Document |
|---|---|
| Acceptance Criteria & Reported Performance | The document states "Testing to verify the subject device meets all image quality criteria" against standards such as NEMA MS 1-2008 (R2020), NEMA MS 3-2008 (R2020), NEMA MS 9-2008 (R2020), NEMA MS 12-2016, and American College of Radiology (ACR) Phantom Test Guidance for Use of the Large MRI Phantom for the ACR MRI Accreditation Program, and ACR standards for named sequences. |
Specific quantitative acceptance criteria and reported device performance values are not provided in the text. |
| Sample size (Test Set) & Data Provenance | Not provided in the text. |
| Number & Qualifications of Experts (Test Set Ground Truth) | Not provided in the text. |
| Adjudication Method (Test Set) | Not provided in the text. |
| MRMC Comparative Effectiveness Study | Not provided in the text. |
| Standalone (Algorithm Only) Performance | Yes, implicitly. The document states, "The Swoop System image reconstruction algorithm utilizes deep learning to provide improved image quality for T1W, T2W, and FLAIR sequences, specifically in terms of reductions in image noise and blurring." This is an algorithm-only function. The "Image Performance" testing against NEMA and ACR standards would evaluate the standalone algorithm's output image quality. |
| Type of Ground Truth Used (Test Set) | For "Image Performance": Inferred to be based on phantom measurements and known physical characteristics as per NEMA and ACR phantom protocols.
For "Software Validation" (user needs): Not specified, but likely expert evaluation of image quality and usability. |
| Sample Size for Training Set | Not provided in the text. |
| How Ground Truth for Training Set was Established | Not provided in the text. |
§ 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.