Hyperfine, Inc. · Class II · Cleared May 21, 2025
| K-number | K251276 |
| Device name | Swoop® Portable MR Imaging® System |
| Applicant | Hyperfine, Inc. |
| Product code | LNH |
| Device class | Class II |
| Decision date | May 21, 2025 |
| Decision | Substantially Equivalent |
| Regulation | 892.1000 |
The Swoop Portable MR Imaging System is a portable, ultra-low field magnetic resonance imaging device that produces images of the internal head structures in situations where full diagnostic examination is not clinically practical. When interpreted by a trained physician, these images provide diagnostic information useful in determining patient diagnosis.
The subject device has identical physical specifications to the predicate (835×630×652 mm, 320 kg, 63.3 mT permanent magnet, identical gradient strength and rise times). The main differences are software modifications related to pulse sequences and image processing, including an advanced reconstruction algorithm using deep learning to improve image quality for T1W, T2W, FLAIR, and DWI sequences, plus advanced interpolation capabilities in post-processing.
IEC 62304:2016, NEMA MS 1/3/9/12-2008/2016, ISO 10993-1/5/10:2018/2009/2010, ISO 17664:2017, ASTM F3208-17, ANSI/AAMI ES 60601-1:2005/(R)2012, IEC 60601-1-2:2014, IEC 60601-1-6:2013, FDA Guidance on Device Software Functions and Cybersecurity, American College of Radiology standards for named sequences.
The subject device shares identical intended use, patient population, anatomical site, operating principles, and hardware specifications with the predicate (K240944). The only modifications are software-based improvements to pulse sequences and image processing algorithms. Risk-based assessment determined these changes do not introduce new worst-case scenarios; extensive performance testing (image quality, contrast-to-noise ratio, radiologist validation) demonstrated Advanced Reconstruction maintains diagnostic consistency while improving image quality, and does not unexpectedly modify or remove pathology features compared to Linear Reconstruction baseline.
View the full FDA submission: accessdata.fda.gov