The TeraRecon Neuro Algorithm is an algorithm for use by trained professionals, including but not limited to physicians, surgeons and medical clinicians.

The TeraRecon Neuro Algorithm is a standalone image processing software device that can be deployed as a Microsoft Windows executable on off-the-shelf hardware or as a containerized application (e.g., a Docker container) that runs on off-the-shelf hardware or on a cloud platform. Data and images are acquired via DICOM compliant imaging devices. DICOM results may be exported, combined with, or utilized by other DICOM-compliant systems and results.

The TeraRecon Neuro Algorithm provides analysis capabilities for functional, dynamic, and derived imaging datasets acquired with CT or MRI. It can be used for the analysis of dynamic brain perfusion image data, showing properties of changes in contrast over time. This functionality includes calculation of parameters related to brain tissue perfusion, vascular assessment, tissue blood volume, and other parametric maps with or without the ventricles included in the calculation. The algorithm also include volume reformat in various orientation, rotational MIP 3D batch while removing the skull. This "tumble view" allows qualitative review of vascular structure in direct correlation to the perfusion maps for comprehensive review.

The results of the TeraRecon Neuro Algorithm can be delivered to the end-user through image viewers such as TeraRecon's Aquarius Intuition system, TeraRecon's Eureka AI Results Explorer, TeraRecon's Eureka Clinical AI Platform, or other image viewing systems like PACS that can support DICOM results generated by the TeraRecon Neuro Algorithm.

The TeraRecon Neuro Algorithm results are designed for use by trained healthcare professionals and are intended to assist the physician in diagnosis, who is responsible for making all final patient management decisions.

Device Description

The TeraRecon Neuro algorithm version 2.0.0 is a modification of the predicate device Neuro.AI Algorithm (K200750), which was a modification of the predicate device, Intuition-TDA, TVA, Parametric Mapping (which was cleared under K131447). The predicate device Intuition -TDA, TVA, Parametric Mapping is an optional module/workflow for the Intuition system (K121916). The TeraRecon Neuro algorithm is an image processing software device that can be deployed as a Microsoft Windows executable on off-the-shelf hardware or as a containerized application (e.g., Docker container) that runs on off-the-shelf hardware or on a cloud platform. The device has limited network connectivity or external medical support.

TeraRecon Neuro allows motion correction and processes, calculates and outputs brain perfusion analysis results for functional, dynamic, and derived imaging datasets acquired with CT or MRI. TeraRecon Neuro results are used for the analysis of dynamic brain perfusion image data, showing properties of changes in contrast over time. This functionality includes calculation of parameters related to brain tissue perfusion, vascular assessment and tissue blood volume.

Outputs include parametric map of measurements including time to peak (TTP), take off time (TOT), recirculation time (RT), mean transit time (MTT), blood volume (BV/CBV), blood flow (BF/CBF), time to maximum (Tmax) and penumbra/umbra maps that are derived from combinations of measurement parameters, such as mismatch maps and hypoperfusion maps with volumes and ratios, as well as 2D and 3D visualization of brain tissues and brain blood vessels (Note: Tmax, mismatch and hypoperfusion maps are only available for images of CT modality).

When TeraRecon Neuro results are used in external viewer devices such as TeraRecon's Intuition or Eureka medical devices, all the standard features offered by Intuition or Eureka are employed such as image manipulation tools like drawing the region of interest, manual or automatic segmentation of structures, tools that support creation of a report, transmitting and storing this report in digital form, and tracking historical information about the studies analyzed by the software.

The TeraRecon Neuro algorithm outputs can be used by physicians to aid in the diagnosis and for clinical decision support including treatment planning and post treatment evaluation. The software is not intended to replace the skill and judgment of a qualified medical practitioner and should only be used by individuals that have been trained in the software's function, capabilities and limitations. The device is intended to provide supporting analytical tools to a physician, to speed decision-making and to improve communication, but the physician's judgment is paramount, and it is normal practice for physicians to validate theories and treatment decisions multiple ways before proceeding with a risky course of patient management.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

Acceptance Criteria	Reported Device Performance
Software Acceptance Criteria	All pre-defined acceptance criteria for the Neuro.AI Algorithm were met, and all software test cases passed during software development and testing in accordance with IEC 62304:2006/AI:2015.
Qualitative Clinical User Evaluation	The generated maps of TeraRecon Neuro were confirmed through qualitative assessment to be at least 85% substantially equivalent or better than the predicate and reference devices.
Quantitative Tmax Measurement Accuracy	Subject device limit of agreement for both absolute error and absolute percent error (of Tmax measurements compared to ground truth, defined as the average Tmax of two reference devices) was less than or equal to the limit of agreement of each predicate device compared to the ground truth.
Safety and Effectiveness	The TeraRecon Neuro device meets its qualified requirements, performs as intended, and is as safe and effective as the predicate device. No new or different questions of safety or efficacy have been raised. All risks were analyzed, and there are no new risks or modified risks that could result in significant harm which are not effectively mitigated in the predicate device. The device is determined to be Substantially Equivalent to the predicate device in terms of safety, efficacy, and performance.

Study Details

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

The document does not explicitly state the numerical sample size for the test set used in the qualitative clinical user evaluation or the quantitative Tmax measurement accuracy study. It refers to "comparison maps generated by the subject device, the predicate device and two additional reference devices." Without specific numbers, it's impossible to determine the precise size of the test set cases.

Regarding data provenance, the document does not provide details on the country of origin or whether the data was retrospective or prospective.

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

Number of Experts: One expert was used.
Qualifications: Dr. Robert Falk, MD. No additional details about his specific experience or sub-specialty (e.g., radiologist with X years of experience) are provided in the text.

4. Adjudication Method for the Test Set

The adjudication method used for the clinical user evaluation was not explicitly specified as 2+1, 3+1, or any other formal method. The study involved a single evaluator (Dr. Robert Falk, MD) who was "asked to confirm through qualitative assessment." This suggests a single-expert review, rather than a multi-expert adjudication process.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of Improvement with AI vs. Without AI Assistance

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described. The evaluation involved a single expert providing a qualitative assessment. The study was focused on demonstrating substantial equivalence to predicate and reference devices, not on measuring the improvement of human readers with AI assistance. Therefore, there is no reported effect size of how much human readers improve with AI vs. without AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, a standalone performance evaluation was conducted for the quantitative Tmax measurement. The acceptance criteria for Tmax accuracy were based on comparing the subject device's measurements directly against the ground truth (average of reference devices) in ROIs, without explicit human intervention in the measurement process for the test cases. While the "ground truth" itself is derived from other devices (which are used by humans), the comparison of the algorithm's output to this ground truth represents a standalone assessment of the algorithm's quantitative accuracy.

7. The Type of Ground Truth Used

Qualitative Clinical User Evaluation: The ground truth for this evaluation appears to be the performance of the predicate and reference devices, as the subject device's maps were compared to these for substantial equivalence. It's a comparative assessment rather than an absolute ground truth (e.g., pathology).
Quantitative Tmax Measurement Accuracy: The ground truth for Tmax measurements was defined as the average Tmax measurement of the two reference devices (GE Medical Systems FastStroke CT Perfusion 4D (K193289) and ISchemaView RAPID (K182130)) for a given ROI.

8. The Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set for the TeraRecon Neuro algorithm.

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

The document does not provide any information on how the ground truth for the training set was established. Training set details are not discussed.

Summary

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

Image /page/0/Picture/0 description: The image contains 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.

TeraRecon, Inc Michael Sosebee Official Correspondent 4309 Emperor Blvd. Durham, North Carolina 27703

August 12, 2022

Re: K220349

Trade/Device Name: TeraRecon Neuro Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: LLZ Dated: June 28, 2022 Received: June 29, 2022

Dear Michael Sosebee:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for

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

devices or postmarketing safety reporting (21 CFR 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 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Jessica Lamb, Ph.D.

Assistant Director Imaging Software Team DHT 8B: Division of Radiological Imaging Devices and Electronic Products OHT 8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known) K220349

Device Name TeraRecon Neuro

Indications for Use (Describe)

The TeraRecon Neuro Algorithm is an algorithm for use by trained professionals, including but not limited to physicians, surgeons and medical clinicians.

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}------------------------------------------------

K220349

510(k) Summary 1

TeraRecon Neuro version 2.0.0

[in accordance with 21CFR 807.92]

Submitter 1.1

510(k) Sponsor:	TereRecon, Inc.
Address:	4309 Emperor Blvd.,Durham, NC 27703, USA
Contact Person:	Michael SosebeeSenior Manager RAQA
Contact Information:	Email: msosebee@terarecon.comPhone: 704-651-6828
Date Summary Prepared:	10Feb2022

1.2 Subject Device

Proprietary (Trade) Name of Subject Device	TeraRecon Neuro
Model Number	2.0.0
Device Class	2
Common / Classification Name	System, Image Processing, Radiological
Product Code	LLZ
Regulation Number	892.2050
510(k) Number	K220349

1.3 Predicate Device

1.3 Predicate Device
Proprietary (Trade) Name of Predicate Device	Neuro.AI Algorithm
Model Number	1.0.0
Device Class	2
Common / Classification Name	System, Image Processing, Radiological
Product Code	LLZ
Regulation Number	892.2050
510(k) Number	K200750

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

1.4 Device Description

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

1.5 Indications for Use

The TeraRecon Neuro algorithm is an algorithm for use by trained professionals, including but not limited to physicians, surgeons and medical clinicians.

The TeraRecon Neuro algorithm is a standalone image processing software device that can be deployed as a Microsoft Windows executable on off-the-shelf hardware or as a containerized application (e.g., a Docker container) that runs on off-the-shelf hardware or on a cloud platform. Data and images are acquired via DICOM compliant imaging devices. DICOM results may be exported, combined with, or utilized by other DICOM-compliant systems and results.

The TeraRecon Neuro algorithm provides analysis capabilities for functional, dynamic, and derived imaging datasets acquired with CT or MRI. It can be used for the analysis of dynamic brain perfusion image data, showing properties of changes in contrast over time. This functionality includes calculation of parameters related to brain tissue perfusion, vascular assessment, tissue blood volume, and other parametric maps with or without the ventricles included in the calculation. The algorithm also include volume reformat in various orientation, rotational MIP 3D batch while removing the skull. This "tumble view" allows qualitative review of vascular structure in direct correlation to the perfusion maps for comprehensive review.

The results of the TeraRecon Neuro algorithm can be delivered to the end-user through image viewers such as TeraRecon's Aquarius Intuition system, TeraRecon's Eureka AI Results Explorer, TeraRecon's Eureka Clinical AI Platform, or other image viewing systems like PACS that can support DICOM results generated by the TeraRecon Neuro Algorithm.

The TeraRecon Neuro algorithm results are designed for use by trained healthcare professionals and are intended to assist the physician in diagnosis, who is responsible for making all final patient management decisions.

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

1.6 Summary of Technological Characteristics

The TeraRecon Neuro algorithm version 2.0.0 (K220349) is substantially equivalent to the predicate device, Neuro.AI Algorithm (K200750). It has the same basic technological characteristics as the predicate device. The main difference between the subject device and the predicate device is the addition of three perfusions maps Tmax, Hypoperfusion and Mismatch along with improvements made to the quality of existing perfusions maps in version 1.0.0 BV, BF, MTT, TOT, TTP and RT. The subject and predicate devices both allow motion correction and process, calculate and output brain perfusion analysis results for functional, dynamic and derived imaging datasets acquired with CT or MRI. The subject and predicate device results are used for visualization and analysis of dynamic brain perfusion image data, showing properties of changes in contrast over time. This functionality includes calculation of parameters related to brain tissue perfusion, vascular assessment and tissue blood volume.

TeraRecon Neuro can be used by physicians to aid in the diagnosis and for clinical decision support including treatment planning and post treatment evaluation.

Both the subject and predicate devices are interoperable or compatible with CT and MR scanners, 3rd party hospital systems such as PACS, and the TeraRecon Intuition platform. Both devices are standalone software packages, the results of which can be consumed by and viewed by TeraRecon's Eureka AI Results Explorer or by other image viewing systems that can support the results generated by the TeraRecon Neuro algorithm.

The differences in technological characteristics do not raise any new or different questions of safety of effectiveness. Software verification and validation testing validates that the TeraRecon Neuro algorithm is as safe and effective as the predicate device in order to support a determination of substantial equivalence.

See the table below for a description of the technological similarities and differences among the subject and predicate device.

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

Table 1: Technological Characteristics Comparison

	Subject Device	Predicate Device	Reference Device(Used in QualitativeAssessment)	Reference Device(Used in QualitativeAssessment)
Functionality	TeraRecon Neuro version 2.0.0(TBD)	Neuro.AI Algorithm version1.0.0(K200750)	FastStroke, CT Perfusion 4D(K193289)	iSchemaView RAPID(K182130)
Areas of Use	Same as predicate device	Radiology and could also includeother clinical specialty areassuch as emergency, neurology,surgery and more	Not specified in K193289's510(k) summary.	Hospital LAN, inside theHospital FirewallTo be used by trainedprofessionals.Radiological data network.
ModalitySupport	Same as predicate device	Vendor-neutral - CT, MR andother volumetric imagingmodalities.	CT	CT and MRI
Body Part	Same as predicate device	Head - entire brain or fromlower edge of the base of nucleusto upper edge of the ventricles.	Head and Body	Not specified in K182130's510(k) summary
DICOM®formats	Same as predicate device	NEMA PS 3.1 - 3.20 (2016)	DICOM 3.0 image compatibility	NEMA PS 3.1 - 3.20 (2016)

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

Functionality	Subject Device	Predicate Device	Reference Device(Used in Qualitative Assessment)	Reference Device(Used in Qualitative Assessment)
	TeraRecon Neuro version 2.0.0(TBD)	Neuro.AI Algorithm version1.0.0(K200750)	FastStroke, CT Perfusion 4D(K193289)	iSchemaView RAPID(K182130)
OperatingSystem	Same as predicate device	Microsoft Windows® executableon off the shelf hardware andCentOS (Interoperability)	Not specified in K193289's510(k) summary	The software runs on a standardoff-the-shelf computer or avirtual platform, such asVMware,and can be used to performimage viewing, processing andanalysis of images. Data andimagesare acquired through DICOMcompliant imaging devices.Linux-based server
Functionality	Subject DeviceTeraRecon Neuro version 2.0.0(TBD)	Predicate DeviceNeuro.AI Algorithm version1.0.0(K200750)	Reference Device(Used in QualitativeAssessment)FastStroke, CT Perfusion 4D(K193289)	Reference Device(Used in QualitativeAssessment)iSchemaView RAPID(K182130)
KeyFunctionality/Feature andRegion-of-Interest (ROI)Markers	Same as predicate device	• Automatic arterial and venousinput function selection• Ventricle subtraction	CT perfusion 4D is an imageanalysis software package, whichallows the user to producedynamic imagedata and to generate informationwith regards to changes in imageintensity over time. It supportstheanalysis of CT Perfusion images(in the head and body) after theintravenous injection of contrast,andcalculation of the variousperfusion-related parameters (i.e.regional blood flow, regionalblood volume,mean transit time and capillarypermeability).	The iSchemaView RAPIDprovides both viewing andanalysis capabilities forfunctional anddynamic imaging datasetsacquired with CT Perfusion (CT-P), CT Angiography (CTA), andMRI including a DiffusionWeighted MRI (DWI) Moduleand a Dynamic Analysis Module(dynamic contrast-enhancedimaging data for MRI and CT).The DWI Module is used tovisualize local water diffusionproperties from the analysis ofdiffusion - weighted MRI data.The Dynamic Analysis Moduleis used for visualization andanalysis of dynamic imagingdata, showing properties ofchanges in contrast over time.This functionality includescalculation of parameters relatedto tissue flow (perfusion) andtissue blood volume.
Functionality	Subject DeviceTeraRecon Neuro version 2.0.0(TBD)	Predicate DeviceNeuro.AI Algorithm version1.0.0(K200750)	Reference Device(Used in QualitativeAssessment)FastStroke, CT Perfusion 4D(K193289)	Reference Device(Used in QualitativeAssessment)iSchemaView RAPID(K182130)
Perfusionmeasurementsand color maps	• Same as predicate device and• Time to Maximum (Tmax)• Hypoperfusion maps andvolumes• Mismatch maps(penumbra/umbra maps thatare derived from combinationsof measurement parameters)and related volumes and ratios	• Time to peak (or Time toMinimum)• Take off time (or MaximumSlope of Increase)• Recirculation time (RT)• Mean transit time (MTT)• Blood volume (BV/CBV)• Blood flow (BF/CBF)• User configurable settings	• Blood Flow• Blood Volume• Mean Transit Time• Capillary Permeability• Time to Maximum	• Blood Flow• Blood Volume• Mean Transit Time• Time to Maximum
Graph Displays	Same as predicate device	Artery and Vein Fitted and Rawcurves - time/activity	Not specified in K193289's510(k) summary	Not specified in K182130's510(k) summary
ExportCapability	• Same as predicate device and• Artery Intensity Profile	DICOM files	Not specified in K193289's510(k) summary	Not specified in K182130's510(k) summary
Methods forMathematicalModeling	Same as predicate device	SVD	Not specified in K193289's510(k) summary	Not specified in K182130's510(k) summary
Arterial andVenous InputFunctionSelection	Same as predicate device	Automatic	Not specified in K193289's510(k) summary	Arterial input function (AIF) andVenous output function (VOF)
Functionality	Subject DeviceTeraRecon Neuro version 2.0.0(TBD)	Predicate DeviceNeuro.AI Algorithm version1.0.0(K200750)	Reference Device(Used in QualitativeAssessment)FastStroke, CT Perfusion 4D(K193289)	Reference Device(Used in QualitativeAssessment)iSchemaView RAPID(K182130)
Containerization/ dockerizationof algorithm thatenablesinteroperabilitywith 3rd partyresults includingviewing suchresults	Same as predicate device	• Neuro.AI Algorithm is hostedon the Eureka platform withinits own docker. The algorithmis triggered based on inputdata and generates resultwhich will be delivered tothird party system.• CT and MR Scanners• 3rd party hospital systemssuch as a PACS server, EMRor other• TeraRecon Intuition• Visualization system• Other image viewingsystems that can supportresults generated by theNeuro.AI Algorithm• Notification systems	The configuration ofNeuroPackage enables the userto open a single application,FastStroke, which provides themaccess to both the updated CTPerfusion 4Dand FastStroke applications.The capabilities in CT Perfusion4Dand FastStroke can be offeredindependently.	RAPID is available in thefollowing configurations:• Standard RAPID, which isinstalled directly on a customer'sLinux-based server andintegrated with medical imageprocessing software such ascommercial PACS.• Virtual RAPID, wherein theuser accesses RAPID online anduses it to process DICOMimages otherwise available onhis/her computer.
VentricleSubtraction	Same as predicate device	Setting allows software tocalculate maps with or withoutventricle included.	Ventricle Segmentation	Not specified in K182130's510(k) summary

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

{10}------------------------------------------------

{11}------------------------------------------------

{12}------------------------------------------------

1.7 Performance Data

Safety and performance of the TeraRecon Neuro algorithm have been verified and validated through software testing, quantitative phantom testing and qualitative clinical user evaluation. Software development and testing were performed in accordance with IEC 62304:2006/AI:2015, Medical Device Software - Software life cycle processes, utilizing a risk-based testing methodology. Risk has been evaluated in accordance with ISO 14971:2007, Medical Devices – Application of Risk Management to Medical Devices. During software testing, all pre-defined acceptance criteria for the Neuro.AI Algorithm were met and all software test cases passed. The same verification and validation methodology, risk assessment and acceptance criterion were used for predicate device.

To execute our clinical user evaluation TeraRecon worked with our evaluator Dr. Robert Falk, MD whom was presented with comparison maps generated by the subject device, the predicate device and two additional reference devices GE Medical Systems FastStroke CT Perfusion 4D (K193289) and ISchemaView RAPID (K182130). The evaluator was asked to confirm through qualitative assessment that the generated maps of TeraRecon Neuro are at least 85% substantially equivalent or better than the predicate and reference devices.

Additionally, we performed a quantitative evaluation of Tmax measurements in comparison to the two reference devices. Considering the ground truth as the average Tmax measurement of the two reference devices for a given ROI, we calculated absolute error and absolute percent error for the subject device compared to ground truth. Acceptance criteria was defined as subject device limit of agreement for both metrics less than or equal than the limit of agreement of each predicate device compared to the ground truth.

The results of the software testing and clinical user evaluation validate that the TeraRecon Neuro device meets its qualified requirements, performs as intended, and is as safe and effective as the predicate device. No new or different questions of safety or efficacy have been raised as a result of the verification and validation process.

{13}------------------------------------------------

1.8 Conclusion

The TeraRecon Neuro algorithm is as safe and effective as the predicate device, Neuro.AI Algorithm. The indications for use of the subject device falls within the scope of that for the predicate device. Many of the technological characteristics are the same for the subject and predicate devices. Differences in the technological characteristics between the subject and predicate devices have been addressed through software verification and validation testing and do not raise any new of different questions of safety and effectiveness.

All risk were analyzed, and there are no new risks or modified risks that could result in significant harm which are not effectively mitigated in the predicate device. The analysis above supports a determination of Substantial Equivalence of the TeraRecon Neuro algorithm to the predicate device in terms of safety, efficacy, and performance.

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).