BrainInsight is intended for automatic labeling, spatial measurement, and volumetric quantification of brain structures from a set of low-field MR images and returns annotated and segmented images, color overlans and reports.

Device Description

BrainInsight is a fully automated MR imaging post-processing medical software that provides image alignment, whole brain segmentation, ventricle segmentation, and midline shift measurements of brain structures from a set of MR images from patients ages 18 years or older. The BrainInsight processing architecture includes a proprietary automated internal pipeline based on machine learning tools. The output annotated and segmented images are provided in standard image format using segmented color overlays and reports that can be displayed on third-party workstations and FDA-cleared Picture Archive and Communications Systems (PACS).

The modified BrainInsight described in this submission includes changes to the machine learning models to allow for the processing Al-reconstructed low-field MR images. The modified device also includes configuration updates and refactoring changes for incremental improvement.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the BrainInsight device, based on the provided text:

BrainInsight Acceptance Criteria and Study Details

1. Table of Acceptance Criteria and Reported Device Performance

For Midline Shift:

Application	Acceptance Criteria (Error Range)	Reported Device Performance (Mean Absolute Error)
Midline Shift	"no worse than the average annotator discrepancy" (non-inferiority)	T1 Error: 1.03 mm T2 Error: 0.97 mm

For Lateral Ventricles and Whole Brain Segmentation (Dice Overlap):

Application	Acceptance Criteria (Dice Overlap)	Reported Device Performance (Dice Overlap [%])
T1 Left Ventricle	"no worse than the average annotator discrepancy" (non-inferiority)	84
T1 Right Ventricle	"no worse than the average annotator discrepancy" (non-inferiority)	82
T1 Whole Brain	"no worse than the average annotator discrepancy" (non-inferiority)	95
T2 Left Ventricle	"no worse than the average annotator discrepancy" (non-inferiority)	81
T2 Right Ventricle	"no worse than the average annotator discrepancy" (non-inferiority)	79
T2 Whole Brain	"no worse than the average annotator discrepancy" (non-inferiority)	96

For Lateral Ventricles and Whole Brain Segmentation (Volume Differences):

Application	Acceptance Criteria (Volume Differences)	Reported Device Performance (Volume Differences [%])
T1 Left Ventricle	"no worse than the average annotator discrepancy" (non-inferiority)	8
T1 Right Ventricle	"no worse than the average annotator discrepancy" (non-inferiority)	7
T1 Whole Brain	"no worse than the average annotator discrepancy" (non-inferiority)	3
T2 Left Ventricle	"no worse than the average annotator discrepancy" (non-inferiority)	11
T2 Right Ventricle	"no worse than the average annotator discrepancy" (non-inferiority)	19
T2 Whole Brain	"no worse than the average annotator discrepancy" (non-inferiority)	5

2. Sample Size Used for the Test Set and Data Provenance

The document does not explicitly state the numerical sample size for the test set. It mentions the distribution of categories:

Age: Min: 19, Max: 77
Gender: 59% Female / 41% Male
Pathology: Stroke (Infarct), Hydrocephalus, Hemorrhage (SAH, SDH, IVH, IPH), Mass/Edema, Tumor, Multiple sclerosis.

Data Provenance: The images were acquired from "multiple sites" using the "FDA cleared Hyperfine Swoop Portable MR imaging system." It is implied to be retrospective as data collection occurred before the testing. The country of origin is not specified but is likely the US given the FDA submission.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

The text states that "Ground truth for midline shift was determined based on the average shift distance of all annotators" and "Ground truth for segmentation is calculated using Simultaneous Truth and Performance Level Estimation (STAPLE)." It also mentions that "The datasets were annotated by multiple experts." However, the exact number of experts used for the test set's ground truth and their specific qualifications (e.g., "radiologist with 10 years of experience") are not explicitly stated.

4. Adjudication Method for the Test Set

The ground truth for midline shift was determined by the average shift distance of all annotators. For segmentation, the Simultaneous Truth and Performance Level Estimation (STAPLE) method was used. This implies a form of consensus-based adjudication, but not a strict numerical rule like 2+1 or 3+1. STAPLE is a probabilistic approach to estimate a true segmentation from multiple expert segmentations while simultaneously estimating the performance level of each expert.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

The document describes a standalone performance study of the algorithm against expert annotations, but does not mention a multi-reader multi-case (MRMC) comparative effectiveness study where human readers' performance with and without AI assistance is compared. Therefore, no effect size of human improvement with AI assistance is provided.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

Yes, a standalone performance study was conducted. The device's performance (Midline Shift, Dice Overlap, Volume Differences) was evaluated directly against a ground truth established by annotators, and the results were compared to the average annotator discrepancy to demonstrate non-inferiority. This is a standalone evaluation of the algorithm's performance.

7. Type of Ground Truth Used

The ground truth used was expert consensus.

For midline shift, it was based on the "average shift distance of all annotators."
For segmentation, it was calculated using "Simultaneous Truth and Performance Level Estimation (STAPLE)" from multiple expert annotations.

8. Sample Size for the Training Set

The document does not explicitly state the numerical sample size for the training set. It only mentions that "Each model was trained using a training dataset to optimize parameters" and "The data collection for the training and validation datasets were done at multiple sites."

9. How the Ground Truth for the Training Set Was Established

The ground truth for the training set was established through expert annotation. The text states: "The datasets were annotated by multiple experts. The entire group of training image sets was divided into segments and each segment was given to a single expert. The expert's determination became the ground truth for each image set in their segment."

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health and Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Hyperfine, Inc. % Christine Kupchick Sr. Regulatory Specialist 351 New Whitfield Street GUILFORD CT 06437

Re: K220815

July 19, 2022

Trade/Device Name: BrainInsight Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QIH Dated: June 22, 2022 Received: June 23, 2022

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 (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 located 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.

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 of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see

{1}------------------------------------------------

https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-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 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 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-device-safety/medical-device-reportingmdr-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/medicaldevices/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-device-advice-comprehensive-regulatoryassistance/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,

Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Ouality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K220815

Device Name BrainInsight

Indications for Use (Describe)

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 the salled in the maintain and maintain the data needed and complex including the different the 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."

FORM FDA 3881 (6/20)

Form Approved: OMB No. 0910-0120 Expiration Date: 06/30/2023 See PRA Statement below.

{3}------------------------------------------------

HYPERFINE

510(k) SUMMARY K220815

510(k) Submitter

Company Name:	Hyperfine, Inc.
Company Address:	351 New Whitfield StGuilford, CT 06437

Contact

Name:	Christine Kupchick
Telephone:	(203) 343-3404
Email:	ckupchick@hyperfine.io

July 14, 2022 Date Prepared:

Device Identification

Trade Name:	BrainInsight
Common Name:	MR Imaging Post-Processing Software
Regulation Number:	21 CFR 892.2050
Product Code:	QIH
Regulatory Class:	Class II

Predicate Device Information

The subject BrainInsight is substantially equivalent to the predicate BrainInsight (K202414). The predicate device has not been subject to a design-related recall.

Device Description

{4}------------------------------------------------

Indications for Use

Technological Characteristics

The subject device has the same intended use, fundamental technology, and operating principles, as the predicate (K202414). Therefore, the subject device is substantially equivalent to the predicate.

Substantial Equivalence Discussion

The table below compares the subject device to the predicate.

Attribute	Subject BrainInsight	Predicate BrainInsight (K202414)
Indications for Use	BrainInsight is intended for automatic labeling,spatial measurement, and volumetricquantification of brain structures from a set oflow-field MR images and returns annotated andsegmented images, color overlays and reports.	Same
Target AnatomicalSites	Brain	Same
Patient Population	Adult (≥ 18 years)	Same
Technology	Automated measurement of brain tissuevolumes and structures of Al-reconstructedlow-field MR images Automatic segmentation and quantificationof brain structures of Al-reconstructed low-field MR images using machine learningtools	Automated measurement of braintissue volumes and structures ofconventional low-field MR images Automatic segmentation andquantification of brain structures ofconventional low-field MR imagesusing machine learning tools
Method of Use	MR images are automatically sent toBrainInsight, and processed images areautomatically returned in ~7 minutes	Same
User Interface /PhysicalCharacteristics	No software required Operates in a serverless cloud environment User interface through PACS (multiplevendors)	Same
Operating System	Supports Linux	Same
ProcessingArchitecture	Automated internal pipeline that performs:segmentation volume calculation distance measurement numerical information display	Same
Data Source	MRI Scanner: Hyperfine Swoop FSE MRIscans acquired with specified protocols Supports DICOM format as input	Same
Output	Provides volumetric measurements of brainstructures:Includes segmented color overlays andmorphometric reports	Same

{5}------------------------------------------------

	Supports DICOM format as output of results that can be displayed on DICOM workstations and PACS
Safety	Automated quality control functions:Tissue contrast check Scan protocol verification Atlas alignment check Results must be reviewed by a trained physician	Same

Performance

As part of demonstrating substantial equivalence to the predicate, a risk analysis was completed to identify the risks associated with the software modifications. Software verification as related to the modifications was performed per IEC 62304:2006 and as recommended in the FDA Guidance, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." The subject device passed all the testing in accordance with internal requirements and applicable standards to support substantial equivalence.

Each model was trained using a training dataset to optimize parameters and a separate validation dataset to select the best set of parameters. Comparing the training and validation metrics helps to monitor and prevent overfitting. The datasets were augmented to improve robustness using standard techniques that apply transformations to the input data. The testing dataset was separate from training and validation datasets. Each subject was assigned a unique identifier and all subjects in training and validation data were excluded from the test set.

The data collection for the training and validation datasets were done at multiple sites. Each site used the T1 and T2 sequences from the FDA cleared Hyperfine Swoop Portable MR imaging system. The datasets were annotated by multiple experts. The entire group of training image sets was divided into segments and each segment was given to a single expert. The expert's determination became the ground truth for each image set in their segment. Each model and application were validated using an appropriate sample size to yield statistically significant results. All test images were acquired using the latest Swoop software version. The test set had the following distribution:

Category	Data Distribution
Age	Min: 19 Max: 77
Gender	59% F / 41% M
Pathology	Stroke (Infarct) Hydrocephalus Hemorrhage (SAH, SDH, IVH, IPH) Mass/Edema Tumor Multiple sclerosis

{6}------------------------------------------------

Quantitative evaluation was performed to validate performance using software. The performance of the model and the annotators to the consensus-based annotation was computed to ensure that the model performance is no worse than the average annotator. The acceptance criteria were defined based on non-inferiority testing, in which the model discrepancy to the annotators can be no worse than the average annotator discrepancy.

The mean absolute error was used to calculate the error range for midline shift. Ground truth for midline shift was determined based on the average shift distance of all annotators.

Application	T1 Error	T2 Error
Midline Shift	1.03 mm	0.97 mm

The mean Dice coefficient was used to calculate the error range for the lateral ventricles and whole brain. Ground truth for segmentation is calculated using Simultaneous Truth and Performance Level Estimation (STAPLE).

Application	Dice Overlap [%]		Volume Differences [%]
T1	Device	Annotator	Device	Annotator
Left Ventricle	84	90	8	8
Right Ventricle	82	89	7	11
Whole Brain	95	97	3	2

Application	Dice Overlap [%]		Volume Differences [%]
T2	Device	Annotator	Device	Annotator
Left Ventricle	81	84	11	27
Right Ventricle	79	84	19	26
Whole Brain	96	97	5	5

The test results show high accuracy of BrainInsight performance as compared to the reference and annotators and the subject device met all acceptance criteria.

{7}------------------------------------------------

Conclusion

Based on the indications for use, technological characteristics, performance results, and comparison to the predicate, the subject BrainInsight has been shown to be substantially equivalent to the predicate and does not present any new issues of safety or effectiveness.

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).