(138 days)
GyriCalc is intended for automatic labeling, visualization, and quantification including volume, surface area and gyrification analysis (i.e., gyrification index) of segmentable brain structures from a set of MR images.
GyriCalc is intended to be used by qualified personnel and interpreted by a qualified clinician.
GyriCalc is not intended to be used for visualization or quantification of neurologic lesions.
GyriCalc is intended for children between 24 to 36 months of age.
GyriCalc is an automated imaging post-processing software medical device (SaMD) that provides automatic labeling, visualization, volumetric quantification, surface area, thickness and gyrification analysis of brain structures for children ages 24-36 months of age from a set of MR images and returns segmented images and morphometric reports. GyriCalc is a proprietary application which incorporates customized, state-of-the-art open-source software to perform image analysis and quantitative functionality.
The resulting output is provided as a PDF report with segmented color overlays and morphometric reports that can be displayed on commonly used Off The Shelf (OTS) PDF viewer. GyriCalc is not intended to be used for image review. The PDF report is the sole output of the device.
GyriCalc provides morphometric measurements based on 3D T1 MRI series. The output of the software includes volumes that have been annotated with color overlays, with each color representing a particular segmented region, and morphometric reports that provide measured volumes and other qualitative and quantitative data.
GyriCalc's processing architecture includes functionality that performs:
• Preprocessing
- Artifact correction (correct for various artifacts and distortions, such as motion, intensity inhomogeneity, and scanner-related differences),
- Skull-stripping to remove non-brain tissue,
- Bias field correction,
- Intensity normalization,
• Volumetric measurement,
• Surface area measurement,
• Morphological/morphometric analysis,
• Gyrification measurement and report generation.
Here's an analysis of the acceptance criteria and the study proving GyriCalc meets them, based on the provided FDA 510(k) Clearance Letter.
Acceptance Criteria and Device Performance for GyriCalc
1. Table of Acceptance Criteria and Reported Device Performance
| Metric | Region(s) Covered | Acceptance Criteria (Pre-specified) | Reported Device Performance (Mean Absolute Error) | Meets Criteria? |
|---|---|---|---|---|
| Dice's Coefficient (Segmentation Accuracy) | All regions | 0.92 - 0.99 (confidence range) | 0.92 - 0.99 (average of 0.95) | Yes |
| Volume Measurement Error | Total Cortex, Superior Frontal, Middle Frontal, Fusiform, Inferior Temporal, Lingual | Below 10% | 0.45% - 5.33% | Yes |
| Volume Measurement Error | Inferior Parietal Gyrus (Left) | Below 10% | 12.10% [8.44%, 15.77%] | No |
| Volume Measurement Error | Cuneus (Left & Right) | Below 10% | Left: 10.75% [8.50%, 13.00%], Right: 10.18% [7.79%, 12.57%] | No |
| Surface Area Measurement Error | Superior Frontal, Middle Frontal, Fusiform, Inferior Temporal, Lingual | Below 10% | 0.33% - 8.42% | Yes |
| Surface Area Measurement Error | Inferior Parietal Gyrus (Left) | Below 10% | 12.58% [8.72%, 16.43%] | No |
| Surface Area Measurement Error | Cuneus (Left & Right) | Below 10% | Left: 11.64% [8.75%, 14.54%], Right: 11.28% [8.51%, 14.05%] | No |
| Gyrification Index Error | All regions of interest | Below 10% | 0.04% - 0.89% | Yes |
Note: While some regions did not meet the stated pre-specified acceptance criteria for volume and surface area errors, the FDA still granted clearance, implying these deviations were considered acceptable in the overall context of safety and effectiveness, or that other factors mitigated the concern.
2. Sample Size and Data Provenance for the Test Set
- Sample Size: 82 T1 head MRIs from 82 patients.
- Data Provenance:
- Country of Origin: U.S. (54 patients) and Brazil (28 patients).
- Retrospective or Prospective: Retrospective. The imaging data was collected retrospectively from a population of anonymized patients with curated clinical records. The dataset represents a new, independent sampling of patients that were not involved in the development of the device.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: A total of 6 experts were used, divided into two groups:
- Group 1 (32 cases): 2 U.S.-based neuroradiologists and 1 U.S.-based neuroimaging consultant PhD. (Specific years of experience are not mentioned, but their titles imply high qualification.)
- Group 2 (50 cases): 3 U.S.-based neuroradiologists. (Specific years of experience are not mentioned, but their titles imply high qualification.)
- Qualifications of Experts: Neuroradiologists and a Neuroimaging Consultant PhD. These are highly specialized medical professionals with expertise in interpreting and analyzing brain MRI images and neuroanatomy.
4. Adjudication Method for the Test Set
- Method: The segmentations of the 3 experts for each MRI were combined using the STAPLE method (Simultaneous Truth and Performance Level Estimation) to produce a single, consolidated segmentation. This method statistically estimates a consensus segmentation from multiple expert annotations, weighting each expert's contribution based on their estimated accuracy.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was it done?: No, an MRMC comparative effectiveness study involving human readers assisting with or without AI was not reported. The study focused on the standalone performance of the AI algorithm against expert manual segmentations (ground truth). The document states, "The subject device (GyriCalc) and the predicate device (NeuroQuant) have the same automated quality control functions. Results must be reviewed by a qualified clinician." This indicates the device is intended as a support tool, implying a human-in-the-loop scenario, but the reported study does not compare human performance with and without the AI.
- Effect Size of Human Improvement with AI vs. Without AI Assistance: Not applicable, as this type of study was not conducted or reported.
6. Standalone (Algorithm Only) Performance Study
- Was it done?: Yes. The entire clinical performance assessment detailed in section 9.2 focuses on the standalone performance of the GyriCalc algorithm by comparing its output (segmentations and measurements) directly against expert-derived ground truth.
7. Type of Ground Truth Used
- Type: Expert Consensus Segmentation.
- For each brain MRI, three experts independently annotated and edited pre-loaded segmentations.
- These three expert segmentations were then combined using the STAPLE method to create a single, consolidated reference standard (ground truth).
- Reference measurements (volume, surface area, gyrification index) were then derived from this combined segmentation.
8. Sample Size for the Training Set
- Sample Size: The document does not specify the sample size used for the training set. It only describes the test set used for performance validation.
9. How Ground Truth for Training Set Was Established
- Method: The document does not explicitly state how the ground truth for the training set was established. It describes the ground truth establishment for the test set (expert consensus via STAPLE). For AI/deep learning models, training data often uses similar or less rigorous ground truth methods, or sometimes pseudo-labeling, but this information is not provided in the supplied text.
FDA 510(k) Clearance Letter - GyriCalc
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.08.00
July 22, 2025
NeuroSpectrum Insights Corp.
℅ James Luker
Sr. Regulatory Consultant
Innolitics LLC
1101 W 34th St. Suite 550
Austin, Texas 78705
Re: K250686
Trade/Device Name: GyriCalc (Version 1.0.0)
Regulation Number: 21 CFR 892.2050
Regulation Name: Medical Image Management And Processing System
Regulatory Class: Class II
Product Code: LLZ
Dated: June 20, 2025
Received: June 20, 2025
Dear James Luker:
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.
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"
Page 2
K250686 - James Luker Page 2
(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-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).
Page 3
K250686 - James Luker Page 3
Sincerely,
Digitally signed by Michael D. O'hara -S
Date: 2025.07.22 12:22:45 -04'00'
for
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)
K250686
Device Name
GyriCalc
Indications for Use (Describe)
GyriCalc is intended for automatic labeling, visualization, and quantification including volume, surface area and gyrification analysis (i.e., gyrification index) of segmentable brain structures from a set of MR images.
GyriCalc is intended to be used by qualified personnel and interpreted by a qualified clinician.
GyriCalc is not intended to be used for visualization or quantification of neurologic lesions.
GyriCalc is intended for children between 24 to 36 months of age.
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
(21 CFR 807.92(c))
510(k) Summary Page 1 of 21
1. CONTACT INFORMATION
| Company Name | NeuroSpectrum Insights Corp. |
|---|---|
| Address | 376 Main St. Suite 100, Bedminster NJ 07921 |
| Phone Number | 908-304-4858 |
| Company Representative | Andrew D. Stewart, CEO |
| Official Correspondent | James Luker, Innolitics |
| JLuker@Innolitics.com | |
| Date Prepared | March 2, 2025 |
2. DEVICE INFORMATION
| Trade Name | GyriCalc |
|---|---|
| Common Name | Neuroanatomy measuring software |
| Product Code | LLZ |
| Regulation Number | 892.2050 |
| Class | Class II |
| Panel | Radiology |
3. PREDICATE DEVICE INFORMATION
| Predicate Device Name | NeuroQuant |
|---|---|
| Predicate Device K Number | K170981 |
| Product Code | LLZ |
| Regulation Number | 892.2050 |
Page 6
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 2 of 21
| Class | Class II |
|---|---|
| Panel | Radiology |
4. DEVICE DESCRIPTION
GyriCalc is an automated imaging post-processing software medical device (SaMD) that provides automatic labeling, visualization, volumetric quantification, surface area, thickness and gyrification analysis of brain structures for children ages 24-36 months of age from a set of MR images and returns segmented images and morphometric reports. GyriCalc is a proprietary application which incorporates customized, state-of-the-art open-source software to perform image analysis and quantitative functionality.
The resulting output is provided as a PDF report with segmented color overlays and morphometric reports that can be displayed on commonly used Off The Shelf (OTS) PDF viewer. GyriCalc is not intended to be used for image review. The PDF report is the sole output of the device.
GyriCalc provides morphometric measurements based on 3D T1 MRI series. The output of the software includes volumes that have been annotated with color overlays, with each color representing a particular segmented region, and morphometric reports that provide measured volumes and other qualitative and quantitative data.
GyriCalc's processing architecture includes functionality that performs:
• Preprocessing
- Artifact correction (correct for various artifacts and distortions, such as motion, intensity inhomogeneity, and scanner-related differences),
- Skull-stripping to remove non-brain tissue,
- Bias field correction,
- Intensity normalization,
• Volumetric measurement,
• Surface area measurement,
• Morphological/morphometric analysis,
• Gyrification measurement and report generation.
Detailed descriptions of the above functionality are provided below.
Page 7
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 3 of 21
Artifact correction
GyriCalc includes the following artifact correction functionality:
• Motion correction,
• Phase unwrapping,
• Slice timing correction,
• Intensity inhomogeneity correction,
• Distortion correction,
• Susceptibility artifact correction,
Automated segmentation
GyriCalc includes the following segmentation functionality:
• Right/Left Hemispheres (Pial) surface segmentation
• Cortical region segmentation/parcellation
- Right/Left Superior Frontal Gyri
- Right/Left Middle Frontal Gyri
- Right/Left Cuneus
- Right/Left Lingual Gyri
- Right/Left Inferior Temporal Gyri
- Right/Left Inferior Parietal Cortex
- Right/Left Fusiform Gyri
Volumetric Measurement
GyriCalc includes the following volumetric measurement functionality:
• Total Cortex volume
• Right/Left Cortex volume
• Cortical region volume:
- Right/Left Superior Frontal volume
- Right/Left Middle Frontal volume
- Right/Left Cuneus volume
Page 8
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 4 of 21
- Right/Left Lingual volume
- Right/Left Inferior Temporal volume
- Right/Left Inferior Parietal Cortex volume
- Right/Left Fusiform volume
Morphological/morphometric analysis
GyriCalc includes surface area and gyrification index measurement functionality for the following regions of the brain
• Total Cortex
• Left/Right Cortex
• Cortical regions:
- Right/Left Superior Frontal
- Right/Left Middle Frontal
- Right/Left Cuneus
- Right/Left Lingual
- Right/Left Inferior Temporal
- Right/Left Inferior Parietal Cortex
- Right/Left Fusiform
5. INDICATIONS FOR USE
GyriCalc is intended for automatic labeling, visualization, and quantification including volume, surface area and gyrification analysis (i.e., gyrification index) of segmentable brain structures from a set of MR images.
GyriCalc is intended to be used by qualified personnel and interpreted by a qualified clinician.
GyriCalc is not intended to be used for visualization or quantification of neurologic lesions.
GyriCalc is intended for children between 24 to 36 months of age.
Page 9
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 5 of 21
6. SUBSTANTIAL EQUIVALENCE DISCUSSION
6.1. Device Comparison Table
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 | Same |
| Regulation Description | Medical image management and processing system | Picture archiving and communications system | Same |
| Classification Name | System, Image Processing, Radiological | System, Image Processing, Radiological | Same |
| Class | Class II | Class II | Same |
| Product Code | LLZ | LLZ | Same |
| Device Description Device type | Software medical device (SaMD) | Software medical device (SaMD) | Same- Both devices are SaMD |
| Physical characteristics | • Software package• Operates on off-the-shelf hardware (multiple vendors) | • Software package• Operates on off-the-shelf hardware (multiple vendors) | Same |
| Operating System | Client: Supports Windows 11 or MAC OS 12Server: Ubuntu 23.04 LTS | Supports Linux, Mac OS X and Windows | EquivalentBoth the subject and predicate devices are software devices (SaMD) which run on industry standard computing hardware and Operating Systems. The GyriCalc device has been tested to confirm that it meets it's stated requirements and performs as intended on the stated operating system(s). GyriCalc does not support the Linux OS. This difference does not affect the safety or effectiveness as compared to the NeuroQuant predicate device. |
Page 10
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 6 of 21
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| General Device Description | Fully automated MR imaging post-processing medical device software which includes:-automatic labeling, visualization and volumetric quantification of brain structures from a set of MR images and returns segmented images and morphometric reports.(Morphometric measurements based on 3D T1 MRI series) | Fully automated MR imaging post-processing medical device software which includes:-automatic labeling, visualization and volumetric quantification of brain and lesions from a set of MR images and returns segmented images and morphometric reports.(Morphometric measurements based on 3D T1 MRI series) | EquivalentThe primary functionality is the same with the exception that the subject GyriCalc device does not include lesion labeling or volumetric quantification of such lesions.As lesion detection is not intended to be performed by GyriCalc, its absence does not affect Intended Use, safety or effectiveness comparison of the subject and predicate devices.The subject device measurements include volume, area and gyrification whereas the predicate device provides only volume measurement. The addition of area and gyrification measurements are considered technological characteristics which are supported by clinical performance testing. As the area and gyrification are also measurements, they do not add a new 'intended use' and do not affect the safety and/or effectiveness of the subject device as compared to the predicate device or raise new questions relating to safety and/or effectiveness. |
| Design and Incorporated Technology | - Automated measurement of brain tissue structures for volume, area and gyrification.- Automatic segmentation and quantification of brain structures using deep learning | • Automated measurement of brain tissue volumes and structures and lesions• Automatic segmentation and quantification of brain structures using a dynamic probabilistic neuroanatomical atlas, with age and gender specificity, based on the MR image intensity | EquivalentThe design and technological characteristics of the subject GyriCalc device and the predicate NeuroQuant device are equivalent. Both devices are software medical devices (SaMD) and utilize DICOM MRI images of the brain which are automatically segmented into regions and then perform measurements.The subject device measurements include volume, area and gyrification whereas the predicate device provides only volume measurement. The addition of area and gyrification are considered technologic characteristics which are supported by clinical performance testing. As the area and |
Page 11
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 7 of 21
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| gyrification are also measurements, they do not add a new 'intended use' and do not affect the safety and/or effectiveness of the subject device as compared to the predicate device or raise new questions relating to safety and/or effectiveness.Differences:-GyriCalc does not include lesion quantification functionality whereas the NeuroQuant predicate does. Lesion quantification functionality is not an aspect of GyriCalc's intended use and does not affect the safety or effectiveness as compared to the predicate device.-GyriCalc's automated segmentation utilizes FreeSurfer's robust SynthSeg algorithm whereas the predicate device uses a dynamic probabalistic neuroanatomical atlas for its automated segmentation functionality. GyriCalc's segmentation results have been validated using an 'expert reader' study.Note: NEUROPHET (K220437) has been added as a Reference device to support the technological characteristic of the use of FreeSurfer for segmentation initialization. A separate comparison table is provided for the reference device.- GyriCalc does not include gender specificity. Gender specificity is not necessary for GyriCalc to perform its its intended use in a safe and effective manner.The differences do not affect the safety or effectiveness as compared to the predicate device and are supported by clinical performance testing. |
Page 12
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 8 of 21
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| Processing Architecture | Automated internal pipeline that performs: | Automated internal pipeline that performs: | Equivalent -The subject device and the predicate have similar processing architectures, with the exception that the subject device also uses gyrification analysis for measuring Local Gyrification Index (LGI). This additional technological characteristic (i.e., gyrification analysis) does not raise different questions of safety and effectiveness. The functionality has been supported by performance testing.Additionally, as previously stated, GyriCalc does not include lesion quantification as it is not within the scope of its intended use/indications. |
| - artifact correction- segmentation- volume calculation- gyrification analysis- report generation | - artifact correction- segmentation- lesion quantification- volume calculation- report generation | ||
| Data Source | • MRI scanner: 3D T1 MRI scans acquired with specified protocols from 1.5 and 3 Tesla MR imaging devices.• GyriCalc supports DICOM format as input | • MRI scanner: 3D T1 MRI scans acquired with specified protocols• NeuroQuant Supports DICOM format as input | EquivalentGyriCalc performance has been successfully tested on DICOM images from 1.5 and 3.0 Tesla MR imaging devices. The available information on the NeuroQuant predicate device does not appear to specify the magnet strength. However, the following note in the NeuroQuant Clinical Training material states that "Some NeuroQuant parameters vary depending on scanner manufacturer & field strength". This supports that NeuroQuant supports various magnet strengths. |
| Output | - Provides volumetric measurements of brain structures, including gyrification information- Includes segmented color overlays and morphometric reports- The information is provided as a .pdf report. | - Provides volumetric measurements of brain structures and lesions- Includes segmented color overlays and morphometric reports- Automatically compares results to reference percentile data and to prior scans when available- Supports DICOM format as output of results that can be displayed on DICOM workstations and | EquivalentBoth the GyriCalc subject device and the NeuroQuant predicate device provide volumetric measurements of brain structures and segmented color overlays and morphometric reports.DifferencesThe GyriCalc device provides gyrification information whereas NeuroQuant does not.This additional technological characteristic (i.e., gyrification analysis) does not raise different questions of safety and effectiveness. The |
Page 13
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 9 of 21
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| Picture Archive and Communications Systems | functionality has been supported by performance testing.GyriCalc does not compare results to reference percentile data and to prior scans. This functionality is not within the scope of GyriCalc's intended use/indications as GyriCalc is intended for quantification rather than comparison at this time. However, GyriCalc does include 'sample values' which are supported by the data used in the performance validation testing.GyriCalc does not output DICOM for display on PACS devices. GyriCalc's sole output is a .pdf report which can be viewed on standard .pdf reading applications or may be printed.The stated differences do not alter the intended use, safety or performance of the GyriCalc device as compared to the NeuroQuant predicate device. | ||
| Specific Device Output | Provides morphometric measurements based on 3D T1 MRI series | Provides morphometric measurements based on 3D T1 MRI series | Same |
| MR Scan Parameters | -Plane: Sagittal, Axial-Mode: –3D-Type: T1 weighted-Matrix: 256 x 256-Resolution: Ideally isotropic with a voxel size of 1mm x1mm x1mm-NEX/NSA: 1-Slice Thickness: 1 mm | Plane –sagittalMode –3DT1 weightedMatrix –192 x 192NEX / NSA 1Slice thickness –1.2 mmSpacing –1.2 mmNumber of slices –160 -170FOV 24 – 25.6 | EquivalentGyriCalc's MR Scan parameters are mainly the same (equivalent) to the NeuroQuant predicates parameters. GyriCalc's parameters are consistent with optimizing the images for analysis by the GyriCalc software. However, there are potentially minor variations between the parameters of the two devices which do not alter the safety, effectiveness or performance of the GyriCalc device. |
| Use Cases | For use in routine patient care as a support tool for | For use in both clinical trial research and routine patient | EquivalentGyriCalc does not explicitly intend the |
Page 14
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 10 of 21
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| clinicians in assessment of structural MRIs | care as a support tool for clinicians in assessment of structural MRIs | software to be used in clinical trials or research. | |
| Output (Brain Regions) | -Total brain-Left/Right Hemisphere (Cortex)- Left/Right Hemisphere (Cuneus)- Left/Right Hemisphere (Fusiform)- Left/Right Hemisphere (Inferiorparietal)- Left/Right Hemisphere (Inferiortemporal)- Left/Right Hemisphere (Lingual)- Left/Right Hemisphere (Middlefrontal)- Left/Right Hemisphere (Superiorfrontal) | -Total brain-Left/Right Hemisphere (Cortex)- Left/Right Occipital lobe- Left/Right Hemisphere (Fusiform)- Left/Right Hemisphere (Inferiorparietal)- Left/Right Hemisphere (Inferiortemporal)-Left/Right Hemisphere (Middlefrontal)- Left/Right Hemisphere (Superiorfrontal) | EquivalentBoth the subject GyriCalc device and the predicate NeuroQuant device segment and quantify the same structures. NeuroQuant appears to include additional brain structures in their reports which are not needed by GyriCalc to perform its intended use. |
| Output (Measurements) | Volume, Area, Gyrification Index | Volume | EquivalentBoth the subject GyriCalc and predicate NeuroQuant devices include volumetric measurements for the segmented brain regions. GyriCalc includes area measurements and gyrification measurements which are required for its stated intended use. The addition of area and gyrification measurements are technological differences which do not raise new questions relating to safety or effectiveness and have been successfully tested to assure accuracy. |
| Safety | Automated quality control functions- Tissue contrast check- Scan protocol verification- Atlas alignment check- Results must be reviewed by a qualified clinician | Automated quality control functions- Tissue contrast check- Scan protocol verification- Atlas alignment check- Results must be reviewed by a qualified physician | SameThe subject device (GyriCalc) and the predicate device (NeuroQuant) have the same automated quality control functions. |
Page 15
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 11 of 21
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| Report | GyriCalc results are documented in a pdf report which is available to the clinician | A report is generatedResults are provided in a standard DICOM format as additional MR series that can be displayed on third-party DICOM workstations and PACS. | EquivalentGyriCalc's sole output is a .pdf report which can be viewed digitally using standard .pdf reading software as well as can be printed if desired.GyriCalc does not provide DICOM series which can be viewed on third-party DICOM workstations and PACS as this functionality is not required for GyriCalc to perform its intended use. The absence of DICOM series output does not raise new questions relating to the safety or effectiveness of the GyriCalc device. |
| Cybersecurity | GyriCalc utilizes current 'state of the art' cybersecurity processes and controls which align with FDA's current guidance and recommendations. | No information is publicly available on cybersecurity. | Equivalent (or better)The K170981 submission of NeuroQuant did not contain specific information related to cybersecurity. In recent years, the requirements related to cybersecurity have greatly evolved. GyriCalc utilizes current 'state of the art' cybersecurity processes and controls which align with FDA's current guidance and recommendations. |
| Performance Testing | GyriCalc performance was evaluated by comparing segmentation accuracy with expert manual segmentations and by measuring segmentation reproducibility between same subject scans.The system yields reproducible results that are well correlated with computer-aided expert manual segmentations.GyriCalc's segmentation accuracy compared to expert manual segmentations of 3D T1 | NeuroQuant performance was evaluated by comparing segmentation accuracy with expert manual segmentations and by measuring segmentation reproducibility between same subject scans.The system yields reproducible results that are well correlated with computer-aided expert manual segmentations.NeuroQuant's segmentation accuracy compared to expert manual segmentations of 3D T1 | EquivalentThe performance of GyriCalc and NeuroQuant was verified using comparison against expert manual segmentation. The results of testing have confirmed equivalent performance.GyriCalc has equivalent segmentation accuracy performance for the major cortical regions is equivalent to the NeuroQuant predicate.Note 1: GyriCalc does not perform subcortical brain structures.Note 2: NEUROPHET (K220437) has been added as a Reference device to support the technological characteristic of the use of FreeSurfer for |
Page 16
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 12 of 21
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| MRI scans was evaluated using Dice's coefficient metric. The results were in the range of 92-99% with an average of 95% confidence.Volume Measurements:GyriCalc's mean percentage absolute volume difference of the major cortical regions was in the range of 0.45 -12.1 %Area Measurements:GyriCalc's mean absolute surface area error was in the range of 0.33 - 12.6 %.Gyrification Measurements:GyriCalc's mean absolute gyrification Index error was in the range of 0.04 - 0.89%.Description of Subjects:The imaging data was collected retrospectively from a population of anonymized patients 2-3 years (24-36 months) with curated clinical records.Safety and Effectiveness:The measurements met the predetermined acceptance criteria.Adverse Events:As the clinical performance testing was performed retrospectively on previously acquired T1 weighted MRI scans, there were no adverse events | MRI scans was evaluated using Dice's coefficient metric. For major subcortical brain structures Dice's coefficients are in the range of 80-90% and for major cortical regions are in the range of 75-85%. For lesion segmentations evaluated separately using 3D T1 and T2 FLAIR MRI scan pairs of subjects with brain lesions, Dice's coefficient exceeds 80%.Brain structure segmentation reproducibility of repeated 3D T1 MRI scans for same subjects was evaluated by using the percentage absolute volume differences. The mean percentage absolute volume differences for all major subcortical structures were in the range of 1-5%. Brain lesion segmentation reproducibility was evaluated separately using 3D T1 and T2 FLAIR MRI repeated scan pairs of subjects with brain lesions. The mean absolute lesion volume difference was less than 0.25cc, while the mean percentage lesion absolute volume difference was less than 2.5%. | segmentation initialization. A separate comparison table is provided for the reference device.Volume Measurements:GyriCalc performed in an equivalent manner to the NeuroQuant in terms of volumetric measurements. (Note: NeuroQuant reported on major subcortical structures rather than the major cortical structures)The NeuroQuant predicate device does not include area or gyrification measurements. These 'Technological Characteristics' are supported by the results of the clinical performance testing and do not raise new questions relating to safety and/or effectiveness as compared to the predicate device.GyriCalc does not perform lesion segmentations or quantification of lesions as this functionality is not within it's stated intended use/indications. As lesion functionality is not within GyriCalc's intended use, the lack of such functionality does not raise new questions related to safety or effectiveness of the GyriCalc device. |
Page 17
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 13 of 21
| Feature/Function | GyriCalc | NeuroQuant (K170981) Primary Predicate Device | Equivalence Discussion |
|---|---|---|---|
| (AEs) noted. |
7. REFERENCE DEVICE COMPARISON
(For segmentation methodology)
| Feature/Function | GyriCalc | NEUROPHET (K220437) Reference Device | Equivalence Discussion |
|---|---|---|---|
| Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 | Same |
| Regulation Description | Medical image management and processing system | Medical image management and processing system | Same |
| Classification Name | System, Image Processing, Radiological | System, Image Processing, Radiological | Same |
| Class | Class II | Class II | Same |
| Product Code | LLZ | LLZ | Same |
| Indications for Use | GyriCalc is intended for automatic labeling, visualization, and quantification including volume, surface area and gyrification analysis (i.e., gyrification index) of segmentable brain structures from a set of MR images.GyriCalc is intended to be used by qualified personnel and interpreted by a qualified clinician. | Neurophet AQUA is intended for Automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR images.Volumetric data may be | Equivalent -Both the subject device (GyriCalc) and the reference device (Neurophet AQUA) are intended to be used for automatic labeling, visualization, volumetric quantification of segmentable brain structures from a set of MR images.The subject device measurements include volume, area and gyrification whereas the reference device provides only volume measurement. The addition of area and gyrification measurements are considered technological characteristics which are supported by clinical performance testing. As the area and gyrification are also measurements, they do not add a new 'intended use' and do not affect the safety and/or effectiveness of the subject |
Page 18
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 14 of 21
| Feature/Function | GyriCalc | NEUROPHET (K220437) Reference Device | Equivalence Discussion |
|---|---|---|---|
| GyriCalc is not intended to be used for visualization or quantification of neurologic lesions.GyriCalc is intended for children between 24 to 36 months of age. | compared to reference percentile data. | device as compared to the reference device or raise new questions relating to safety and/or effectiveness.GyriCalc does not include a normative database with which to compare brain structures to 'normal' patients. This functionality is not needed as GyriCalc is intended for visualization and quantification only at this time. However, GyriCalc does include 'reference values' which are supported by the data used in the performance validation testing.For clarity, GyriCalc has added an explicit statement that the device is intended to be used by qualified personnel and interpreted by a qualified clinician. The reference Neurophet AQUA device Indications statement does not state this explicitly but it is assumed as Neurophet AQUA is an Rx only device. | |
| Target Anatomical Sites | Brain | Brain | Same |
| Data Source | - MRI scanner: 3D T1 scans acquired with specified protocols- Supports DICOM format as input. | - MRI scanner: 3D T1 scans acquired with specified protocols- Supports DICOM format as input. | Same |
| Design and Incorporated Technology | - Automated measurement of brain tissue volumes and structures.- Automatic segmentation and quantification of brain structures using deep learning. | - Automated measurement of brain tissue volumes and structures- Automatic segmentation and quantification of brain structures using deep learning | EquivalentBoth the subject GyriCalc and Reference NEUROPHET device perform segmentation based on deep-learning methodologies whereas the Primary Predicate device utilizes a technically similar 'atlas-based' segmentation methodology.GyriCalc's segmentation accuracy compared to expert manual segmentations of 3D T1 MRI scans was evaluated using Dice's coefficient metric. The results were in the range of 92-99% with an average of 95% confidence.The results of the segmentation support that the subject GyriCalc device is as safe and effective as the reference device. |
Page 19
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 15 of 21
8. SUMMARY OF TECHNOLOGICAL CHARACTERISTICS COMPARISON
GyriCalc is functionally equivalent to the primary predicate device (NeuroQuant K170981).
• Both the subject GyriCalc and predicate NeuroQuant devices are intended for automatic labeling, visualization and quantification of segmentable brain structures from a set of MR images.
• Both devices provide morphometric measurements based on 3D T1 MRI images.
• Both devices produce similar reports. The output includes volumes that have been annotated with color overlays, with each color representing a particular segmented region, and morphometric reports.
• Both devices utilize the same automated safety measures and have similar processing architecture.
• Both systems are used by qualified medical professionals as a support tool in assessment of structural MRIs.
• Both devices have been validated using clinical performance testing.
9. PERFORMANCE TESTING SUMMARY
9.1. Software Verification and Validation
Software verification and validation testing were conducted, and documentation was provided as recommended by 2023 FDA Guidance "Content of Premarket Submissions for Device Software Functions".
The software verification and validation testing verified that the design requirements were successfully met. The Intended use and user needs were successfully validated.
As the intended use, functionality and performance of the subject device and the predicate device are equivalent, the result of the performance testing is evidence that the GyriCalc performs in an equivalent manner to the NeuroQuant.
9.2. Clinical Performance Assessment
The performance of GyriCalc and NeuroQuant was verified using comparison against expert manual segmentation as well as measuring segmentation reproducibility between same subject
Page 20
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 16 of 21
scans. GyriCalc's segmentation accuracy compared to expert manual segmentations of 3D T1 MRI scans was evaluated using Dice's coefficient metric. The results were in the range of 0.92-0.99 with an average of 0.95 confidence.
Volume Measurements:
GyriCalc's mean percentage absolute volume difference of the major cortical regions was in the range of 0.45 -12.1 %
Area Measurements:
GyriCalc's mean absolute surface area error was in the range of 0.33 - 12.6 %.
Gyrification Measurements:
GyriCalc's mean absolute gyrification Index error was in the range of 0.04 - 0.89%.
9.2.1. Patient Population & Imaging Characteristics
The dataset used in the clinical performance assessment consisted of 82 T1 head MRIs from 82 patients with ages ranging from 24 to 36 months with normal-appearing brains. This dataset represents a new, independent sampling of patients that were not involved in the development of the device.
| Patient Characteristic | Count |
|---|---|
| Patient Sex | |
| Male | 57 |
| Female | 25 |
| Patient Age (months) | |
| 24-27 | 18 |
| 27-30 | 24 |
| 30-33 | 16 |
| 33-36 | 24 |
| Location |
Page 21
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 17 of 21
| Patient Characteristic | Count |
|---|---|
| U.S. | 54 |
| Brazil | 28 |
Imaging Characteristics
| Magnetic Field Strength | Count |
|---|---|
| 1.5 T | 67 |
| 3.0 T | 15 |
| Manufacturer | Count |
|---|---|
| Philips | 25 |
| GE | 56 |
| SIEMENS | 1 |
| Voxel Spacing (mm) | Median [Range] |
|---|---|
| Pixel Spacing X | 0.45 [0.35, 1.25] |
| Pixel Spacing Y | 0.45 [0.35, 1.30] |
| Slice Thickness | 3.00 [0.99, 5.00] |
| Slice Count | 48 [24, 341] |
|---|
Because MR imaging of healthy patients in the age range 24-36 months is rare, all patients selected had normal-appearing brains as described in radiological reports. Patients with traumatic brain injury, post-surgical changes, or brain lesions were excluded. The following tables summarize the reasons patients underwent an MRI study and the radiological findings/potential confounders for patients in the test dataset.
| Reason for MRI | Count * |
|---|---|
| Not specified | 29 |
Page 22
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 18 of 21
| Reason for MRI | Count * |
|---|---|
| Seizure(s) | 20 |
| Developmental Delay | 14 |
| Episode of altered mental status | 3 |
| Epilepsy | 2 |
| Estropia | 2 |
| Vomiting | 2 |
| Weakness/Lethargy | 2 |
| Ataxia, exotropia, headaches, macrocephaly, microcephaly, optic nerve hypoplasia, orbital mass, spastic hemiparesis, nystagmus, spastic diplegia, suspected pituitary disorder | 11 (1 for each) |
* some patients with multiple reasons for MRI
| Radiological Findings/Potential Confounders | Count * |
|---|---|
| None/Not Specified | 23 |
| Seizure(s)/Epilepsy | 22 |
| Sinus Inflammation/Infection | 19 |
| Developmental Delay | 14 |
| Premature Birth | 4 |
| Diminutive Pituitary | 2 |
| Eye Disorder | 5 |
| Movement Disorder | 5 |
| Asymmetry of hippocampus, benign ventricular cyst, ear infection, focal cortical displasia, hyperthyroidism, macrocephaly, microcephaly, neonatal infarction, orbital dermoid | 9 (1 for each) |
* some patients with multiple radiological findings/potential confounders
Page 23
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 19 of 21
9.2.2. Reference Standard
Each image was annotated independently by 3 experts. A total of 6 experts in two groups of three were used to establish the reference segmentations of the brain:
• Group 1: 32 cases annotated. Consisted of two U.S-based neuroradiologists and one U.S.-based neuroimaging consultant PhD.
• Group 2: 50 cases annotated. Consisted of three U.S.-based neuroradiologists.
For each brain MRI, the expert used an annotation platform to view the image series and a pre-loaded initialization of 16 subregions of the brain. The expert then reviewed the initial segmentation and edited the segmentations as necessary for accuracy.
The segmentations of the 3 experts where then combined to produce a single segmentation using the STAPLE method. Reference measurements (i.e., volume, surface area, and local gyrification index) were derived from the combined segmentation.
9.3. Results
The average Dice score between the predicted volumes of brain subregions and the reference volumes ranged from 0.92 to 0.99, with an average of 0.95 for all regions. The region with the lowest average Dice score was the left inferior parietal gyrus (0.92 [0.90, 0.94]).
The mean absolute errors for volume, surface area, and gyrification index for each of the specified regions of the brain are reported below.
| Structure/Region | Mean Absolute Volume Error | Mean Absolute Surface Area Error | Mean Absolute Gyrification Index Error |
|---|---|---|---|
| Total Cortex | 2.14% [1.66%, 2.61%] | N/A* | N/A* |
| Left Cortex | 2.41% [1.81%, 3.01%] | ||
| Right Cortex | 1.88% [1.49%, 2.28%] | ||
| Superior Frontal | 0.48% [0.25%, 0.72%] | 0.63% [0.21%, 1.05%] | 0.04% [0.02%, 0.05%] |
| Left | 0.59% [0.31%, 0.87%] | 0.04% [0.02%, 0.05%] | |
| Right | 0.46% [0.17%, 0.76%] | ||
| Middle Frontal | 0.51% [0.29%, 0.72%] | 0.49% [0.08%, 0.91%] | 0.05% [0.03%, 0.06%] |
| Left | 0.45% [0.29%, 0.60%] | 0.33% [0.16%, 0.49%] | 0.04% [0.03%, 0.05%] |
| Right |
Page 24
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 20 of 21
| Structure/Region | Mean Absolute Volume Error | Mean Absolute Surface Area Error | Mean Absolute Gyrification Index Error |
|---|---|---|---|
| Fusiform | 1.44% [0.74%, 2.14%] | 1.40% [0.48%, 2.32%] | 0.07% [0.05%, 0.10%] |
| Left | 1.37% [0.66%, 2.08%] | 1.30% [0.47%, 2.13%] | 0.08% [0.04%, 0.12%] |
| Right | |||
| Inferior Temporal | 1.11% [0.71%, 1.51%] | 1.14% [0.62%, 1.67%] | 0.12% [0.06%, 0.17%] |
| Left | 1.05% [0.59%, 1.52%] | 1.09% [0.56%, 1.61%] | 0.12% [0.06%, 0.17%] |
| Right | |||
| Inferior Parietal | 12.10% [8.44%, 15.77%] | 12.58% [8.72%, 16.43%] | 0.89% [0.56%, 1.22%] |
| Left | 7.88% [5.68%, 10.07%] | 8.42% [5.98%, 10.86%] | 0.49% [0.32%, 0.67%] |
| Right | |||
| Lingual | 4.92% [3.85%, 6.00%] | 5.70% [4.11%, 7.29%] | 0.32% [0.23%, 0.41%] |
| Left | 4.46% [3.59%, 5.33%] | 5.45% [4.09%, 6.80%] | 0.49% [0.35%, 0.63%] |
| Right | |||
| Cuneus | 10.75% [8.50%, 13.00%] | 11.64% [8.75%, 14.54%] | 0.48% [0.32%, 0.65%] |
| Left | 10.18% [7.79%, 12.57%] | 11.28% [8.51%, 14.05%] | 0.50% [0.36%, 0.64%] |
| Right |
* identical surfaces, so the error is zero
The pre-specified acceptance criteria for volume, surface area, and gyrification index errors was below 10%. The total cortex, superior frontal, middle frontal, fusiform, inferior temporal, and lingual regions met the expected performance thresholds.
Two regions exceeded the stated thresholds. For the inferior parietal gyrus (left), the average volume error was 12.10% [8.44%, 15.77%] and the average surface area error was 12.58% [8.72%, 16.43%]. For the cuneus (left & right): the average volume error was 10.75% [8.50%, 13.00%] and 10.18% [7.79%, 12.57%] for the left and right, respectively, and the average surface area error was 11.64% [8.75%, 14.54%] and 11.28% [8.51%, 14.05%] for the left and right, respectively. All regions met the expected performance thresholds for gyrification index error.
10. CONCLUSION
• GyriCalc has the equivalent indications for use and intended use as NeuroQuant.
• Both devices have similar technological characteristics as they are both automatically label, visualize, and quantify segmentable brain structures from a set of MR images.
Page 25
510(k) Summary
(21 CFR 807.92(c))
510(k) Summary Page 21 of 21
• Any differences in technological characteristics between both devices, such as the addition of area measurements and gyrification analysis, do not raise different questions of safety and effectiveness. The GyriCalc subject device has also undergone successful verification and validation testing, which supports the safe and effective performance of the device.
These similarities support the substantial equivalence of GyriCalc to the predicate NeuroQuant device.
§ 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).