The Viz Subdural+ (Subdural Plus) device is intended for automatic labeling, visualization and quantification of collections in the subdural space from a set of Non-Contrast Head CT (NCCT) images. The software is intended to automate the current manual process of identifying, labeling and quantifying the volume of collections in the subdural space identified on NCCT images. Viz Subdural + provides volumes from NCCT images acquired at a single time point.

The Viz Subdural+ software is intended for labeling subdural collections and reporting the grayscale value of the collection, widest width of the subdural collection, and midline shift. The device output should be reviewed along with the patient's original images by a physician qualified to interpret brain CT images.

Device Description

Viz Subdural+ is a software-only device that uses a locked artificial intelligence machine learning (AI/ML) algorithm to process and analyze non-contrast CT (NCCT) scans of the head to automatically measure the collections in the subdural region in the brain and midline shift.

The device output provides visual overlays of automatically measured subdural collections where the overlay opacity (intensity) corresponds to the grayscale value of the collection within the native NCCT, and reports the total volume and widest width of the subdural collections. The device also automates and reports the measure of midline shift.

The results of the automated measurement are provided in a summary series and segmentation series in DICOM format. The summary series consists of a summary table of subdural collections, snapshot of each collection and a midline shift measurement. The first slice of the Subdural+ summary series summarizes the measurement results of each subdural collection (volume and widest width), total volume and midline shift in tabular format. The summary series also contains a snapshot of each subdural collection and a snapshot of the midline shift measurement. The segmentation series shows an RGB overlay where a subdural collection is identified by a colored overlay with the color intensity corresponding to the HU values of the original image on each slice of the input series of the segmented region. On slices with an overlay representing a measured subdural collection, the volume of the subdural collection is provided. The midline shift is overlaid and provided on the slice where the midline shift is measured.

Images are automatically forwarded from the Healthcare Facility and sent to Viz.ai's Backend Server after acquisition at the CT scanner. Viz Subdural+ is hosted on Viz.ai's Backend Server and automatically analyzes applicable NCCT scans that are acquired on CT scanners and are forwarded to Viz.ai's Backend Server. The results of the analysis are exported in DICOM format and are sent to a DICOM destination (e.g., PACS) where they are available for review by radiologists, neurologists, neuro-surgeons, interventional neuroradiologists, or other appropriately trained professionals to assist in the measurement of subdural collection volume, widest subdural collection width and midline shift.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance letter for Viz Subdural+:

Acceptance Criteria and Reported Device Performance

Metric	Acceptance Criteria (Target/Threshold)	Reported Device Performance (Mean (95% CI))
Subdural Collection Volume MAE	Not explicitly stated (implied by passing primary endpoint)	7.53 (5.60, 9.45)
Subdural Collection Volume DICE Score	Not explicitly stated (implied by passing primary endpoint)	73% (68% - 77%)
Subdural Collection Max Thickness MAE	Not explicitly stated (implied by passing primary endpoint)	1.77 (1.24, 2.30)
Midline Shift MAE	< 2mm (as per predicate device)	1.1 (0.94, 1.27)

Note: The document states the device "passed the primary endpoints for the study in terms of mean absolute error (MAE)," but it does not explicitly state the numerical acceptance thresholds for subdural collection volume or thickness MAE/DICE. The 2mm MAE for Midline Shift is inferred from the statement that the Subdural+ algorithm can measure midline shift "within the same performance limits (MAE < 2mm) as the predicate device."

Study Information

Sample Size Used for the Test Set and Data Provenance:
- Subdural Collection Volume and Thickness Assessment: 203 cases
- Midline Shift Assessment: 151 cases
- Data Provenance: Retrospective study. Cases were obtained from two clinical sites. Imaging was from patients who received NCCT imaging assessment after presenting to one of the participating sites. The country of origin is not explicitly stated.
Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
- Number of Experts: Not explicitly stated, but established by "trained neuroradiologists."
- Qualifications: "Trained neuroradiologists" – specific experience levels (e.g., 10 years) are not provided.
Adjudication Method for the Test Set:
- Not explicitly stated. The ground truth was "established by trained neuroradiologists," which could imply consensus or sequential review, but the specific method (e.g., 2+1, 3+1) is not detailed.
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No MRMC comparative effectiveness study involving human readers improving with AI vs. without AI assistance was mentioned. The study focused on the standalone performance of the algorithm against a human-established ground truth.
Standalone (Algorithm Only) Performance Study:
- Yes, a retrospective study was conducted to assess the "standalone performance of the image analysis algorithm for Viz Subdural+ as compared to a ground truth established by trained neuroradiologists."
Type of Ground Truth Used:
- Expert Consensus: The ground truth was "established by trained neuroradiologists" in segmenting, labeling, and quantifying subdural collections, maximal subdural collection width (thickness), and midline shift. This implies expert consensus or adjudicated expert readings. It is not pathology or outcomes data.
Sample Size for the Training Set:
- Not explicitly stated in the provided text.
How the Ground Truth for the Training Set Was Established:
- Not explicitly stated in the provided text. The document focuses on the performance of the locked AI/ML algorithm (implying training was already completed) and its validation against a test set.

Summary

FDA 510(k) Clearance Letter - Viz Subdural+

Page 1

U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov

Doc ID # 04017.07.05

June 10, 2025

Viz.ai, Inc.
Gregory Ramina
Regulatory Affairs Director
5000 Center Green Way
Cary, North Carolina 27513

Re: K250354
Trade/Device Name: Viz Subdural+, Viz SUBDURAL PLUS
Regulation Number: 21 CFR 892.2050
Regulation Name: Medical Image Management And Processing System
Regulatory Class: Class II
Product Code: QIH
Dated: May 5, 2025
Received: May 5, 2025

Dear Gregory 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 (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.

Page 2

K250354 - Gregory Ramina Page 2

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 (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.

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

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-

Page 3

K250354 - Gregory Ramina Page 3

assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Jessica Lamb, Ph.D.
Assistant Director
DHT8B: Division of Radiological Imaging
Devices and Electronic Products
OHT8: Office of Radiological Health
Office of Product Evaluation and Quality
Center for Devices and Radiological Health

Enclosure

Page 4

DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration

Indications for Use

Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.

Submission Number (if known): K250354

Device Name: Viz Subdural+, Viz SUBDURAL PLUS

Indications for Use (Describe)

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

☒ Prescription Use (Part 21 CFR 801 Subpart D) ☐ Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services
Food and Drug Administration
Office of Chief Information Officer
Paperwork Reduction Act (PRA) Staff
PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

Page 5

510(k) Summary

Viz Subdural+

Applicant Name: Viz.ai, Inc.
5000 Center Green Way
Cary NC, 27513

Contact Person: Gregory Ramina
Regulatory Affairs Director
5000 Center Green Way
Cary NC, 27513
Tel. (415) 663-6130
Greg@viz.ai

Date Prepared: May 1, 2025

Device Name and Classification

Name of Device: Viz Subdural+, Viz SUBDURAL PLUS
Common or Usual Name: Automated Radiological Image Processing Software
Classification Panel: Radiology
Regulation No: 21 C.F.R. § 892.2050
Regulatory Class: Class II
Product Code: QIH

Predicate Device(s)

Manufacturer	Device Name	Application No.
Viz.ai, Inc.	Viz HDS	K232363

Device Description

The device output provides visual overlays of automatically measured subdural collections where the overlay opacity (intensity) corresponds to the grayscale value of the collection within the native

Page 6

NCCT, and reports the total volume and widest width of the subdural collections. The device also automates and reports the measure of midline shift.

Figure 1. Examples of the summary table from the summary series output (left) and a slice from the segmentation series output (right). The summary series would include an additional summary image (snapshot) of each collection in the table and a summary image of the midline shift. The color overlay gradient in the slice from the segmentation series output corresponds to the Hounsfield Unit (HU) of each corresponding pixel in the NCCT.

Page 7

assist in the measurement of subdural collection volume, widest subdural collection width and midline shift.

Figure 2. Data flow diagram for Viz Subdural+.

Intended Use and Indications for Use

The Viz Subdural+ (Subdural Plus) device is intended for automatic labeling, visualization and quantification of collections in the subdural space from a set of Non-Contrast Head CT (NCCT) images. The software is intended to automate the current manual process of identifying, labeling and quantifying the volume of collections in the subdural space identified on NCCT images. Viz Subdural+ provides volumes from NCCT images acquired at a single time point.

Summary of Technological Characteristics

The subject device, Viz Subdural+, is substantially equivalent to the predicate device, Viz HDS (K232363). In comparing the technological characteristics, both the subject and predicate devices use an artificial intelligence algorithm to identify, label and quantify measured quantities in NCCT imaging of the head from images acquired at a single time point. Both the subject and predicate devices use software algorithms that incorporate artificial-intelligence to perform as intended. Both devices' algorithms automatically receive, assess the applicability of received input imaging, and automatically process and measure supported imaging. Both devices' algorithms use similar pipelines with similar steps to measure their indicated structures and both devices' algorithms use deep-learning convolutional neural networks with similar architectures. Both devices provide their outputs in DICOM format and return the results to a pre-configured destination (e.g., a PACS server) for the user to view the device outputs.

Page 8

While both devices provide an automated measurement of midline shift, the subject device's algorithm is different from the predicate device's algorithm and is designed and indicated for automatically labeling and quantifying subdural collections (subdural collection volume and widest width) whereas the predicate device's algorithm is indicated and designed for automatically labeling and measuring the volume of intracranial hyperdensities and lateral ventricles. Performance testing demonstrated that Viz Subdural+ has acceptable subdural collection volume and collection width measurement performance. Additionally, the Viz Subdural+ algorithm can measure midline shift within the same performance limits (MAE < 2mm) as the predicate device. Thus, any differences in the subject device's algorithm or the different structures measured by the Viz Subdural+ algorithm do not raise any new or different questions of safety and efficacy.

Both devices provide summary and segmentation series outputs. Both device outputs include overlays of the segmentation on the measured NCCT which forms the basis of the reported volume measurements. The subject device's overlay output differs from the predicate in that the subject device's overlay color intensity at each pixel corresponds to the HU values of the segmented pixels representing subdural collection in the original NCCT whereas the overlays of the predicate device are a single color used solely to differentiate between hyperdensities. This difference does not raise any new or different questions of safety and efficacy regarding the segmentation overlay as the information provided by the color intensity represents standardized HU information which the user can retrieve by looking at the original NCCT.

Substantial Equivalence Table

	Predicate Device	Subject Device
	Viz HDS	Viz Subdural+
Application No.	K232363	K250354
Product Code	QIH	QIH
Regulation No.	21 C.F.R. § 892.2050	21 C.F.R. § 892.2050

Page 9

	Predicate Device	Subject Device
Intended Use / Indications for Use	The Viz HDS device is intended for automatic labeling, visualization, and quantification of segmentable brain structures from a set of Non-Contrast CT (NCCT) head scans. The software is intended to automate the current manual process of identifying, labeling, and quantifying the volume of segmentable brain structures identified on NCCT images. Viz HDS provides volumes from NCCT scans acquired at a single time point. The Viz HDS software is indicated for use in the analysis of the following structures: Intracranial Hyperdensities, Lateral Ventricles and Midline Shift. The device output should be reviewed along with patient's original images by a physician.	The Viz Subdural+ (Subdural Plus) device is intended for automatic labeling, visualization and quantification of collections in the subdural space from a set of Non-Contrast Head CT (NCCT) images. The software is intended to automate the current manual process of identifying, labeling and quantifying the volume of collections in the subdural space identified on NCCT images. Viz Subdural+ provides volumes from NCCT images acquired at a single time point. The Viz Subdural+ software is intended for labeling subdural collections and reporting the grayscale value of the collection, widest width of the subdural collection, and midline shift. The device output should be reviewed along with the patient's original images by a physician qualified to interpret brain CT images.
Anatomical Region	Head	Head
Independent Standard of Care Workflow	Yes	Yes
Input images	Non-contrast CT from a single time point	Non-contrast CT from a single time point
Measured Structures / Conditions	Intracranial hyperdensities, lateral ventricles and midline shift	Subdural collections and midline shift
Measurands	Intracranial hyperdensities volume; lateral ventricles volume; midline shift	Subdural collections volume; Subdural collections widest width; midline shift
Data Acquisition	Acquires medical image data from DICOM compliant imaging devices and modalities.	Acquires medical image data from DICOM compliant imaging devices and modalities.

Page 10

	Predicate Device	Subject Device
Supported Imaging Modality	Non-contrast CT (NCCT)	Non-contrast CT (NCCT)
Alteration of Original Image	No	No
Artificial Intelligence Algorithm	Yes	Yes
Output	Multiple electronic reports with measurements quantifying brain structures and midline shift; annotated DICOM Images.	Multiple electronic reports with measurements quantifying subdural collections and midline shift; annotated DICOM Images.

Performance Data

A retrospective study was conducted to assess the standalone performance of the image analysis algorithm for Viz Subdural+ as compared to a ground truth established by trained neuroradiologists in segmenting, labeling and quantifying subdural collections, maximal subdural collection width (thickness) and midline shift. Subdural collection measurement performance (volume and thickness) and midline shift were assessed on datasets with 203 and 151 cases, respectively. Each dataset was obtained from two clinical sites. Imaging within each dataset were from patients that received an NCCT imaging assessment after presenting to one of the participating sites.

Metric	Mean Absolute Error (MAE)			DICE Score
	Mean (95% Confidence Interval)	Standard Deviation	Median (10th - 90th Percentile)	Mean (95% Confidence Interval)
Subdural Collection Volume (N=203)	7.53 (5.60, 9.45)	13.91	2.70 (0.0 - 22.22)	73% (68% - 77%)
Subdural Collection Maximum (Widest) Thickness (N=203)	1.77 (1.24, 2.30)	3.84	0.43 (0.0 - 5.37)	N/A
Midline Shift (N=151)	1.1 (0.94,1.27)	1.03	0.8 (0.17 - 2.37)	N/A

The results of the retrospective study demonstrated the device passed the primary endpoints for the study in terms of mean absolute error (MAE).

Page 11

Additional stratification of the device performance as measured by MAE was provided by different patient demographic, technical and radiographic findings to demonstrate generalizability of the device within the intended population. Device results for subdural collection volume, widest width and midline shift were also compared to the truther consensus by Bland-Altman plots and linear regression analysis.

Conclusions

Viz Subdural+ is as safe and effective as the predicate device. The subject device and the predicate have the same intended use and similar indications, technological characteristics, and principles of operation. Differences in the types of structures labeled and quantified by each device, and the information provided in the device's respective outputs do not raise any new or different questions of safety and efficacy. Viz.ai has provided supportive clinical data and software testing which demonstrates that the subject device can perform effective labeling, visualization and quantification of subdural collection volume, widest subdural collection width and midline shift. Thus, Viz Subdural+ is substantially equivalent to the predicate.

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).