Viz ICH is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of care workflow.

Viz ICH uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation. Identification of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes non-contrast CT images of the brain acquired in the acute setting, and sends notifications to a neurovascular or neurosurgical specialist that a suspected intracranial hemorrhage has been identified and recommends review of those images. Images can be previewed through a mobile application.

lmages that are previewed through the mobile application may be compressed and are for informational purposes only and not intended for diagnostic use beyond notification. Notified clinicians are responsible for viewing non-compressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests. Viz ICH is limited to analysis of imaging data and should not be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.

Viz ICH is contraindicated for analyzing non-contrast CT scans that are acquired on scanners from manufacturers other than General Electric (GE) or its subsidiaries (i.e. GE Healthcare). This contraindication applies to NCCT scans that conform to all applicable Patient Inclusion Criteria, are of adequate technical image quality, and would otherwise be expected to be analyzed by the device for a suspected ICH.

Device Description

Viz ICH is a software-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to an appropriate specialist, such as a neurovascular specialist or neurosurgeon, independent of the standard of care workflow. The system automatically receives and analyzes non-contrast CT (NCCT) studies of patients for image features that indicate the presence of an intracranial hemorrhage (ICH) using an artificial intelligence algorithm, and upon detection of a suspected ICH, sends a notification so as to alert a specialist clinician of the case.

Viz ICH consists of backend and mobile application component software. The Backend software includes a DICOM router and backend server. The DICOM router transmits NCCT images of the head acquired on a local healthcare network to the Backend Server. The Backend Server receives, stores, processes and serves received NCCT scans. The Backend Server also includes an artificial intelligence algorithm that analyzes the received NCCT images for image characteristics that indicate an intracranial haemorrhage (ICH) and, upon detection, sends a notification of the suspected finding to pre-determined specialists.

The Viz ICH Mobile Application software receives notifications generated by the Backend of suspected image findings and allows the notification recipient to view the analyzed NCCT images through a non-diagnostic viewer, as well as patient information that was embedded in the image metadata. Image viewing through the mobile application is for informational purposes only and is not intended for diagnostic use.

AI/ML Overview

Here's a summary of the acceptance criteria and study details for Viz ICH, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

Metric	Acceptance Criteria (Pre-specified performance goal)	Reported Performance (95% CI)
Sensitivity	≥ 80%	93% (87%-97%)
Specificity	≥ 80%	90% (84%-94%)
AUC	Not explicitly stated as an acceptance criterion, but 0.96 was demonstrated as clinical utility	0.96
Time to Alert	Not explicitly stated as an acceptance criterion for the device, but comparative data was provided	0.49 ± 0.15 minutes (device) vs. 38.2 ± 84.3 minutes (Standard of Care)

2. Sample size used for the test set and the data provenance

Sample Size: 261 non-contrast Computed Tomography (NCCT) scans (studies). Approximately equal numbers of positive (47%) and negative (53%) cases were included.
Data Provenance: Retrospective study. Data obtained from two clinical sites in the U.S.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Number of Experts: Not explicitly stated, but "trained neuro-radiologists" were used.
Qualifications of Experts: "Trained neuro-radiologists". Specific years of experience are not mentioned.

4. Adjudication method for the test set

The document implies a consensus-based ground truth ("ground truth, as established by trained neuro-radiologists"). However, the specific adjudication method (e.g., 2+1, 3+1) is not detailed.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

No, a multi-reader multi-case (MRMC) comparative effectiveness study with human readers was not described. The study focused on the standalone performance of the AI algorithm and a comparison of notification times.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

Yes, a standalone performance study of the image analysis algorithm was conducted. The sensitivity and specificity reported are for the algorithm only.

7. The type of ground truth used

Expert consensus, established by "trained neuro-radiologists," in the detection of intracranial hemorrhage (ICH).

8. The sample size for the training set

The sample size for the training set is not provided in the document. The information focuses only on the test set.

9. How the ground truth for the training set was established

The method for establishing ground truth for the training set is not described in the provided document.

Summary

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

March 18, 2020

Image /page/0/Picture/1 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.

Viz.ai, Inc. % Mr. Gregory Ramina Director of Regulatory Affairs 555 De Haro St., Suite 400 SAN FRANCISCO CA 94107

Re: K193658

Trade/Device Name: Viz ICH Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: QAS Dated: March 2, 2020 Received: March 2, 2020

Dear Mr. Ramina:

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/cfpmp/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

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

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see

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

https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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

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

Sincerely,

For

Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

510(k) Number (if known)

K193658

Device Name

Viz ICH

Indications for Use (Describe)

lmages that are previewed through the mobile application may be compressed and are for informational purposes only and not intended for diagnostic use beyond notified clinicians are responsible for viewing non-compressed images on a diagnostic viewer and engaging in appropriate patient and relevant discussion with a treating physician before making care-related decisions or requests. Viz ICH is limited to analysis of imaging data and should not be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.

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. 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}------------------------------------------------

510(k) SUMMARY

Viz.ai, Inc.'s Viz ICH

K193658

Applicant Name: Viz.ai, Inc. 555 De Haro St Suite 400 San Francisco, CA 94107
Contact Person: Gregory Ramina Director of Regulatory Affairs 555 De Haro St Suite 400 San Francisco, CA 94107 Tel. (415) 663-6130 Greg@viz.ai
Date Prepared: March 6, 2020

Device Name and Classification

Name of Device:	Viz ICH
Common or Usual Name:	Radiological Computer-Assisted Triage and Notification Software
Classification Panel:	Radiology
Regulation No:	21 C.F.R. § 892.2080
Regulatory Class:	Class II
Product Code:	QAS

Predicate Devices

Manufacturer	Device Name	Application No.
Viz.ai, Inc. (Primary)	ContaCT	DEN170073
Aidoc Medical, Ltd.	BriefCase	K180647

Device Description

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

Intended Use / Indications for Use

Viz ICH uses an artificial intelligence alqorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation. Identification of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes non-contrast CT images of the brain acquired in the acute setting, and sends notifications to a neurovascular or neurosurgical specialist that a suspected intracranial hemorrhage has been identified and recommends review of those images can be previewed through a mobile application.

Summary of Technological Characteristics

Viz ICH and its primary predicate, ContaCT (DEN170073), use the same process of automatic data identification and transfer to send images from the local hospital network to a

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

remote server for image processing and analysis, i.e., via a DICOM router that automatically identifies relevant images on a local IT Network and transfers them to a Backend Server using a DICOM compliant communication protocol.

Both Viz ICH and the ContaCT device have Backend Server software that can receive, store, process, and serve images that are forwarded from a DICOM router. The Backend Server software for each device has the same additional software functionality that interacts with the image management architecture, including a notifier module.

Where Viz ICH and the primary predicate differ, namely the specific condition and image modality analyzed by each device's algorithm. Viz ICH is similar to the secondary predicate. BriefCase (K180647), in that both software algorithms are designed to detect the same condition, intracranial haemorrhage (ICH), in non-contrast Computed Tomography images (NCCTs) of the head. Like the secondary predicate, BriefCase, the Viz ICH algorithm does not externalize any internal segmentation, analysis, or intermediate outputs used in determining if an ICH is present in the NCCT, nor does either algorithm mark the analyzed NCCT image.

Both Viz ICH and the ContaCT predicate support a mobile application that allows a user to receive push notifications, preview related images, and view patient details associated with a series. The Viz ICH mobile application is subject to the same non-diagnostic viewing limitations as the ContaCT predicate and has the same non-diagnostic warning on the image viewing screen as the predicate. Furthermore, the mobile application for Viz ICH and the ContaCT predicate can perform the same image viewing functions (window, pan, level, zoom, scroll through a cine).

	Viz ICH	ContaCT (DEN170073)	BriefCase (K180647)
Technological Characteristics
DICOMCompatible	Yes	Yes	Yes
Transfer, store,and processDICOM images	Yes	Yes	Yes
Data Acquisition	Acquires medical image datafrom DICOM compliantimaging devices andmodalities.	Acquires medical image datafrom DICOM compliantimaging devices andmodalities.	Acquires medical image datafrom DICOM compliantimaging devices andmodalities.
Image Analysis
SupportedImaging Modality	Computed Tomography, non-contrast (NCCT)	Computed Tomography,contrast-enhanced (CTA)	Computed Tomography, non-contrast (NCCT)
Alteration ofOriginal Image	No	No	No
Results of ImageAnalysis	Internal, no image marking	Internal, no image marking	Internal, no image marking
Image Viewing Functionality
Preview Images	Initial assessment; non-diagnostic purposes	Initial assessment; non-diagnostic purposes	Initial assessment; non-diagnostic purposes
View DICOMData	DICOM Information about thepatient, study and currentimage.	DICOM Information about thepatient, study and currentimage.	DICOM Information about thepatient, study and currentimage.
Image viewing	Yes	Yes	Yes

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

and manipulation(window, pan,level, zoom)
---------------------------------------------------	--	--

Performance Data

Viz.ai conducted a retrospective study to assess the standalone performance of the image analysis algorithm and notification functionality of Viz ICH. The study evaluated the Viz ICH image analysis algorithm in terms of sensitivity and specificity with respect to a ground truth, as established by trained neuro-radiologists, in the detection of intracranial hemorrhage (ICH) in the brain. In addition, the study reported and compared the time to notification for the Viz ICH device with respect to the time to notification for the standard of care as established from available radiological reports.

261 non-contrast Computed Tomography (NCCT) scans (studies) were obtained from two clinical sites in the U.S. There were approximately equal numbers of positive and negative cases (47% of images with ICH and 53% without ICH, respectively) included in the analysis. Sensitivity and specificity were calculated in the image database, comparing the Viz ICH's output to ground truth as established by trained neuro-radiologists. Sensitivity and specificity were 93% (87%-97%) and 90% (84%-94%), respectively. Because the lower bound of each confidence interval exceeded 80%, the study met the pre-specified performance goals of 80% for sensitivity and specificity.

In addition, the area under the receiver operating characteristic curve (AUC) was 0.96 demonstrating the clinical utility and potential benefits of the classifier based on the imaging study results.

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

Image /page/7/Figure/0 description: The image is a Receiver Operating Characteristic (ROC) curve for Viz ICH. The x-axis represents the false positive rate, and the y-axis represents the true positive rate. The ROC curve has an area of 0.96, and a threshold of 0.1 mL is marked with a dotted vertical line.

In the study, the average time to alerting a specialist was 0.49±0.15 minutes, which is substantially lower than the average time to notification seen in the Standard of Care of 38.2±84.3 minutes. This data generally demonstrates that specialists have the opportunity to become involved in the clinical workflow early with notifications from the Viz ICH software.

As part of a secondary analysis, the company stratified the device performance by various confounding variables:

Performance Stratified by Clinical Site
Clinical Site	Sensitivity [95% CI]	Specificity [95% CI]
Erlanger	0.93 [0.85, 0.98]	0.92 [0.84, 0.97]
Mt. Sinai	0.92 [0.8, 0.98]	0.86 [0.75, 0.94]

Performance Stratified by Age
Age Range (years)	Sensitivity [95% CI]	Specificity [95% CI]
<50	0.89 [0.52, 1.0]	0.95 [0.76, 1.0]
50 - 70	0.92 [0.82, 0.97]	0.9 [0.8, 0.96]
>70	0.94 [0.84, 0.99]	0.88 [0.76, 0.95]

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

Performance Stratified by Gender
Gender	Sensitivity [95% Cl]	Specificity [95% CI]
Male	0.9 [0.8, 0.96]	0.9 [0.8, 0.96]
Female	0.95 [0.86, 0.99]	0.89 [0.8, 0.95]

Performance Stratified by ICH Subtype
ICH Subtype	Sensitivity [95% CI]
Intraparenchymal Hemorrhage (IPH)	0.98 [0.91, 1.0]
Intraventricular Hemorrhage (IVH)	1.00 [0.74, 1.0]
Subarachnoid Hemorrhage (SAH)	0.60 [0.26, 0.88]
Subdural Hemorrhage (SDH)	0.85 [0.62, 0.97]
Extradural Hemorrhage (EDH)	N/A
SDH or EDH	0.85 [0.62, 0.97]

Performance Stratified by Slice Thickness
Slice Thickness	Sensitivity	Specificity
2.5mm <= Slice Thickness < 3.5mm	0.93 [0.85, 0.98]	0.92 [0.83, 0.97]
3.5mm <= Slice Thickness <= 5.0mm	0.92 [0.81, 0.98]	0.88 [0.77, 0.95]

Performance Stratified by ICH Volume
Minimal Volume Threshold (mL)	Sensitivity above Threshold [95% CI]	Sensitivity below/equal Threshold [95% CI]
1	0.95 [0.89, 0.98]	0.73 [0.39, 0.94]
5	0.97 [0.91, 0.99]	0.81 [0.64, 0.93]
10	0.99 [0.93, 1.0]	0.84 [0.7, 0.93]

Conclusions

Viz ICH is as safe and effective as the primary predicate, ContaCT (DEN170073), in that it has the same intended use and similar indications, technological characteristics and principles of operation. Where minor differences in indications exist between both devices, Viz ICH is similar to the secondary predicate device, BriefCase (K180647), which uses an artificial intelligence algorithm to detect and notify specified clinicians of an intracranial haemorrhage (ICH) in NCCT scans of the head. The minor differences in indications between ContaCT and Viz ICH do not alter the intended diagnostic use of the device and do not affect its safety and effectiveness. In addition, the minor technological differences between the Viz ICH and its predicate devices raise no new issues of safety or effectiveness. Performance data demonstrate that Viz ICH can identify an ICH per the same primary

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

performance goals, in terms of sensitivity and specificity, as the BriefCase predicate and is as safe and effective as the predicate devices. Thus, Viz ICH is substantially equivalent to its predicate devices.

Regulation Number and Section

§ 892.2080 Radiological computer aided triage and notification software.

(a)
Identification. Radiological computer aided triage and notification software is an image processing prescription device intended to aid in prioritization and triage of radiological medical images. The device notifies a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis of those images performed by the device. The device does not mark, highlight, or direct users' attention to a specific location in the original image. The device does not remove cases from a reading queue. The device operates in parallel with the standard of care, which remains the default option for all cases.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (
e.g., improved time to review of prioritized images for pre-specified clinicians).(iii) Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (
e.g., subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment.(iv) Stand-alone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results).(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use;
(ii) A detailed description of the intended user and user training that addresses appropriate use protocols for the device;
(iii) Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality for certain subpopulations), as applicable;(iv) A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images;
(v) Device operating instructions; and
(vi) A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (
e.g., improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (e.g., confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.