(123 days)
Indications for use vary depending on the specific product and its intended application. These products are designed for use in medical or laboratory settings by trained professionals. Depending on the device, intended uses may include:
- Diagnostic purposes: Analyzing biological samples (e.g., blood, urine, tissue) to identify diseases, conditions, or other health markers. This can include detecting infections, monitoring chronic illnesses, or screening for genetic predispositions.
- Therapeutic procedures: Assisting in or performing medical interventions, such as administering medications, delivering fluids, or providing respiratory support.
- Research and development: Used in laboratory experiments and studies to investigate biological processes, test new drugs, or develop new medical technologies.
- Monitoring physiological parameters: Measuring heart rate, blood pressure, oxygen saturation, or other vital signs.
- Sample collection and preparation: Gathering, processing, and storing biological samples for further analysis.
Specific indications for use are provided in the product's labeling, instructions for use (IFU), or accompanying documentation. Users should always refer to the manufacturer's provided information for the most accurate and complete indications.
{{overview}}
The FDA Clearance Letter for the Swoop® Portable MR Imaging® System (V2) provides details on the acceptance criteria and the studies conducted to demonstrate the device meets these criteria, particularly focusing on the "Advanced Reconstruction" feature which likely incorporates deep learning for image quality optimization.
Here's a breakdown of the requested information:
1. Acceptance Criteria and Reported Device Performance
The core performance of the device's "Advanced Reconstruction" was evaluated through three studies: Performance Analysis, Contrast-to-Noise Ratio (CNR) Validation, and Advanced Reconstruction Image Validation.
| Acceptance Criteria Category | Specific Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Performance Analysis (Robustness, Stability, Generalizability) | Quantitative: Reduced Normalized Mean Squared Error (NMSE) and improved Structural Similarity Index (SSIM) for Advanced Reconstruction compared to Linear Reconstruction. Qualitative: Preservation of motion and zipper artifacts, and no unexpected output. | Quantitative: "For all models and all test datasets NMSE was reduced and SSIM was improved for Advanced Reconstruction test images compared to Linear Reconstruction test images." Qualitative: "Advanced Reconstruction preserved the presentation of motion and zipper artifacts, and no unexpected output was observed." |
| Contrast-to-Noise Ratio (CNR) Validation | Mean CNR of Advanced Reconstruction required to be greater than the mean CNR of baseline Linear Reconstruction at a statistical significance level of 0.05 for each sequence type. | "In all cases, CNR of Advanced Reconstruction was greater than or equal to Linear Reconstruction for both hyper- and hypo-intense pathologies. The study result demonstrates that Advanced Reconstruction does not unexpectedly modify, remove, or reduce the contrast of pathology features." |
| Advanced Reconstruction Image Validation (Human Reader Study) | Advanced Reconstruction required to perform at least as well as Linear Reconstruction in all categories (median score ≥0 on Likert scale) and perform better (≥1 on Likert scale) in at least one of the quality-based categories (noise, sharpness, contrast, geometric fidelity, artifact, overall image quality). | "Advanced Reconstruction achieved a median score of 2 (the most positive rating scale value) in all categories. This scoring indicates reviewers found Advanced Reconstruction improved image quality while maintaining diagnostic consistency relative to Linear Reconstruction." |
2. Sample Size Used for the Test Set and Data Provenance
The document describes three distinct test sets for different validation studies.
-
Performance Analysis (Robustness, Stability, Generalizability):
- Sample Size:
- T1, T2, FLAIR group: 40 patients, 111 images.
- DWI group: 29 patients, 94 images.
- Data Provenance: Not explicitly stated regarding country of origin. The test set was "entirely independent from the dataset used for model training." The "Equipment Type" is listed as "Swoop v2" (with <1% Swoop Mk1.9), indicating prospective data collection or data acquired specifically for the V2 system.
- Sample Size:
-
Contrast-to-Noise Ratio (CNR) Validation:
- Sample Size: 15 patients, 46 images, 58 pathologies, 464 ROIs.
- Data Provenance: Not explicitly stated regarding country of origin. The "Equipment" is listed as "Swoop v2," suggesting data acquired for the V2 system.
-
Advanced Reconstruction Image Validation (Human Reader Study):
- Sample Size: 32 patients, 167 images. (Minimum of 16 images per sequence).
- Data Provenance: Not explicitly stated regarding country of origin. The "Equipment" is listed as "Swoop v2," suggesting data acquired for the V2 system.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Performance Analysis: This study used "a set of images including Swoop data, high field images, and synthetic contrast images" as "ground truth target images." It does not mention human experts directly establishing ground truth for this reconstruction quality metric. The ground truth was based on pre-existing high-quality images.
- Contrast-to-Noise Ratio (CNR) Validation: "Regions of interest (ROI) encompassing pathologies were annotated and reviewed by two American Board of Radiology (ABR) certified radiologists." Their qualifications are explicitly stated: ABR-certified radiologists.
- Advanced Reconstruction Image Validation (Human Reader Study): "Five external, ABR-certified radiologists representing clinical users were asked to review side-by-side clinical image sets." Their qualifications are explicitly stated: ABR-certified radiologists.
4. Adjudication Method for the Test Set
- Performance Analysis: Not applicable as ground truth was defined by reference images and quantitative metrics.
- Contrast-to-Noise Ratio (CNR) Validation: "ROIs were annotated and reviewed by two ABR-certified radiologists." "All annotated images were then reviewed, and inaccurate ROI annotations were excluded from the analysis." This suggests a consensus/review process, but a specific "2+1" or "3+1" formal adjudication is not detailed. The wording implies a collaborative review to ensure quality of ROIs.
- Advanced Reconstruction Image Validation (Human Reader Study): Not applicable, as this was a reader study where each reader independently scored images. There was no explicit adjudication of differences in reader scores for a single case; rather, the median score across all readers was used for evaluation.
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
Yes, a multi-reader multi-case (MRMC) comparative effectiveness study was done. This is the "Advanced Reconstruction Image Validation" study.
- Study Design: Five ABR-certified radiologists reviewed side-by-side clinical image sets (Advanced vs. Linear Reconstruction) and rated image quality and consistency of diagnosis using a five-point Likert scale.
- Effect Size: The study found that "Advanced Reconstruction achieved a median score of 2 (the most positive rating scale value) in all categories."
- The Likert scale categories were noise, sharpness, contrast, geometric fidelity, artifact, and overall image quality.
- The acceptance criterion was "median score ≥0 on Likert scale" (at least as good) and "≥1 on Likert scale" in at least one category (better).
- Achieving a median score of 2 in all categories strongly indicates an improvement in perceived image quality and diagnostic consistency with Advanced Reconstruction compared to Linear Reconstruction. While not a direct measure of diagnostic accuracy improvement (e.g., AUC), it indicates a significant positive effect on the radiologists' perception and utility of the images. The exact numerical improvement (e.g., specific percentage increase in accuracy) is not provided, but the qualitative improvement is clear based on the scoring.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, standalone performance was evaluated through the "Performance Analysis" and the "Contrast-to-Noise Ratio Validation" studies.
- Performance Analysis: The study directly compared the output of the "Advanced Reconstruction" algorithm to a defined ground truth using quantitative metrics (NMSE, SSIM) without human interpretation as the primary endpoint.
- Contrast-to-Noise Ratio (CNR) Validation: This study measured the CNR of the algorithm's output independently, comparing it to the linear reconstruction, to ensure pathology features are preserved. While expert knowledge was used to annotate ROIs, the metric itself (CNR) is a direct, quantitative measure of the algorithm's output.
7. The Type of Ground Truth Used
Different types of ground truth were used depending on the study:
- Performance Analysis: "Reference-based metrics" using "a set of images including Swoop data, high field images, and synthetic contrast images" as "ground truth target images." This implies a reference image-based ground truth for evaluating reconstruction fidelity.
- Contrast-to-Noise Ratio (CNR) Validation: Relied on expert consensus/review for pathology ROI annotation by two ABR-certified radiologists. The CNR metric itself is a quantifiable measure derived from these annotations rather than a clinical outcome.
- Advanced Reconstruction Image Validation: The ground truth for comparative effectiveness was expert consensus/opinion (the subjective ratings of the five ABR-certified radiologists).
8. The Sample Size for the Training Set
The document states: "Performance analysis and validation of the subject device Advanced Reconstruction models was performed using a test dataset entirely independent from the dataset used for model training." However, the exact sample size for the training set is not disclosed in the provided text.
9. How the Ground Truth for the Training Set Was Established
The document states: "models are trained and validated with MRI data and images as the only inputs and outputs." It also mentions "synthetic k-space generated from the target images" for the performance analysis, suggesting that synthetic data or high-quality reference scans might have been part of the training data as well. However, the specific method for establishing the ground truth for the training set is not explicitly detailed in the provided text. It implies the training was done using existing MRI data, but does not specify how labels or ideal reconstructions were determined for that training data.
FDA Clearance Letter for Swoop® Portable MR Imaging® System (V2)
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
May 30, 2025
Hyperfine, Inc.
Christine Kupchick
Sr. Manager, Global Regulatory
351 New Whitfield St
Guilford, Connecticut 06437
Re: K250236
Trade/Device Name: Swoop® Portable MR Imaging® System (V2)
Regulation Number: 21 CFR 892.1000
Regulation Name: Magnetic Resonance Diagnostic Device
Regulatory Class: Class II
Product Code: LNH, MOS
Dated: May 7, 2025
Received: May 7, 2025
Dear Christine Kupchick:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Page 2
K250236 - Christine Kupchick Page 2
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-
Page 3
K250236 - Christine Kupchick Page 3
assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Daniel M. Krainak, Ph.D.
Assistant Director
DHT8C: Division of Radiological
Imaging and Radiation Therapy Devices
OHT8: Office of Radiological Health
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
Enclosure
Page 4
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.
Submission Number (if known)
Device Name
Swoop® Portable MR Imaging® System (V2)
Indications for Use (Describe)
The Swoop® Portable MR Imaging® System (V2) 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.
Type of Use (Select one or both, as applicable)
- Prescription Use (Part 21 CFR 801 Subpart D)
- Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services
Food and Drug Administration
Office of Chief Information Officer
Paperwork Reduction Act (PRA) Staff
PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
Page 5
510(k) Summary
Swoop® Portable MR Imaging® System (V2)
K250236
510(K) SUBMITTER
Company Name: Hyperfine, Inc.
Company Address: 351 New Whitfield St
Guilford, CT 06437
CONTACT
Name: Christine Kupchick
Telephone: (203) 343-3404
Email: ckupchick@hyperfine.io
Date Prepared: May 22, 2025
DEVICE IDENTIFICATION
Trade Name: Swoop® Portable MR Imaging® System (V2)
Common Name: Magnetic Resonance Imaging
Regulation Number: 21 CFR 892.1000
Classification Name: System, Nuclear Magnetic Resonance Imaging Coil, Magnetic Resonance
Product Code: LNH; MOS
Regulatory Class: Class II
PREDICATE DEVICE INFORMATION
The subject Swoop Portable MR Imaging System (V2) is substantially equivalent to the predicate Swoop System (K240944).
Page 6
DEVICE DESCRIPTION
The Swoop System (V2) 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 scan orders, exam setup, exam execution, viewing MRI image data for quality control purposes, and PACS 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 preview images. The Swoop System (V2) image reconstruction algorithm utilizes deep learning for optimized image quality.
INDICATIONS FOR USE
The Swoop Portable MR Imaging System (V2) 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.
SUBSTANTIAL EQUIVALENCE DISCUSSION
The table below compares the subject device to the predicate.
| Specification | Subject Swoop Portable MR Imaging System (V2) | Predicate Swoop Portable MR Imaging System (V1) (K240944) |
|---|---|---|
| INTENDED USE | ||
| Intended Use/ Indications for Use | 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. | Same |
| Patient Population | Adult and pediatric patients (≥ 0 years) | Same |
| Anatomical Sites | Head | Same |
| Environment of Use | At the point of care in professional health care facilities such as emergency rooms, intensive/critical care units, hospitals, outpatient, or rehabilitation centers. | Same |
| Energy Used and/or delivered | Magnetic Resonance | Same |
Page 7
| MAGNET | ||
|---|---|---|
| Field strength | 64.9 mT (nominal) | 63.3 ± 2.0 mT |
| Type | Permanent magnet | Same |
| Patient accessible bore size | 36.0 in. width, 13.4 in. height | 24.0 in. width, 12.4 in. height |
| Magnet weight | 712 lbs. | 705 lbs. |
| GRADIENT SYSTEM | ||
| Maximum gradient amplitude | X: 33.9 mT/mY: 33.2 mT/mZ: 66.2 mT/m | X: 24.3 mT/mY: 22.9 mT/mZ: 38.5 mT/m |
| Rise time (zero to max) | X: 1.8 msY: 1.8 msZ: 5.1 ms | X: 2.1 msY: 2.0 msZ: 3.8 ms |
| Slew rate | X: 18.8 T/m/sY: 18.4 T/m/sZ: 13.0 T/m/s | X: 24 T/m/sY: 22 T/m/sZ: 21 T/m/s |
| RF COIL | ||
| Type | Transmit/receive | Same |
| Transmit coil design | Linear | Same |
| OTHER | ||
| Patient weight capacity | 1.6kg-200 kg | Same |
| Operation temperature | 15-30 C | Same |
| Warm up time | <3 minutes | Same |
| Temperature control | No | Same |
| Humidity control | No | Same |
| SEQUENCES & IMAGE PROCESSING | ||
| T1W sequences | • T1 (Standard), T1 (Gray/White)• Advanced Gridding reconstruction | • Same• Same |
| T2W sequences | • T2, T2 (Fast)• Advanced Gridding reconstruction | • Same• Same |
| FLAIR sequences | • FLAIR, FLAIR (Fast)• Advanced Gridding reconstruction | • FLAIR only• Same |
| DWI/ADC sequences | • DWI/ADC, DWI/ADC (Fast)• Advanced Gridding + FISTA | • DWI/ADC only• FISTA only |
| Image post-processing (All Sequences) | • Advanced Denoising• Image orientation transform• Geometric distortion correction• Receive coil intensity correction• Advanced Interpolation• DICOM output | • Same• Same• Same• Same• n/a• Same |
The subject device and the predicate device have the same intended use, operating principles, and similar technological characteristics. The subject device differs from the predicate in hardware and software. These differences do not raise new questions of safety and efficacy as compared to the predicate.
Page 8
NON-CLINICAL PERFORMANCE
The subject device passed all the testing in accordance with internal requirements and applicable standards to support substantial equivalence to the predicate.
| Test | Test Description | Applicable Standard(s) |
|---|---|---|
| Verification | Verification testing in accordance with the design requirements. | • IEC 62304:2015• FDA Guidance, "Content of Premarket Submissions for Device Software Functions"• NEMA MS 1-2008 (R2020)• NEMA MS 3-2008 (R2020)• NEMA MS 9-2008 (R2020)• NEMA MS 12-2016• NEMA MS 8-2016• 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• FDA Guidance, "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions" |
| Validation | Validation to ensure the subject device meets user needs and performs as intended. | • FDA Guidance, "Content of Premarket Submissions for Device Software Functions"• FDA Guidance, "Applying Human Factors and Usability Engineering to Medical Devices• IEC 62366-1:2015+AMD1:2020 |
| Biocompatibility | Biocompatibility evaluation of patient-contacting materials. | • ISO 10993-1:2018• ISO 10993-5:2009• ISO 10993-10:2021• ISO 10993-23:2021 |
| Reprocessing | Cleaning and disinfection evaluation of patient-contacting materials. | • FDA Guidance, "Reprocessing Medical Devices in Health Care Settings: Validation Methods and Labeling"• ISO 17664:2021• ASTM F3208-20• AAMI TIR12:2020• ANSI/AAMI ST98:2022 |
Page 9
| Test | Test Description | Applicable Standard(s) |
|---|---|---|
| Safety | Electrical Safety, EMC, and Essential Performance testing. | • IEC 60601-1:2005 Ed.3+A1; A2• IEC 60601-1-2:2014 Ed.4+A1• IEC 60601-1-6:2010 Ed.3+A1; A2• IEC 60601-2-33:2015 Ed. 3.2 |
ADVANCED RECONSTRUCTION PERFORMANCE ANALYSIS AND VALIDATION
Performance analysis and validation of the subject device Advanced Reconstruction models was performed using a test dataset entirely independent from the dataset used for model training. The test dataset comprises a total of 58 individual subjects and 313 unique images collected using sequence types available on the subject device. For each subject, a subset of the following sequences, chosen appropriately for the indication for imaging, was scanned: T1 Gray-White, T1 Standard, T2, T2 Fast, FLAIR, FLAIR Fast, DWI, DWI Fast (DWI b=0, b=900, ADC). Axial, Sagittal, and Coronal orientations were included; for DWI sequences, only Axial was available. A description of the acceptance criteria and subset of data used for each test is included in the test summaries below.
In all cases, models are trained and validated with MRI data and images as the only inputs and outputs; there are no confounding factors and clinical subgroups are not defined or considered. While gender and age are available for most subjects, age, gender, ethnic background, and pathology are not expected to influence model architecture.
Performance Analysis:
Study Design:
Advanced Reconstruction was assessed for robustness, stability, and generalizability over a variety of subjects, design parameters, artifacts, and scan conditions using reference-based metrics.
A set of images including Swoop data, high field images, and synthetic contrast images, was used as ground truth target images. Test input data (synthetic k-space generated from the target images) was reconstructed using both Advanced and Linear Reconstruction, and the similarity to the original ground truth image was compared between the two reconstruction methods. Reconstruction outputs with motion and zipper artifacts were qualitatively assessed.
Reference Standard and Metrics:
Normalized mean squared error (NMSE) and structural similarity index (SSIM) were used to compare the ability of Advanced Reconstruction to reproduce the ground truth image compared to Linear Reconstruction.
Page 10
Dataset and Sample Size per Model:
Model/Sequence group: T1, T2, FLAIR
| Patients | 40 |
|---|---|
| Images | 111 |
| Demographics | |
| Gender | Female 38%Male 55%Unknown 7% |
| Age | 18-35 5%35-60 28%60+ 62%2+* 5% |
| Ethnicity Data | Not Recorded |
| Number of sites | 4 |
| Equipment Type | Swoop v2† |
| Pathology | Atrophy, Cerebellar Infarct, Chronic Infarct, Demyelinating diseases, Embolic Infarct, Hydrocephalus, Infarct, Intracerebral Hemorrhage, Intraparenchymal Hemorrhage, Lesion, M1 Occlusion, Mass Effect, Seizure, Stroke, Subdural Hemorrhage, Traumatic Brain Injury, Tumor, White Matter Disease, White Matter Lesion |
* Partially anonymized
† Contained Swoop Mk1.9 (<1%)
Model/Sequence group: DWI
| # of patient | 29 |
|---|---|
| # Images | 94 |
| Demographics | |
| Gender | Female 35%Male 55%Unknown 10% |
| Age | 18-35 7%35-60 21%60+ 65%2+* 7% |
| Ethnicity Data | Not Recorded |
| Number of sites | 4 |
| Equipment Type | Swoop v2 |
| Pathology | Atrophy, Cerebella Infarct, Chronic Infarct, Demyelinating Diseases, Embolic Infarct, Infarct, Intracerebral Hemorrhage, Intraparenchymal Hemorrhage, Lesion, M1 Occlusion, Mass Effect, Stroke, Subdural Hemorrhage, Traumatic Brain Injury, Tumor, White Matter Disease |
* Partially anonymized
Study Results:
For all models and all test datasets NMSE was reduced and SSIM was improved for Advanced Reconstruction test images compared to Linear Reconstruction test images. Advanced Reconstruction preserved the presentation of motion and zipper artifacts, and no unexpected output was observed.
Page 11
Contrast-to-Noise Ratio Validation
Study Design:
Regions of interest (ROI) encompassing pathologies were annotated and reviewed by two American Board of Radiology (ABR) certified radiologists. The contrast-to-noise of hyper- and hypo- intense pathologies were measured with respect to healthy white matter tissue from the same image. The inclusion criterion for images used for this study was at least one visible pathology.
Reference Standard and Metrics:
Linear Reconstruction was used as the reference standard for the comparison. Contrast-to-Noise Ratio (CNR) between pathology and healthy tissues was measured to quantify how accurately pathology features are preserved by Advanced Reconstruction.
The mean CNR of Advanced Reconstruction was required to be greater than the mean CNR of the baseline Linear Reconstruction at statistical significance level of 0.05 for each sequence type.
Dataset and Sample Size:
A minimum of 16 images per model type (sequence group) were included for lesion annotation. Pathologies spanning multiple slices were used multiple times. All annotated images were then reviewed, and inaccurate ROI annotations were excluded from the analysis. The data meeting inclusion criteria are described below.
| Patients | 15 |
|---|---|
| Images | 46 |
| Pathologies | 58 |
| ROIs | 464 |
| Demographics and other Variability | |
| Gender | Female 28%Male 70%Unknown 2% |
| Age | 35-60 28%60+ 70%2+* 2% |
| Ethnicity Data | Not Recorded |
| Number of sites | 2 |
| Equipment | Swoop v2 |
| Pathology | Atrophy, Demyelinating diseases, Embolic Infarct, Infarct, Intracereberal Hemorrhage, Intraparenchymal Hemorrhage, Lesion, Resection, Stroke, Thrombectomy, Tumor, White Matter Disease, White Matter Hyperintensity, White Matter Lesion |
*Partially anonymized
Study Results:
In all cases, CNR of Advanced Reconstruction was greater than or equal to Linear Reconstruction for both hyper- and hypo-intense pathologies. The study result demonstrates that Advanced Reconstruction does not unexpectedly modify, remove, or reduce the contrast of pathology features.
Page 12
Advanced Reconstruction Image Validation
Study Design:
Five external, ABR-certified radiologists representing clinical users were asked to review side-by-side clinical image sets taken with the subject Swoop System, reconstructed with both Advanced and Linear Reconstruction. The reviewers rated the images using a five-point scale for image quality and the consistency of diagnosis using both methods in the categories of noise, sharpness, contrast, geometric fidelity, artifact, and overall image quality.
Reference Standard and Metrics:
Linear Reconstruction was used as the reference standard for the comparison. Advanced Reconstruction was required to perform at least as well as Linear Reconstruction in all categories (median score ≥0 on Likert scale) and perform better (≥1 on Likert scale) in at least one of the quality-based categories.
Dataset and Sample Size:
A sample size of at least 16 was used per sequence. Within the sample dataset at least four cases for each sequence-available image orientation (axial, sagittal, coronal) were used.
| Patients | 32 |
|---|---|
| Images | 167 |
| Demographics and other Variability | |
| Gender | Female 28%Male 70%Unknown 2% |
| Age | 18-35 1%35-60 25%60+ 35%2+* 39% |
| Ethnicity Data | Not Recorded |
| Number of sites | 3 |
| Equipment | Swoop v2 |
| Pathology | Included pathology: Atrophy, Chronic Infarct, Demyelinating diseases, Embolic Infarct, Hemorrhage, Hydrocephalus, Infarct, Intracereberal Hemorrhage, Intraparenchymal Hemorrhage, Lesion, M1 Occlusion, Mass Effect, Stroke, Subdural Hemorrhage, Traumatic Brain Injury, Tumor, White Matter Disease |
*Partially anonymized
Test Results:
Advanced Reconstruction achieved a median score of 2 (the most positive rating scale value) in all categories. This scoring indicates reviewers found Advanced Reconstruction improved image quality while maintaining diagnostic consistency relative to Linear Reconstruction.
Page 13
CONCLUSION
Based on the intended use, technological characteristics, performance results, and comparison to the predicate, the subject Swoop Portable MR Imaging System (V2) has been shown to be substantially equivalent to the predicate and there are no new questions of safety and effectiveness.
§ 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.