QP-Brain® is a medical imaging processing application intended for automatic labeling and volumetric quantification of segmentable brain structures and white matter hyperintensities (WMH) from a set of adults and adolescents 18 and older MR images. Volumetric measurements may be compared to reference percentile data. The application with proper training, as a support tool in assessment of structural MRIs. Patient management decisions should not be results of the device.

Device Description

QP-Brain® is a medical image processing and analyzing software intended for image processing to analyze brain MR imaging studies. These brain MR images, when interpreted by clinicians with proper training, may yield clinically useful information.

QP-Brain® is an automated MR imaging post-processing medical device software that uses 3D T1-weighted (T1w) Gradient Echo structural MRI scans to provide a quantitative imaging analysis and automatic segmentation of brain regions. If T2 FLAIR images are uploaded. QP-Brain® uses this sequence to automatically identify white matter hyperintensities using Artificial Intelligence.

Once the T1 MR or T2 FLAIR has been uploaded, QP-Brain® will check the available sequences for compatibility before automatically launching the analysis.

The output of the medical device consists of specific volumes with seqmentation overlay as well as different reports with quantitative information. The outputs can be returned to and displayed on third-party DICOM workstations and Picture Archive and Communication Systems (PACS).

In case age and gender information is available on the study DICOM tags for brain structure analysis module, all quantified volumes are framed in a normative database to be compared with cognitively normal adults of the same age and gender.

QP-Brain® also allows for longitudinal information reporting if a patient has acquired more than one MRI over time.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for QP-Brain®:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" as a set of predefined thresholds. Instead, it presents performance metrics for the device compared to a reference standard (manual expert segmentation). The implicit acceptance criteria appear to be the achievement of high correlation and low error rates, demonstrating that QP-Brain® functions as intended and is comparable to manual segmentation.

Metric / Region	Reported Device Performance (Mean (95% CI or Range))	Implicit Acceptance Threshold (Inferred)
Brain Volumetry (T1 MRI)
GM DICE Score	0.983 (0.981 – 0.986)	High Dice Score (e.g., > 0.95 or similar to expert inter-rater variability)
GM Relative Volume Difference	2.846 (2.523 – 3.008)	Low Relative Volume Difference (e.g., < 5% or similar to expert variability)
WM DICE Score	0.990 (0.988 – 0.992)	High Dice Score
WM Relative Volume Difference	1.643 (0.923 – 1.684)	Low Relative Volume Difference
CSF DICE Score	0.955 (0.944 – 0.965)	High Dice Score
CSF Relative Volume Difference	7.495 (3.950 – 7.718)	Low Relative Volume Difference (potentially higher for CSF due to variability)
ICV DICE Score	0.994 (0.994 – 0.995)	Very High Dice Score
ICV Relative Volume Difference	0.496 (0.298 – 0.694)	Very Low Relative Volume Difference
White Matter Hyperintensities (T2 FLAIR)
Low WMH DICE Score	0.506 (0.406 – 0.450)	Moderate to high Dice Score (given inherent difficulty in segmenting small WMH)
Medium WMH DICE Score	0.636 (0.622 – 0.699)	Moderate to high Dice Score
High WMH DICE Score	0.774 (0.748 – 0.790)	High Dice Score
Very High WMH DICE Score	0.885 (0.806 – 0.923)	Very High Dice Score
Low WMH Absolute Volume Error	0.675 mL (0.455 – 0.682)	Low Absolute Volume Error
Medium WMH Absolute Volume Error	2.544 mL (2.084 – 3.704)	Low Absolute Volume Error
High WMH Absolute Volume Error	3.097 mL (2.871 – 4.763)	Low Absolute Volume Error
Very High WMH Absolute Volume Error	7.833 mL (5.668 – 15.831)	Low Absolute Volume Error
WMH F1 Score (Medium)	0.701 (0.666 - 0.739)	High F1 Score
WMH Pearson's Correlation Coefficient	0.88	High positive correlation (e.g., > 0.8)

Note: The acceptance thresholds above are inferred based on the context of demonstrating substantial equivalence and acceptable clinical utility. The document itself does not explicitly list these as "acceptance criteria" with specific numerical cutoffs that were pre-defined.

2. Sample Size for Test Set and Data Provenance

Sample Size for Test Set: Not explicitly stated in the provided text. The tables present summarized metrics (e.g., mean DICE scores, mean errors, and confidence intervals), but the number of images or patients in the test set is not provided.
Data Provenance: Not specified. The document does not mention the country of origin of the data or whether it was retrospective or prospective.

3. Number of Experts and Qualifications for Ground Truth

Number of Experts: Not explicitly stated. The document mentions "manual expert segmentation" as the reference standard but does not specify the number of experts involved.
Qualifications of Experts: Not specified. The document refers to them as "expert" but does not detail their specific qualifications (e.g., years of experience, board certifications).

4. Adjudication Method for the Test Set

Adjudication Method: Not explicitly stated. The document refers to "manual expert segmentation" as the reference standard, which implies that expert opinion was used, but the method for resolving any potential disagreements among multiple experts (e.g., 2+1, 3+1, or simple consensus) is not mentioned. If only one expert performed the segmentation, then no adjudication would be needed.

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

Was an MRMC study done? No. The performance data presented compares the device's output to "manual expert segmentation" as a reference standard, not to human readers' performance with or without AI assistance. Therefore, it is a standalone performance study against a reference standard, not an MRMC comparative effectiveness study.
Effect size of human readers improvement: Not applicable, as no MRMC study was performed.

6. Standalone (Algorithm Only) Performance

Was a standalone performance study done? Yes. The "Performance Data" section describes how "QP-Brain® outputs were compared to manual expert segmentation (reference standard)." This directly assesses the algorithm's performance without human intervention after the algorithm has generated its output.

7. Type of Ground Truth Used

Type of Ground Truth: Expert consensus (or expert segmentation). The document states, "For the performance evaluation, QP-Brain® outputs were compared to manual expert segmentation (reference standard)."

8. Sample Size for the Training Set

Sample Size for Training Set: Not specified. The document only discusses the validation phase and its performance results. Information regarding the training set's size is not provided.

9. How Ground Truth for the Training Set was Established

How Ground Truth for Training Set was Established: Not specified. While it's implied that "manual expert segmentation" would likely also be used for establishing ground truth in the training data, the document does not explicitly state this or provide details on the process for the training set.

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 & 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.

December 13, 2023

Quibim S.L. % John J. Smith, M.D., J.D. Partner Hogan Lovells US LLP 555 13th St. NW Washington, DC 20005

Re: K232231

Trade/Device Name: QP-Brain® Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QIH, LLZ Dated: November 15, 2023 Received: November 15, 2023

Dear John Smith:

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.

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

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30. Design controls; 21 CFR 820.90. Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting 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-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 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.

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-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

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

For comprehensive regulatory information about mediation-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,

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 Ouality Center for Devices and Radiological Health

Enclosure

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

510(k) Number (if known) K232231

Device Name

QP-Brain®

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)

区 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 Druq Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.qov

"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.

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

510(k) SUMMARY Quibim's QP-Brain®

Submitter Quibim S.L. Avenida Aragon 30, 13th floor, Office I-J, 46021 Valencia (Spain)

Phone:

. +34 961 243 255
Contact Person:
Ángel Alberich Bayarri, CEO and Founder of Quibim (angel@quibim.com) ●
Josep Hortigüela Zamora, VP of Quality Assurance and Regulatory Affairs . (josephortiguela@quibim.com)

Date Prepared: November 15, 2023

Name of Device: QP-Brain®

Common or Usual Name: Medical image management and processing system Classification Name: 892.2050 Medical image management and processing system Requlatory Class: Class II Product Code: QIH, LLZ

Predicate Device

. Manufacturer's name: CorTechs Labs, Inc. 4690 Executive Drive, Suite 250, San Diego, CA 92121
Device's trade name: NeuroQuant
. 510(k) number: K170981
Product code: LLZ

Reference Devices

Reference Device #1:

Manufacturer's name: Quantib B.V. Westblaak 106, 3012 KM Rotterdam (Netherlands).
Device's trade name: Quantib™ Brain 1.3 ●
510(k) number: K173939
Product code: LLZ .

Reference Device #2:

Manufacturer's name: Qynapse. PariSanté Campus, 2-10 rue d'Oradour-sur-Glane, . 75015 Paris, France
. Device's trade name: Qyscore Software
510(k) number: K192531
Product code: LLZ

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

Device Description

Once the T1 MR or T2 FLAIR has been uploaded, QP-Brain® will check the available sequences for compatibility before automatically launching the analysis.

QP-Brain® also allows for longitudinal information reporting if a patient has acquired more than one MRI over time.

Intended Use / Indications for Use

QP-Brain® is a medical imaging processing application intended for automatic labeling and volumetric quantification of segmentable brain structures and white matter hyperintensities (WMH) from a set of adults and adolescents 18 and older MR images. Volumetric measurements may be compared to reference percentile data. The application is used by clinicians with proper training, as a support tool in assessment of structural MRIs. Patient management decisions should not be based solely on the results of the device.

Comparison to predicate device

The QP-Brain® and predicate devices differs on the following elements:

. QP-Brain® and the predicate device NeuroQuant® have very similar indications statements. Both are intended for a medical image processing application intended for automatic labeling and volumetric quantification of segmentable brain structures and white matter hyperintensities (WMH) from a set of MR images. NeuroQuant® uses the word "lesions" meaning White Matter Hyperintensities points to hyperintense area, which is within QP-Brain® scope. This wording difference does not alter the intended use effect of QP-Brain® as a support tool to clinicians in assessment of structural MRIs.

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

QP-Brain® has the same intended use environment and intended user, and the intended patient population (adult patients and adolescent patients aged 18 through 21) is covered by the intended patient population of the predicate device (pediatric and adult patients).

Summary of Technological Characteristics

At a high level, the subject and predicate devices are based on the following same technological elements:

Both devices are compatible with DICOM standard. .
. Both devices have the same input to run the analysis module: 3D T1 MRI scans (for brain structures) and T2 FLAIR M (for White Matter Hyperintensities) acquired with specified protocols.
· Both devices have the same automated internal pipeline to perform the analysis.
· Both devices have the same clinical outputs.

The following technological differences exist between the subject and predicate devices:

The difference in processing architecture (since they are not exactly the ● same algorithm), could affect its safety or effectiveness, but does not raise any different questions of safety or effectiveness, because a set of verification and validation tests (performance testing) demonstrate the safety and effectiveness of QP-Brain®.
A table comparing the key features of the subject and predicate devices is provided below:

Feature	Proposed device:QP-Brain® (K232231)	Predicate device:NeuroQuant® (K170981)
REGULATORY DATA
Class	II	II
Regulation name	Picture Archiving andCommunication System	Medical Image managementand processing system
Regulation number	21 CFR 892.2050	21 CFR 892.2050
Classification Panel	Radiology	Radiology
Product Code	QIH, LLZ	LLZ
Manufacturer:	Quibim S.L.	CorTechs Labs, Inc.
INTENDED USE
Medical device description	QP-Brain® is a medicalimaging processingapplication intended forautomatic labeling andvolumetric quantification of	NeuroQuant® is intendedfor automatic labeling,visualization and volumetricquantification ofsegmentable brain
Feature	Proposed device:QP-Brain® (K232231)	Predicate device:NeuroQuant® (K170981)
	segmentable brainstructures and white matterhyperintensities (WMH) froma set of adults andadolescents 18 and olderMR images.	structures and lesions froma set of MR images.It is intended to automatethe manual process ofidentifying, labeling andquantifying the volume ofsegmentable brainstructures identified on MRimages.
Medical device intendeduse environment	Software as a MedicalDevice, DICOM compatibleand operate on off-the-selfhardware (multiple vendors).	Software as a MedicalDevice, DICOM compatibleand operate on off-the-selfhardware (multiple vendors).
Medical device intendeduser	The application should beused by clinicians withproper training, as a supporttool in assessment ofstructural MRIs.Patient managementdecisions should not bebased solely on the resultsof the device.	NeuroQuant® is used bymedical professionals, suchas radiologists, neurologistsand neuroradiologists, aswell as by clinicalresearchers, as a supporttool in assessment ofstructural MRIs.
Medical device intendedpatient population	Adult patients andadolescent patients aged 18through 21 with brain MRIstudy. Available up to 94years.	Adult and pediatric patientswith brain MRI study.Available for ages 3 to 100years.
Clinical output	Provides volumetricmeasurements of brainstructures.- Includes segmentedcolor overlays andmorphometricreports.- Automaticallycompares results toreference percentiledata and to priorscans whenavailable.Supports DICOM format asoutput of results that can bedisplayed on DICOMworkstations and PictureArchive andCommunications Systems.	Provides volumetricmeasurements of brainstructures.- Includes segmentedcolor overlays andmorphometricreports.- Automaticallycompares results toreference percentiledata and to priorscans whenavailable.Supports DICOM format asoutput of results that can bedisplayed on DICOMworkstations and PictureArchive andCommunications Systems.
Data source	MRI scanner: 3D T1 MRIscans (for brain structures)	MRI scanner: 3D T1 MRIscans (for brain volumetry)
Feature	Proposed device:QP-Brain® (K232231)	Predicate device:NeuroQuant® (K170981)
	and T2 FLAIR MR (for WhiteMatter Hyperintensities)acquired with specifiedprotocols.QP-Brain® supports DICOM format as input.	and T2 FLAIR MR (for WhiteMatter Hyperintensities)acquired with specifiedprotocols.NeuroQuant® supports DICOM format as input.
Processing architecture	Automated internal pipelinethat performs:- artifact correction- segmentation- atlas-basedparcellation- WMH quantification- volume calculation- report generation	Automated internal pipelinethat performs:- artifact correction- segmentation- atlas-basedparcellation- lesion quantification- volume calculation- report generation
Safety	Automated quality controlfunction: scan protocolverification.Results must be reviewedby a clinician with propertraining.	Automated quality controlfunctions:- Tissue contrastcheck.- Scan protocolverification.- Atlas alignmentcheck.Results must be reviewedby a trained physician

Table 1: Comparison of key features of QP-Brain® (Quibim) and the predicate device NeuroQuant® (CorTechs Labs, Inc.)

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

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

Performance Data

QP-Brain® software was developed according to FDA recognized consensus standards for software development. Software verification and validation was performed following V&V plans and protocols verifying that product specifications were met.

For the performance evaluation, QP-Brain® outputs were compared to manual expert segmentation (reference standard) for Gray Matter (GM), White Matter (WM), Cerebrospinal fluid (CSF) and White Matter Hyperintensities (WMH).

For brain regions segmented from 3D T1 MRI scans, the results between manual segmentation and QP-Brain® segmentation are summarized below:

Region	DICE Score	Relative Volume Difference
GM	0.983 (0.981 – 0.986)	2.846 (2.523 – 3.008)
WM	0.990 (0.988 – 0.992)	1.643 (0.923 – 1.684)
CSF	0.955 (0.944 – 0.965)	7.495 (3.950 – 7.718)
ICV	0.994 (0.994 – 0.995)	0.496 (0.298 – 0.694)

Table 2: Summary of the performance testing for QP-Brain® Brain volumetry analysis module.

{9}------------------------------------------------

For White Matter Hyperintensities segmented from T2 FLAIR, the results between manual segmentation and QP-Brain® segmentation are summarized below:

Table 3: Summary of the performance testing for QP-Brain® Brain WMH analysis module.

Size	DICE Score	Absolute volume error	F1 score
Low WMH	0.506	0.675 mL
Medium WMH	0.636	2.544 mL
High WMH	0.774	3.097 mL	0.692
Very High WMH	0.885	7.833 mL

Wilcoxon signed-rank test is used to establish uncertainty intervals. The results are summarized below:

Table 4: Summary of the performance testing for QP-Brain® Brain WMH analysis module (confidence intervals).

Size	DICE Score	Absolute volume error	F1 score
Low WMH	0.406(0.360 - 0.450)	0.455 mL(0.317 - 0.682)
Medium WMH	0.622(0.559 - 0.699)	2.084 mL(1.190 - 3.704)	0.701
High WMH	0.748(0.707 – 0.790)	2.871 mL(1.311 - 4.763)	(0.666 - 0.739)
Very High WMH	0.806(0.677 - 0.923)	5.668 mL(2.853 - 15.831)

The Pearson's correlation coefficient result for the WMH count is 0.88.

The test results demonstrate that QP-Brain® functioned as intended, is acceptable for clinical use, and is as safe and effective as its predicate device, without introducing new questions of safety and efficacy.

Conclusions

The QP-Brain® is as safe and effective as the NeuroQuant®. The QP-Brain® has the same intended uses and similar indications, technological characteristics, and principles of operation as its predicate device. The minor differences in indications do not alter the intended diagnostic use of the device and do not affect its safety and effectiveness when used as labeled. In addition, the minor technological differences between the QP-Brain® and its predicate devices raise no new issues of safety or effectiveness. Performance data demonstrate that the QP-Brain® is as safe and effective as the NeuroQuant®. Thus, the QP-Brain® is substantially equivalent.

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).