cNeuro cMRI is intended for automatic labeling, quantification of segmentable brain structures from a set of MR images. The software is intended to automate the current manual process of identifying, labeling and quantifying the segmentable brain structures identified on MR images.

The intended user profile covers medical professionals who work with medical imaging. The intended operational environment is an office-like environment with a computer.

Device Description

As input, cNeuro cMRI uses T1-weighted (T1) and fluid-attenuated inversion recovery (FLAIR) DICOM MR images from a single time point. The T1 image is mandatory but the FLAIR image is optional. The user selects images through connection with a Picture Archiving and Communication System (PACS) or by selecting DICOM files from a folder. cNeuro cMRI displays the selected images together with information extracted from the DICOM headers.

lmage processing starts with a pre-processing stage with bias-field correction and brain extraction before the actual segmentation and calculation of MRI biomarkers begins. When the processing has completed, the user can review the images with brain segmentations displayed as an overlay. cNeuro cMRI presents computed biomarkers corresponding to volumes of structures and FLAIR white matter hyperintensities. The computed biomarkers are corrected for the subject's head size, gender and age and are compared to corresponding biomarkers from a healthy reference population using a statistical model.

AI/ML Overview

Here's a detailed breakdown of the acceptance criteria and study information for the cNeuro cMRI device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document explicitly states that "A literature review was performed to set relevant acceptance criteria for each type of experiment. All experiments passed the acceptance criteria." While the specific numerical acceptance criteria from the literature review are not detailed in the provided text, the reported device performance for key metrics is given.

Metric	Acceptance Criteria (Not explicitly stated numerically in source, but "passed")	Reported Device Performance
Similarity Index (Dice Index) - Hippocampus	Value from literature review	0.88
Similarity Index (Dice Index) - Thalamus	Value from literature review	0.91
Similarity Index (Dice Index) - Whole Cortex	Value from literature review	0.88
Intraclass Correlation Coefficient (ICC) - Test-Retest Reproducibility (averaged over 133 structures)	Value from literature review	0.96
Correlation Coefficient - FLAIR White Matter Hyperintensities (vs. manually labeled)	Value from literature review	0.97

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

Sample Size for Test Set: 1399 subjects in total.
Data Provenance: The test data included "data from healthy subjects, and patients with neurodegenerative diseases such as Alzheimer's disease, mild cognitive impairment, fronto-temporal lobe degeneration, vascular dementia as well as Multiple Sclerosis patients." The country of origin is not specified, nor is whether the data was retrospective or prospective.

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

The document mentions "manually labeled ground truth data" and "manually labelled data" for white matter hyperintensities. However, it does not specify the number of experts used or their qualifications (e.g., radiologists with X years of experience).

4. Adjudication Method for the Test Set

The document does not specify an adjudication method (e.g., 2+1, 3+1, none) for the test set. It only mentions "manually labeled ground truth data."

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned in the provided text. The study focused on validating the accuracy and reproducibility of the automated system against ground truth, not on human reader performance with or without AI assistance.

6. Standalone Performance Study

Yes, a standalone study was done. The performance metrics reported (Similarity Index, ICC, Correlation Coefficient) directly reflect the algorithm's performance in automatically segmenting and quantifying brain structures in comparison to "manually labeled ground truth data" or test-retest data, without direct human-in-the-loop interaction for the reported metrics. The "QC of segmentation results" and "reviewing biomarkers" in the workflow indicate a human review step, but the reported performance metrics are for the algorithmic output.

7. Type of Ground Truth Used

The ground truth used was expert consensus / manual labeling. Specifically, the document states:

"In the accuracy experiments, cNeuro cMRI fully automated brain segmentation was compared to manually labeled ground truth data."
"and the correlation coefficient between the computed FLAIR white matter hyperintensities and the manually labelled data was 0.97."

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set. The 1399 subjects are mentioned in the context of "experiments," which typically implies testing or validation rather than training.

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

The document does not provide information on how the ground truth for the training set was established.

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, with the letters "FDA" in a blue box, followed by the words "U.S. FOOD & DRUG" in a larger, bold blue font. Below that is the word "ADMINISTRATION" in a smaller, blue font.

January 8, 2018

Combinostics Oy % Lennart Thurfjell CEO Hatanpään valtatie 24 Tampere FI 33100 FINLAND

Re: K171328

Trade/Device Name: cNeuro cMRI Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: II Product Code: LLZ Dated: December 6, 2017 Received: December 8, 2017

Dear Lennart Thurfjell:

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. 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 801); medical device reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820);

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

Page 2 - Lennart Thurfjell

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 http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

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/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). 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 (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Michael D. O'Hara For

Robert Ochs. Ph.D Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

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

DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration

Indications for Use

Form Approved: OMB No. 0910-0120 Expiration Date: January 31, 2017 See PRA Statement below.

510(k) Number (if known)

K171328

Device Name cNeuro cMRI

Indications for Use (Describe)

The intended user profile covers medical professionals who work with medical imaging. The intended operational environment is an office-like environment with a computer.

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."

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

Image /page/3/Picture/1 description: The image shows the word "COMBINOSTICS" in all capital letters. To the left of the word is a symbol that looks like a "C" with a blue square on top and a red square on the bottom. The word is written in a simple, sans-serif font and is black.

Combinostics Oy Hatanpään valtatie 24 33 100 Tampere Finland

Section 5. 510(k) Summary

5.1 Submitter

Name:	Combinostics OY
Address:	Hatanpään valtatie 24, FI 33 100 Tampere,Finland
Contact Person:	Lennart Thurfjell
Telephone number:	+46 730 699057
Fax Number:	N.A.
E-mail:	lennart.thurfjell@combinostics.com
Consultant:	Allison Komiyama, PhD, RAC
Date prepared:	January 2, 2018

5.2 Device

Trade Name:	cNeuro cMRI
Common Name	Medical Image Processing Software
Classification Name	System, Image processing, Radiological
Regulation Number	892.2050
Product Code	LLZ
Classification Panel	Radiology

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

5.3 Predicate Device

Primary predicate device
Device	NeuroQuant
510(k) #	K061855
Manufacturer	CorTechs Labs, Inc. 4690 Executive Drive, Suite
	250 San Diego, CA 92121 USA
Secondary predicate device
Device	icobrain
510(k) #	K161148
Manufacturer	Icometrix, Kolonel Begaultlaan 1b / 12
	3012 Leuven, Belgium

5.4 Device Description

The flowchart below outlines the workflow and main steps in the usage of cNeuro cMRI.

Image /page/4/Figure/6 description: The image shows a flowchart of a process. The process starts with selecting DICOM images, followed by pre-processing. The next step is atlas-based segmentation, then QC of segmentation results. The process ends with reviewing biomarkers and creating a report in PDF format.

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

5.5 Indications for Use

The intended user profile covers medical professionals who work with medical imaging. The intended operational environment is an office-like environment with a computer.

5.6 Comparison and substantial equivalence statement

cNeuro cMRI is substantially equivalent to the NeuroQuant device by Cortechs Labs, cleared in K061855 with regards to processing of T1 images and it is substantially equivalent to the icobrain device by icometrix, cleared in K161148 with regards to processing of FLAIR images. K061855 is the primary predicate and K161148 is the secondary predicate.

	SUBJECT DEVICE	Primary PredicateDevice	Secondary PredicateDevice	Conclusion/Comparison
Device	cNeuro cMRI	NeuroQuant	icobrain	---
510(k) Number	K171328	K061855	K161148
Manufacturer	Combinostics OY	CorTechs Labs, Inc	icometrix	---
DeviceClassificationName	Picture archiving andcommunication system	Picture archiving andcommunication system	Picture archiving andcommunication system	Identical
Deployment	Cloud based	Cloud based or installed	Cloud based	cNeuro cMRI and icobrain areidentical. NeuroQuant isavailable either cloud basedor installed.

A comparison of the subject device and predicate devices (K061855 and K161148) is provided below.

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

	SUBJECT DEVICE	Primary PredicateDevice	Secondary PredicateDevice	Conclusion/Comparison
Device	cNeuro cMRI	NeuroQuant	icobrain	--
510(k) Number	K171328	K061855	K161148	--
Manufacturer	Combinostics OY	CorTechs Labs, Inc	icometrix	--
Indications forUse	cNeuro cMRI isintended for automaticlabeling, quantificationand visualization ofsegmentable brainstructures from a set ofMR images. Thesoftware is intended toautomate the currentmanual process ofidentifying, labeling andquantifyingsegmentable brainstructures identified onMR images.The users are trainedhealthcareprofessionals who workwith medical imaging.The product is used inan office-likeenvironment.	NeuroQuantTM isintended for automaticlabeling, visualization andvolumetric quantificationof segmentable brainstructures from a set ofMR images. This softwareis intended to automatethe current manualprocess of identifying,labeling and quantifyingthe volume ofsegmentable brainstructures identified onMR images.	icobrain is intended forautomatic labeling,visualization and volumetricquantification of segmentablebrain structures from a set ofMR images. This software isintended to automate thecurrent manual process ofidentifying, labeling andquantifying the volume ofsegmentable brain structuresidentified on MR images.icobrain consists of twodistinct image processingpipelines: icobrain cross andicobrain long. icobrain crossis intended to providevolumes from imagesacquired at a single timepointicobrain long is intended toprovide changes in volumesbetween two images thatwere acquired on the samescanner, with the same imageacquisition protocol and withsame contrast at two differenttimepoints The results oficobrain cross cannot becompared with the results oficobrain long.	Functionally identical.cNeuro cMRI lists"quantification" whileNeuroQuant lists "volumetricquantification". Since cNeurocMRI makes a volumetricquantification, theseexpressions can be consideredidentical.Furthermore, icobrain has theadded description of twodistinct processing pipelines:icobrain cross and icobrainlong. Results of icobrain crosscannot be compared with theresults of icobrain long.cNeuro cMRI and NeuroQuantprovides only one processingpipeline.Finally, cNeuro cMRI listsintended users and intendeduse environment whereasNeuroQuant and icobraindoes not.

Subject device and predicate devices are software for automatically identifying and quantifying volumes of brain structures, labeling and visualization. Both subject and predicate devices take 3D MR images of the brain as input and generate an electronic report with similar quantitative information. The output values are for all devices compared to a normative data based on MRI data from healthy control subjects.

Subject device and the primary predicate device segments cortical structures from MRI T1 images based on a similar principle, where the quantification relies on pre-processing with skull stripping (brain extraction) followed by multi-atlas segmentation. The main difference is that different atlases are used. The subject device uses atlases with 133 brain structures, while the primary predicate uses atlases with 34 brain structures. Similarly, the subject device and the secondary predicate device segments white matter hyperintensities from FLAIR MR images based on a similar principle. Furthermore, for volumes derived from T1 images, the subject device and the predicate devices provide statistical comparison of normalized values with a normative dataset from a healthy reference population. In addition, subject device compares normalized volumes of FLAR white matter hyperintensities to a normative dataset from a reference population. The secondary predicate device does not provide such a comparison.

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

The primary predicate device uses an index computed based on the image volumes from normal atlas space as a quality control measure. The subject device does not employ such an index, but provides functionality where the user interactively can review the quality of the segmentations by checking color coded overlays on the original MR slices.

Subject device provides a gray matter concentration map, i.e., an overlay on MR T1 images highlighting regions where the local gray matter concentration of the patient is smaller than the gray matter concentration in the reference population normalized for age, sex and head size. This overlay, which can be toggled on and off, provides a means for the user to locate regions that are atypical compared to the reference population. The predicate devices do not provide such a gray matter concentration map. Subject device's gray matter concentration map provides a visual complement to the quantitative volume measurements and it does not affect safety and effectiveness of the device.

5.7 Performance testing

Support for the substantial equivalence of cNeuro cMRI to the predicate devices was provided as a result of risk management and testing. The design verification activities consist of code review and static code analysis, unit tests, integration tests, system tests (including safety related tests from risk analysis) and regression testing after modifications

To demonstrate the performance of cNeuro cMRI, the computed volumes of brains structures were validated for accuracy and reproducibility. Test data included data from healthy subjects, and patients with neurodegenerative diseases such as Alzheimer's disease, mild cognitive impairment, fronto-temporal lobe degeneration, vascular dementia as well as Multiple Sclerosis patients. In the accuracy experiments, cNeuro cMRI fully automated brain segmentation was compared to manually labeled ground truth data. In the reproducibility experiments, the volumes were compared using test-retest data. The experiments included data from 1399 subjects in total.

A literature review was performed to set relevant acceptance criteria for each type of experiment. All experiments passed the acceptance criteria. Averaged over all experiments, the similarity index (or Dice index) were 0.88 for the hippocampus, 0.91 for the thalamus and 0.88 for the whole cortex. Furthermore, intraclass correlation coefficient for the test-retest reproducibility measurements averaged over all 133 structures was 0.96 and the correlation coefficient between the computed FLAIR white matter hyperintensities and the manually labelled data was 0.97.

The verification and performance testing demonstrate that cNeuro cMRI is safe and effective to use.

5.8 Conclusion

Combinostics OY believes that cNeuro cMRI has the identical indication for use and that there are no new types of questions regarding safety and effectiveness for cNeuro cMRI as compared to the cleared predicate devices. Combinostics OY has conducted the risk analysis and performed the necessary verification and validation activities to demonstrate that the design outputs meet the design inputs and the applicable process standards. Combinostics OY has concluded that the performance data for the cNeuro cMRI shows that it is substantially equivalent to the primary predicate device, NeuroQuant (K061855), for processing of MRI T1 images and to the secondary predicate device, icobrain (K161148), for processing of MRI FLAIR images.

{8}------------------------------------------------

This document is reviewed and approved by Lennart Thurfjell, CEO of Combinostics.

Image /page/8/Picture/2 description: The image shows a DocuSign signature block. The block includes the phrase "DocuSigned by" followed by a signature. The signer's name is Lennart Thurfjell, and the signing reason is "I approve this document." The signing time is 2018-01-02 at 21:10 CET, and the document ID is D90D9E2D88AF4E038888D92E1C8BDDFA.

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).