(102 days)
The Swoop Portable MR Imaging System is a portable, ultra-low field 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 portable, ultra-low field MRI device that 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, FLAIR, and DWI sequences.
The provided document is a 510(k) Summary for the Hyperfine Swoop Portable MR Imaging System (K240944). It describes the device, its intended use, and compares it to a predicate device (K232760) to demonstrate substantial equivalence.
Here's an analysis of the acceptance criteria and the study information based on the document:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly list "acceptance criteria" for the device, but rather describes the tests performed and the standards met for demonstrating substantial equivalence. The provided information focuses on engineering and software validation rather than clinical performance metrics such as sensitivity, specificity, or accuracy for a specific diagnostic task.
Here's a table summarizing the tests described and the reported outcome:
| Category | Test Description | Applicable Standard(s) | Reported Performance/Outcome |
|---|---|---|---|
| Non-Clinical Performance | |||
| Software Verification | Software verification testing in accordance with the design requirements to ensure that the software requirements were met. | • IEC 62304:2015 | |
| • FDA Guidance, "Content of Premarket Submissions for Device Software Functions" | The subject device passed all the testing in accordance with internal requirements and applicable standards to support substantial equivalence. | ||
| Image Performance | Testing to verify the subject device meets all image quality criteria. | NEMA MS 1-2008 (R2020), NEMA MS 3-2008 (R2020), NEMA MS 9-2008 (R2020), NEMA MS 12-2016, American College of Radiology (ACR) Phantom Test Guidance for Use of the Large MRI Phantom for the ACR MRI Accreditation Program, American College of Radiology standards for named sequences | The subject device passed all the testing in accordance with internal requirements and applicable standards to support substantial equivalence. |
| Cybersecurity | Testing to verify cybersecurity controls and management. | FDA Guidance, "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions" | The subject device passed all the testing in accordance with internal requirements and applicable standards to support substantial equivalence. |
| Software Validation | Validation to ensure the subject device meets user needs and performs as intended. | FDA Guidance, "Content of Premarket Submissions for Device Software Functions" | The subject device passed all the testing in accordance with internal requirements and applicable standards to support substantial equivalence. |
| Leveraged from Predicate | |||
| Biocompatibility | Biocompatibility testing of patient-contacting materials. | • ISO 10993-1:2018 | |
| • ISO 10993-5:2009 | |||
| • ISO 10993-10:2010 | Test results from the predicate were used to support the subject device because the conditions were identical or the subject device modifications did not introduce a new worst-case configuration or scenario for testing. | ||
| Cleaning/Disinfection | Cleaning and disinfection validation of patient-contacting materials. | • FDA Guidance, "Reprocessing Medical Devices in Health Care Settings: Validation Methods and Labeling" | |
| • ISO 17664:2017 | |||
| • ASTM F3208-17 | Test results from the predicate were used to support the subject device because the conditions were identical or the subject device modifications did not introduce a new worst-case configuration or scenario for testing. | ||
| Safety | Electrical Safety, EMC, and Essential Performance testing. | • ANSI/AAMI ES 60601-1:2005/(R)2012 | |
| • IEC 60601-1-2:2014 | |||
| • IEC 60601-1-6:2013 | Test results from the predicate were used to support the subject device because the conditions were identical or the subject device modifications did not introduce a new worst-case configuration or scenario for testing. | ||
| Performance | Characterization of the Specific Absorption Rate for Magnetic Resonance Imaging Systems. | • NEMA MS 8-2016 | Test results from the predicate were used to support the subject device because the conditions were identical or the subject device modifications did not introduce a new worst-case configuration or scenario for testing. |
The document states that the "subject device passed all the testing in accordance with internal requirements and applicable standards to support substantial equivalence." This implies that the acceptance criteria were met, which were defined by the adherence to these standards and the internal requirements.
2. Sample Size Used for the Test Set and the Data Provenance
The document details testing for software verification, image performance (phantom-based), cybersecurity, and software validation. It does not describe a clinical test set involving patient data for the subject device to evaluate diagnostic performance. The image performance testing appears to be based on physical phantoms (NEMA, ACR). Therefore, information on sample size for a "test set" in the context of clinical images and data provenance (country of origin, retrospective/prospective) is not provided.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts
Since no clinical test set evaluating diagnostic performance with patient images is described for the subject device in this document, there is no mention of experts establishing ground truth for such a set. The image performance testing refers to ACR Phantom Test Guidance and standards, which don't typically involve expert reading of collected patient images.
4. Adjudication Method for the Test Set
As no clinical test set for diagnostic performance is described, there is no information on an adjudication method.
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 MRMC comparative effectiveness study is mentioned in this document. The submission focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance and leveraging prior test results from the predicate, not on comparative clinical efficacy or improvement with AI assistance for human readers. The device does utilize deep learning for image reconstruction, but its impact on human reader performance is not evaluated in this submission.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document does not describe a standalone performance study in the context of diagnostic accuracy for the AI component (deep learning for image reconstruction). The deep learning is part of an image reconstruction algorithm, and the "image performance" testing is done against established phantom standards, not against a ground truth for diagnostic accuracy.
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
For the non-clinical tests described, the "ground truth" refers to:
- Software Verification/Validation: Adherence to design requirements and user needs.
- Image Performance: Adherence to image quality criteria as defined by NEMA and ACR phantom standards. The "ground truth" for these tests would be the known properties of the phantoms and the expected imaging parameters.
- Cybersecurity, Biocompatibility, Cleaning/Disinfection, Safety, Performance (SAR): Adherence to relevant regulatory standards (IEC, ISO, FDA Guidance, ANSI/AAMI, ASTM).
There is no mention of expert consensus, pathology, or outcomes data as ground truth because no clinical diagnostic accuracy study is presented.
8. The Sample Size for the Training Set
The document states that "The Swoop System image reconstruction algorithm utilizes deep learning to provide improved image quality for T1W, T2W, FLAIR, and DWI sequences." However, it does not provide any information regarding the sample size of the training set used for this deep learning algorithm.
9. How the Ground Truth for the Training Set was Established
Since the document does not provide details on the training set for the deep learning algorithm, it also does not specify how the ground truth for that training set was established. Given it's an image reconstruction algorithm, the "ground truth" for training would typically involve pairs of raw MRI data and high-quality reconstructed images (often from different acquisition parameters or iterative reconstruction methods) rather than diagnostic labels from experts.
§ 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.