(101 days)
Yes
The document explicitly states that "Clarius Median Nerve AI is a machine learning algorithm" and uses a "deep learning image segmentation algorithm" to perform its functions.
No
The device is described as an assistive tool for measurement and segmentation of the median nerve's cross-sectional area, not for treating conditions or diseases.
Yes
Explanation: The device is intended for "segmentation and semi-automatic non-invasive measurements of the median nerve cross-sectional area on ultrasound data." While it does not provide a definitive diagnosis, measuring the cross-sectional area of the median nerve is a key component in the diagnosis of certain conditions, such as carpal tunnel syndrome. It assists healthcare professionals in making clinical judgments which can lead to a diagnosis, therefore classifying it as a diagnostic device.
No
The device is integrated into the Clarius App software as part of the complete Clarius Ultrasound Scanner system, which includes hardware (transducers). The description specifically states, "Clarius Median Nerve AI is not a stand-alone software device."
No
The device analyzes ultrasound data, which is acquired in-vivo, not in vitro.
Yes
The letter explicitly states, "FDA's substantial equivalence determination also included the review and clearance of your Predetermined Change Control Plan (PCCP)." This language directly indicates that the PCCP for this specific device has been cleared by the FDA.
Intended Use / Indications for Use
Clarius Median Nerve AI is intended for segmentation and semi-automatic non-invasive measurements of the median nerve cross-sectional area on ultrasound data acquired by the Clarius Ultrasound Scanner (i.e., linear array scanners). The user shall be a healthcare professional trained and qualified in ultrasound. The user retains the responsibility of confirming the validity of the measurements based on standard practices and clinical judgment. Clarius Median Nerve AI is indicated for use in adult patients only.
Product codes
QIH
Device Description
Clarius Median Nerve AI is a machine learning algorithm that is integrated into the Clarius App software as part of the complete Clarius Ultrasound Scanner system for use in musculoskeletal ultrasound applications, specifically intended for segmentation and measurement of the cross-sectional area of the median nerve. Clarius Median Nerve AI is intended for use by trained healthcare practitioners for measurement of the cross-sectional area (CSA) of the median nerve on ultrasound data acquired by the Clarius Ultrasound Scanner system (i.e., linear array scanners) using a deep learning image segmentation algorithm.
During the ultrasound imaging procedure, the anatomical site is selected through a preset software selection (i.e., Hand/Wrist) from the Clarius App in which Clarius Median Nerve AI will segment the median nerve in transverse view (with a segmentation mask placed on the ultrasound image) and engage to automatically place calipers on the segmentation mask to measure the median nerve's cross-sectional area.
Clarius Median Nerve AI operates by performing the following tasks:
• Automatic detection and measurement of the median nerve in transverse view
Clarius Median Nerve AI operates by identifying and segmenting the median nerve in the forearm and wrist and performs automatic measurements of the median nerve's cross-sectional area. The user has the option to manually adjust the measurements made by Clarius Median Nerve AI by moving the caliper crosshairs. Clarius Median Nerve AI does not perform any functions that could not be accomplished manually by a trained and qualified user.
Clarius Median Nerve AI is an assistive tool intended to inform clinical management and is not intended to replace clinical decision-making. The clinician retains the ultimate responsibility of ascertaining the measurements based on standard practices and clinical judgment. Clarius Median Nerve AI is indicated for use in adult patients only.
Clarius Median Nerve AI is integrated into the Clarius App software, which is compatible with iOS and Android operating systems two versions prior to the latest iOS or Android stable release build and is intended for use with the following Clarius Ultrasound Scanner system transducers (previously 510(k)-cleared in K213436). Clarius Median Nerve AI is not a stand-alone software device.
Clarius Ultrasound Transducers: L7 HD3; L15 HD3; L20 HD3
Clarius App Software: Clarius Ultrasound App (Clarius App) for iOS; Clarius Ultrasound App (Clarius App) for Android
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
Ultrasound
Anatomical Site
Wrist, forearm
Indicated Patient Age Range
Adults
Intended User / Care Setting
Healthcare professional trained and qualified in ultrasound / Healthcare setting (e.g., hospital, clinic)
Description of the training set, sample size, data source, and annotation protocol
The Clarius Median Nerve AI Deep Neural Network (DNN) model was developed and trained using three data sets: training, tuning, and internal testing. The DNN parameters and weights were updated on the training data and evaluated on the validation (tuning) data at each epoch. Data used for model development was collected from the Clarius Cloud and/or partner clinics and was partitioned by unique anonymous patient identifiers to ensure there was no data overlap between the training, internal testing, and clinical verification datasets. The internal test data was fully independent of the training/tuning dataset and was labelled by experts.
Description of the test set, sample size, data source, and annotation protocol
Following internal testing, a single model was selected, and a completely separate test dataset was used for performance testing of the AI model (clinical verification). This verification dataset was independent of the training/tuning, and internal testing datasets, in order to ensure robust results.
The clinical verification data to evaluate the clinical performance of Clarius Median Nerve AI was entirely independent from the training, tuning (validation) and internal testing datasets used in the development of the AI model. Data was collected from the Clarius Cloud and/or partner clinics.
For the clinical verification study, ultrasound images were randomly obtained from an anonymized multi-center database of images from the United States, Canada, Brazil, United Kingdom, Australia, Belgium, Germany, South Africa, Dominican Republic, Poland, The Netherlands, and Philippines. The study was conducted using de-identified ultrasound data previously collected and stored on a cloud platform. The total sample size included in the study was 182 images collected from 126 subjects, with the majority representing patients from the United States. The images collected were cross sectional (transverse view) images on the median nerve at the level of the forearm and wrist. Some subjects had images collected at both levels (forearm and wrist), which accounts for the 182 images collected from 126 subjects.
As part of the truthing process, Clarius only included data from the institutions/clinical sites that were not represented in the data used for algorithmic development of the Clarius Median Nerve AI model. The exclusion criteria used were that images of inadequate quality were not added to the sample size (non-diagnostic images with artifacts obstructing specific anatomy) and images with incomplete anatomy and views. In measurement comparisons, Clarius excluded the subjects where the Median Nerve AI model failed to generate a measurement since there was no value to compare. To aggregate measurements from different truthers, the mean of the three values was taken and was treated as one reviewer mean. No clinical information was provided to the clinicians regarding patients utilized in the clinical truthing process. The clinicians only had access to the ultrasound image for identifying the anatomy, segmenting the median nerve, and performing measurements by placing the calipers. The lighting and monitor size/resolution were operator-dependent using their clinical judgement. The truthing process was not based on any follow-up medical examination.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Clinical Verification Study:
- Study Type: Retrospective analysis.
- Sample Size: 182 images collected from 126 subjects.
- Standalone Performance: Not explicitly stated as standalone performance; rather, it was compared against human experts.
- Key Results:
- The automatic median nerve CSA measurement was found to be non-inferior to manual measurements by human experts.
- Non-inferiority p-value: 6.497e-47 (97.5% CI: -inf, 0.3285) with an equivalence margin of 3 mm².
- Mean difference (human experts vs. Clarius Median Nerve AI): -0.065 mm².
- Intraclass Correlation Coefficient (ICC): 0.81 (95% CI: 0.74, 0.87) for Clarius Median Nerve AI versus the Mean of Reviewers cross-sectional area.
- Jaccard Scores for Segmentation masks (Clarius Median Nerve AI vs. Reviewers):
- Reviewer 1 vs Clarius Median Nerve AI: 0.62 [95%CI: 0.62, 0.68]
- Reviewer 2 vs Clarius Median Nerve AI: 0.71 [95%CI: 0.69, 0.74]
- Reviewer 3 vs Clarius Median Nerve AI: 0.68 [95%CI: 0.65, 0.71]
- Bland-Altman plots indicated strong agreement.
- ICC scores for different probe models demonstrated reliability.
Clinical Validation Study:
- Study Type: Clinical validation using production equivalent units in a simulated user environment.
- Sample Size: Not specified.
- Key Results: Consistent results among all users, meeting pre-defined acceptance criteria. Users were able to activate the AI, image the nerve, perform live segmentation and automated measurements, manually adjust measurements, change segmentation mask opacity, calculate and display CSA, and save measurements.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
- Non-inferiority p-value: 6.497e-47 (97.5% CI: -inf, 0.3285)
- Mean Difference (Clarius Median Nerve AI vs Human Experts): -0.065 mm²
- Intraclass Correlation Coefficient (ICC): 0.81 (95% CI: 0.74, 0.87)
- Jaccard Score (Reviewer 1 vs Clarius Median Nerve AI): 0.62 [95%CI: 0.62, 0.68]
- Jaccard Score (Reviewer 2 vs Clarius Median Nerve AI): 0.71 [95%CI: 0.69, 0.74]
- Jaccard Score (Reviewer 3 vs Clarius Median Nerve AI): 0.68 [95%CI: 0.65, 0.71]
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Clarius Median Nerve AI uses a machine learning (ML) algorithm for measurement of the median nerve cross-sectional area on ultrasound image data acquired by the Clarius Ultrasound Scanner.
Modifications to Clarius Median Nerve AI will be made in accordance with its Predetermined Change Control Plan (PCCP). The PCCP provides a description of the device's planned modifications, a modification protocol to test, verify, validate, and implement the modifications in a manner that ensures the continued safety and effectiveness of the device, mitigating risks associated with changes to the Median Nerve AI model to not adversely impact the device's performance, safety, or effectiveness associated with its indications for use, and an impact assessment of the planned modifications.
The modified Clarius Median Nerve AI algorithm will be adequately trained, tuned, tested, and locked before release of the modified Median Nerve AI model. Implemented modifications to the Clarius Median Nerve AI algorithm will be communicated to users via the Clarius App software update notification and through updated labelling.
Summary of planned modifications to Clarius Median Nerve AI per the PCCP:
1. Modification of training hyperparameters (initial learning rate, width multiplier, dropout rate)
- Rationale: Improvement and optimization of Clarius Median Nerve AI's performance.
- Testing Methods: Re-training of the Median Nerve AI model with modified hyperparameters to optimize its performance followed by internal testing and a comparison of the original Median Nerve AI model to the modified Median Nerve AI model (using performance metrics) followed with clinical performance testing (verification and validation).
- Impact Assessment: Improved performance metrics of modified Median Nerve AI model with increased accuracy and more robust measurements displayed to users.
- Benefit-Risk Analysis:
- Benefits: Improved performance; generalization.
- Risks: Overfitting; unintended bias.
- Risk Mitigation: Proper regularization techniques and cross-validation and dropout will be employed to mitigate overfitting. Internal testing and verification will be conducted to mitigate unintended biases.
2. Modification of post-processing algorithms (adjustments to measurement validity thresholds)
- Rationale: Improvement and optimization of Clarius Median Nerve AI's performance and robustness.
- Testing Methods: Internal testing and a comparison of the original Median Nerve AI model to the modified Median Nerve AI model (using performance metrics) and clinical performance testing (verification and validation).
- Impact Assessment: Improved performance metrics of modified Median Nerve AI model.
- Benefit-Risk Analysis:
- Benefits: Improved performance; generalization.
- Risks: Overfitting; unintended bias.
- Risk Mitigation: Proper regularization techniques and cross-validation and dropout will be employed to mitigate overfitting. Internal testing and verification will be conducted to mitigate unintended biases.
3. Modification of data input sources (Clarius probes)
- Rationale: To add data from current Clarius scanners and future 510(k) cleared scanners to the Clarius Median Nerve AI model so the model can be deployed on more scanners.
- Testing Methods: Re-training of the Median Nerve AI model to expand its use with additional data input sources (i.e., 510(k)-cleared models of the Clarius Ultrasound Scanner), internal testing, and clinical performance testing (verification and validation) to assesses its performance with the new data input sources.
- Impact Assessment: By accommodating a wider array of image geometries and characteristics with the use of new 510(k)-cleared Clarius ultrasound scanners, the updated Median Nerve AI model will be better equipped to handle different transducer models of the Clarius Ultrasound Scanner used in varying clinical scenarios.
- Benefit-Risk Analysis:
- Benefits: Enhanced compatibility; Flexibility for diverse clinical settings.
- Risks: Data skewing and concept drift.
- Risk Mitigation: Internal testing and verification datasets within the intended patient population will ensure that data skewing and concept drift are mitigated.
§ 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).
Clarius Median Nerve AI - FDA 510(k) Clearance
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue D o c I D # 0 4 0 1 7 . 0 7 . 0 5
Silver Spring, MD 20993
www.fda.gov
Clarius Mobile Health Corp.
Agatha Szeliga
Director, Regulatory Affairs
205-2980 Virtual Way
VANCOUVER, BC V5M 4X3
CANADA
Re: K250226
Trade/Device Name: Clarius Median Nerve AI
Regulation Number: 21 CFR 892.2050
Regulation Name: Medical Image Management And Processing System
Regulatory Class: Class II
Product Code: QIH
Dated: April 4, 2025
Received: April 7, 2025
Dear Agatha Szeliga:
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.
May 8, 2025
Page 2
K250226 - Agatha Szeliga Page 2
FDA's substantial equivalence determination also included the review and clearance of your Predetermined
Change Control Plan (PCCP). Under section 515C(b)(1) of the Act, a new premarket notification is not
required for a change to a device cleared under section 510(k) of the Act, if such change is consistent with an
established PCCP granted pursuant to section 515C(b)(2) of the Act. Under 21 CFR 807.81(a)(3), a new
premarket notification is required if there is a major change or modification in the intended use of a device,
or if there is a change or modification in a device that could significantly affect the safety or effectiveness of
the device, e.g., a significant change or modification in design, material, chemical composition, energy
source, or manufacturing process. Accordingly, if deviations from the established PCCP result in a major
change or modification in the intended use of the device, or result in a change or modification in the device
that could significantly affect the safety or effectiveness of the device, then a new premarket notification
would be required consistent with section 515C(b)(1) of the Act and 21 CFR 807.81(a)(3). Failure to submit
such a premarket submission would constitute adulteration and misbranding under sections 501(f)(1)(B) and
502(o) of the Act, respectively.
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
Page 3
K250226 - Agatha Szeliga Page 3
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-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, Imaging Software Team
DHT8B: Division of Radiologic 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
FORM FDA 3881 (8/23)
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.
510(k) Number (if known)
Device Name
Clarius Median Nerve AI
Indications for Use (Describe)
Clarius Median Nerve AI is intended for segmentation and semi-automatic non-invasive measurements of the median
nerve cross-sectional area on ultrasound data acquired by the Clarius Ultrasound Scanner (i.e., linear array scanners). The
user shall be a healthcare professional trained and qualified in ultrasound. The user retains the responsibility of
confirming the validity of the measurements based on standard practices and clinical judgment. Clarius Median Nerve Al
is indicated for use in adult patients only.
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
This 510(k) summary of safety and effectiveness information is submitted in accordance with the requirements of 21 CFR § 807.92.
Subject Device Trade Name: Clarius Median Nerve AI
Device Classification Name: Automated Radiological Image Processing Software
Regulation Number, Name and Product Code:
| Regulation Number | Regulation Name | Product Code |
|---|---|---|
| 21 CFR § 892.2050 | Medical Image Management and Processing System | QIH |
FDA 510(k) Review Panel: Radiology
Classification: Class II
Manufacturer:
Clarius Mobile Health Corp.
205-2980 Virtual Way
Vancouver, BC V5M 4X3 Canada
Contact Name:
Agatha Szeliga
Director, Regulatory Affairs
agatha.szeliga@clarius.com
Date 510(k) Summary Prepared: May 8, 2025
Predicate Device Information:
Device Trade Name: Clarius AI
510(k) Reference: K222406
Manufacturer Name: Clarius Mobile Health Corp.
Regulation Name: Medical Image Management and Processing System
Device Classification Name: Automated Radiological Image Processing Software
Primary Product Code: QIH
Regulation Number: 21 CFR § 892.2050
Regulatory Class: Class II
Note: The predicate device has not been subject to a design-related recall.
Device Description
Clarius Median Nerve AI is a machine learning algorithm that is integrated into the Clarius App software as part of the complete Clarius Ultrasound Scanner system for use in musculoskeletal ultrasound applications, specifically intended for segmentation and measurement of the cross-sectional area of the median nerve. Clarius Median Nerve AI is intended for use by trained healthcare practitioners for
Page 6
measurement of the cross-sectional area (CSA) of the median nerve on ultrasound data acquired by the Clarius Ultrasound Scanner system (i.e., linear array scanners) using a deep learning image segmentation algorithm.
During the ultrasound imaging procedure, the anatomical site is selected through a preset software selection (i.e., Hand/Wrist) from the Clarius App in which Clarius Median Nerve AI will segment the median nerve in transverse view (with a segmentation mask placed on the ultrasound image) and engage to automatically place calipers on the segmentation mask to measure the median nerve's cross-sectional area.
Clarius Median Nerve AI operates by performing the following tasks:
• Automatic detection and measurement of the median nerve in transverse view
Clarius Median Nerve AI operates by identifying and segmenting the median nerve in the forearm and wrist and performs automatic measurements of the median nerve's cross-sectional area. The user has the option to manually adjust the measurements made by Clarius Median Nerve AI by moving the caliper crosshairs. Clarius Median Nerve AI does not perform any functions that could not be accomplished manually by a trained and qualified user.
Clarius Median Nerve AI is an assistive tool intended to inform clinical management and is not intended to replace clinical decision-making. The clinician retains the ultimate responsibility of ascertaining the measurements based on standard practices and clinical judgment. Clarius Median Nerve AI is indicated for use in adult patients only.
Clarius Median Nerve AI is integrated into the Clarius App software, which is compatible with iOS and Android operating systems two versions prior to the latest iOS or Android stable release build and is intended for use with the following Clarius Ultrasound Scanner system transducers (previously 510(k)-cleared in K213436). Clarius Median Nerve AI is not a stand-alone software device.
| Clarius Ultrasound Transducers | L7 HD3; L15 HD3; L20 HD3 |
|---|---|
| Clarius App Software | Clarius Ultrasound App (Clarius App) for iOS; Clarius Ultrasound App (Clarius App) for Android |
Indications for Use for Clarius Median Nerve AI
Clarius Median Nerve AI is intended for segmentation and semi-automatic non-invasive measurements of the median nerve cross-sectional area on ultrasound data acquired by the Clarius Ultrasound Scanner (i.e., linear array scanners). The user shall be a healthcare professional trained and qualified in ultrasound. The user retains the responsibility of confirming the validity of the measurements based on standard practices and clinical judgment. Clarius Median Nerve AI is intended for use in adult patients only.
Comparison of the Subject Device and Legally Marketed Device for Demonstration of Substantial Equivalence
The following table provides a comparison of the subject device, Clarius Median Nerve AI, to the predicate device, Clarius AI. The comparison of the subject device to the legally marketed device shows that the subject device has the same intended use, similar indications for use, the same principle of operation, and
Page 7
is based on a similar AI/ML algorithm providing segmentation and measurement of musculoskeletal structures, comparable to the legally marketed device referenced herein.
Page 8
Table 1 - Comparison of the Subject Device to the Legally Marketed Device
| Criteria | SUBJECT DEVICE | PREDICATE DEVICE | RATIONALE
(if subject device differs from predicate device) |
|---------|----------------|------------------|-------------------------------------------------------------|
| Device Trade Name | Clarius Median Nerve AI | Clarius AI | |
| 510(k) Holder/ Manufacturer | Clarius Mobile Health Corp. | Clarius Mobile Health Corp. | Same as predicate device. |
| Submission Reference | Current Submission | K222406 | Not applicable |
| Primary Product Code | QIH | QIH | Same as predicate device. |
| Device Classification Name | Automated Radiological Image Processing Software | Automated Radiological Image Processing Software | Same as predicate device. |
| Regulation Name | Medical Image Management and Processing System | Medical Image Management and Processing System | Same as predicate device. |
| Regulation Number | 21 CFR § 892.2050 | 21 CFR § 892.2050 | Same as predicate device. |
| Intended Use | Intended for use as an assistive tool during the acquisition and interpretation of ultrasound images utilizing an artificial intelligence/machine-learning algorithm for segmentation and measurement of anatomical structures. | Non-invasive processing of ultrasound images using automatic image segmentation and measurement of anatomical structures utilizing artificial intelligence/ machine learning algorithms. | Same as predicate device. |
| Indications for Use | Clarius Median Nerve AI is intended for segmentation and semi-automatic non-invasive measurements of the median nerve cross-sectional area on ultrasound data acquired by the Clarius Ultrasound Scanner (i.e., linear array scanners). The user shall be a healthcare professional trained and qualified in ultrasound. The user retains the responsibility of confirming the validity of the measurements based on standard practices and clinical | Clarius AI is intended to semi-automatically place calipers for non-invasive measurements of musculoskeletal structures (e.g., Achilles' tendon, plantar fascia, patellar tendon) on ultrasound data acquired by the Clarius Ultrasound Scanner (i.e., L7 and L15). The user shall be a healthcare professional trained and qualified in MSK (musculoskeletal) ultrasound. The user shall retain the ultimate responsibility of ascertaining the measurements based on standard practices and clinical judgment. | Both the predicate device and subject device are indicated for semi-automated measurements of anatomical (musculoskeletal) structures on ultrasound image data acquired by the Clarius Ultrasound Scanner using AI/ML-based technology. Both devices detect the anatomical structure, perform segmentation, and perform measurements of the structure. Both the predicate and subject devices are intended for use as an adjunctive 'tool' or aid by the user for the segmentation and anatomical measurements of |
Page 9
| Criteria | SUBJECT DEVICE | PREDICATE DEVICE | RATIONALE
(if subject device differs from predicate device) |
|---------|----------------|------------------|-------------------------------------------------------------|
| | judgment. Clarius Median Nerve Al is indicated for use in adult patients only. | | ultrasound images and are not intended to replace clinical decision-making. The minor differences in the indications for use do not impact the safety and effectiveness of the subject device relative to the predicate device. |
| Radiological application/ Supported modality | Ultrasound | Ultrasound | Same as predicate device. |
| Principle of Operation/ Technology | Ultrasound image processing software implementing artificial intelligence utilizing non-adaptive machine learning algorithms trained with clinical and/or artificial data intended for segmentation and measurements of ultrasound data. | Ultrasound image processing software implementing artificial intelligence utilizing non-adaptive machine learning algorithms trained with clinical and/or artificial data intended for segmentation and measurements of ultrasound data. | Same as predicate device. |
| Quantitative and/or Qualitative Analysis | Median nerve cross-sectional area measurement | Tendon thickness measurement | Equivalent to the predicate device. The subject device performs semi-automated measurements of the median nerve cross-sectional area, whereas the predicate device performs semi-automated measurements of tendon thickness. |
| Segmentation | Yes – Segmentation of anatomical structures (median nerve) | Yes – Segmentation of anatomical structures (tendons) | Equivalent to the predicate device. The only difference is the anatomical structure (median nerve vs. tendons). |
| Measurement | Yes – Measurement of anatomical structures (median nerve cross-sectional area) | Yes – Measurement of anatomical structures (tendon thickness of | Equivalent to the predicate device. The only difference is the anatomical structure (median nerve vs. tendons). |
Page 10
| Criteria | SUBJECT DEVICE | PREDICATE DEVICE | RATIONALE
(if subject device differs from predicate device) |
|---------|----------------|------------------|-------------------------------------------------------------|
| | | the Achilles' tendon, plantar fascia, patellar tendon) | |
| Algorithm Methodology | Artificial Intelligence (AI)/Machine Learning (ML)
Image segmentation for border detection, and median nerve view classification using a Deep Neural Network. | Artificial Intelligence (AI)/Machine Learning (ML)
Image segmentation for border detection, and tendon view classification using a Deep Neural Network. | Same as predicate device. |
| Automation
(Yes or No) | Yes | Yes | Same as predicate device. |
| Manual adjustment/Manual editing capability
(Yes or No) | Yes | Yes | Same as predicate device. |
| Environment of Use | Healthcare setting (e.g., hospital, clinic) | Healthcare setting (e.g., hospital, clinic) | Same as predicate device. |
| Anatomical Site | Wrist, forearm | Foot, ankle, knee | The difference in anatomical site does not impact the safety and effectiveness of the subject device relative to the predicate device. |
| Intended Users | Licensed healthcare professionals | Licensed healthcare professionals | Same as predicate device. |
| Patient Population | Adults | Adults | Same as reference device. |
| Operating System Compatibility | iOS and Android | iOS and Android | Same as predicate device. |
| Platform | Embedded in the Clarius ultrasound app for use with the Clarius Ultrasound Scanner system | Embedded in the Clarius ultrasound app for use with the Clarius Ultrasound Scanner system | Same as predicate device. |
Page 11
Non-Clinical Performance Testing Summary
Clarius Median Nerve AI was designed and developed by Clarius Mobile Health Corp. in accordance with the applicable requirements, design controls, and standards to establish safety and effectiveness of the device.
Non-clinical performance testing has demonstrated that Clarius Median Nerve AI complies with the following FDA-recognized consensus standards:
| Standard Recognition Number | Title of Standard |
|---|---|
| 13-79 | IEC 62304:2006 + A1:2015 - Medical device software — Software life cycle processes |
| 5-125 | ISO 14971:2019 Medical devices — Application of risk management to medical devices |
| 12-349 | NEMA PS 3.1 - 3.20 (2022d) Digital Imaging and Communications in Medicine (DICOM) Set |
| 5-129 | IEC 62366-1:2015 + A1:2020 Medical devices — Part 1: Application of usability engineering to medical devices |
| 5-134 | ISO 15223-1:2021 Medical devices — Symbols to be used with medical device labels, labelling and information to be supplied |
Safety and performance of Clarius Median Nerve AI have been evaluated through verification and validation testing in accordance with applicable specifications, acceptance criteria, and performance standards. The traceability analysis provides traceability between the requirement specifications, design specifications, risks, and verification testing of the subject device. All requirements and risk controls have been successfully verified and traced. A comprehensive risk analysis was performed for the subject device and appropriate risk controls have been implemented to mitigate hazards.
Software verification and validation activities were conducted in accordance with IEC 62304:2006 + AMD1:2015 – Medical device software – Software lifecycle processes and ISO 14971:2019 Medical devices – Application of risk management to medical devices, and in accordance with relevant FDA guidance documents, General Principles of Software Validation, Final Guidance for Industry and FDA Staff (issued January 11, 2002), Guidance for the Content of Premarket Submissions for Device Software Functions (issued June 14, 2023), and Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions (issued September 27, 2023).
Cybersecurity and vulnerability analyses were conducted, and it has been determined that Clarius conforms to the cybersecurity requirements by implementing a process of preventing unauthorized access, modifications, misuse or denial of use, or the unauthorized use of information that is stored, accessed or transferred from a medical device to an external recipient.
The following processes were followed and applied during the design and development of Clarius Median Nerve AI:
• Risk Analysis
• Design Reviews
• Integration Testing
• System Testing
• Performance Testing
• Usability Engineering
Page 12
• Software Verification & Validation
• Cybersecurity Analysis
Clarius Median Nerve AI was tested and was found to be safe and effective for the intended use, intended users, intended patient population, and use environments, as demonstrated through verification and validation testing evaluating its clinical usage and performance. Validation testing was performed to ensure that the final product meets the requirements for the specified clinical application and performs as intended to meet users' needs, while demonstrating substantial equivalence to the predicate device.
Clinical Performance Evaluation Summary
Following the completion of Clarius Median Nerve AI model development (i.e., training, tuning (validation), and internal testing), which was intended to create a documented baseline of the AI model, clinical verification testing and clinical design validation were performed to evaluate its clinical performance. Data used for model development was collected from the Clarius Cloud and/or partner clinics and was partitioned by unique anonymous patient identifiers to ensure there was no data overlap between the training, internal testing, and clinical verification datasets.
As part of the truthing process, Clarius only included data from the institutions/clinical sites that were not represented in the data used for algorithmic development of the Clarius Median Nerve AI model (i.e., training, tuning, and internal testing data) to prevent data leakage. The exclusion criteria used were that images of inadequate quality were not added to the sample size (non-diagnostic images with artifacts obstructing specific anatomy) and images with incomplete anatomy and views. In measurement comparisons, Clarius excluded the subjects where the Median Nerve AI model failed to generate a measurement since there was no value to compare. To aggregate measurements from different truthers, the mean of the three values was taken and was treated as one reviewer mean. No clinical information was provided to the clinicians regarding patients utilized in the clinical truthing process. The clinicians only had access to the ultrasound image for identifying the anatomy, segmenting the median nerve, and performing measurements by placing the calipers. The lighting and monitor size/resolution were operator-dependent using their clinical judgement. The truthing process was not based on any follow-up medical examination.
The clinical performance of Clarius Median Nerve AI was evaluated through a retrospective analysis of anonymized ultrasound images obtained from multiple clinical sites predominantly from the United States, representing different ethnic groups, genders, and ages. The clinical verification data to evaluate the clinical performance of Clarius Median Nerve AI was entirely independent from the training, tuning (validation) and internal testing datasets used in the development of the AI model.
The Clarius Median Nerve AI Deep Neural Network (DNN) model was developed and trained using three data sets: training, tuning, and internal testing. The DNN parameters and weights were updated on the training data and evaluated on the validation (tuning) data at each epoch. Once the AI model was fully trained, its generalizability was tested by evaluating it on the internal testing dataset (internal testing prior to clinical (external) verification). The internal test data was fully independent of the training/tuning dataset and was labelled by experts. Then, following internal testing, a single model was selected, and a completely separate test dataset was used for performance testing of the AI model (clinical verification). This verification dataset was independent of the training/tuning, and internal testing datasets, in order to ensure robust results.
The objective of clinical performance testing was to verify that Clarius Median Nerve AI auto-measurements are non-inferior to manual measurements performed by qualified experts with relevant (i.e., musculoskeletal) ultrasound experience.
Page 13
Summary of the Clinical Verification Study
Ultrasound images were randomly obtained from an anonymized multi-center database of images from the United States, Canada, Brazil, United Kingdom, Australia, Belgium, Germany, South Africa, Dominican Republic, Poland, The Netherlands, and Philippines, representing various ethnicities, genders, and ages of the subjects. The verification study was conducted using de-identified ultrasound data previously collected and stored on a cloud platform. No clinical or sociodemographic information—such as age, gender, or clinical diagnosis—was available or accessible at any point during the study. This data was fully anonymized prior to Clarius' access and use, in accordance with applicable privacy laws and ethical guidelines. Institutions included in the Clarius Median Nerve AI model development (i.e., training, tuning, and internal testing datasets) were excluded from this study. Images of the median nerve were collected and the total sample size included in the study was 182 images collected from 126 subjects, with the majority representing patients from the United States. The images collected were cross sectional (transverse view) images on the median nerve at the level of the forearm and wrist. Some subjects had images collected at both levels (forearm and wrist), which accounts for the 182 images collected from 126 subjects. The geographic distribution of data collected is shown in Table 1:
Table 1: Geographic Data
| Location | Number of Images |
|---|---|
| United States | 130 |
| Brazil | 13 |
| Canada | 10 |
| Australia | 9 |
| Belgium | 4 |
| unknown | 4 |
| Germany | 3 |
| United Kingdom | 3 |
| South Africa | 2 |
| Dominican Republic | 1 |
| Philippines | 1 |
| Poland | 1 |
| The Netherlands | 1 |
| Total | 182 |
The primary objective of the retrospective verification study was to determine whether Clarius Median Nerve AI measurements are non-inferior to those obtained manually by human experts/qualified ultrasound users (if the magnitude of the difference (the absolute difference/error) between Clarius Median Nerve AI and mean reviewer (human expert) measurements is greater than the magnitude of the mean difference (mean absolute difference/error) between the reviewers themselves). The secondary objective was to determine the correlation between Clarius Median Nerve AI segmentation and those of human experts, whether it can accurately identify the median nerve in transverse view at the level of the wrist or mid forearm.
Page 14
Each reviewer was blinded to the Clarius Median Nerve AI output and the other reviewers' annotations as well. All ultrasound exams were captured using Clarius' 510(k)-cleared linear-array ultrasound scanners.
An assessment of the magnitude of the difference between Clarius Median Nerve AI and human experts' median nerve cross-sectional area (CSA) measurements was performed to ascertain whether Clarius Median Nerve AI measurement is non-inferior to those of human experts/ qualified ultrasound users.
The absolute difference between reviewer pairs was calculated and compared to the absolute difference between the Clarius Median Nerve AI measurement and mean reviewer measurement using a one-sided t-test and an equivalence/error margin of 3 mm². The automatic median nerve CSA measurement was found to be non-inferior (p value of 6.497e-47 (97.5% CI: -inf, 0.3285)). The mean difference between the differences among human experts and Clarius Median Nerve AI was –0.065 mm². The Intraclass Correlation Coefficient (ICC) of the Clarius Median Nerve AI versus the Mean of Reviewers cross sectional area is 0.81 (95% CI: 0.74, 0.87).
The non-inferiority performance testing summary is shown in Table 2:
Table 2: Non-Inferiority Test Result Summary for Clinical Performance of Clarius Median Nerve AI
| p-value | Equivalence Margin | Mean Difference | |
|---|---|---|---|
| Clarius Median Nerve AI vs Human Experts | 6.497e-47 (97.5% CI: -inf, 0.3285) | 3 mm² | -0.065 mm² |
The Jaccard scores were calculated between the segmentation mask provided by Clarius Median Nerve AI and a trace from the expert reviewers, as well as the reviewers against each other. Table 3 presents the results:
Table 3: Jaccard Scores of Segmentation masks
| Comparison | Jaccard Score |
|---|---|
| Reviewer 1 vs Clarius Median Nerve AI | 0.62 [95%CI: 0.62, 0.68] |
| Reviewer 2 vs Clarius Median Nerve AI | 0.71 [95%CI: 0.69, 0.74] |
| Reviewer 3 vs Clarius Median Nerve AI | 0.68 [95%CI: 0.65, 0.71] |
| Reviewer 1 vs Reviewer 2 | 0.76 [95%CI: 0.74, 0.78] |
| Reviewer 1 vs Reviewer 3 | 0.72 [95%CI: 0.70, 0.75] |
| Reviewer 2 vs Reviewer 3 | 0.77 [95%CI: 0.75, 0.79] |
Bland-Altman plots indicated strong agreement between Clarius Median Nerve AI and human expert measurements. The ICC scores for different probe models (i.e., L7 HD3, L15 HD3, L20 HD3) demonstrated reliability.
The results of the clinical verification study (retrospective analysis) evaluating the performance of Clarius Median Nerve AI have demonstrated that Clarius Median Nerve AI's performance is non-inferior to that of experienced ultrasound reviewers/clinicians for measurement of the cross-sectional area of the median nerve, thus meeting the primary objective of the study. Furthermore, the study validated Clarius Median Nerve AI's accuracy in identifying median nerve views.
Page 15
Therefore, the clinical performance of Clarius Median Nerve AI has been adequately verified for median nerve cross-sectional area measurements and has been determined to be as reliable and accurate as compared to human clinical experts.
Summary of the Clinical Validation Study
A clinical validation study was conducted to evaluate the design and clinical usage of Clarius Median Nerve AI, as it is integrated into the Clarius App software, to determine if it performs as intended in a representative user environment, meets the product requirements, is clinically usable, and meets users' needs for use in semi-automated measurements of the median nerve cross-sectional area. Testing was performed using production equivalent units in a simulated use environment.
The results of the clinical validation study showed consistent results among all users, meeting the pre-defined acceptance criteria. The users were able to activate Clarius Median Nerve AI using Clarius' linear-array ultrasound scanners (L7 HD3, L15 HD3, L20 HD3), image the median nerve, perform live segmentation, perform automated measurements of the median nerve, manually adjust the measurements, change the segmentation mask opacity, calculate and display the median nerve cross-sectional area, and save the measurement with each exam.
Therefore, based on the results of the clinical validation study it has been determined that Clarius Median Nerve AI performs as intended and meets user needs for use in semi-automated median nerve measurements in musculoskeletal ultrasound applications.
Predetermined Change Control Plan (PCCP)
Clarius Median Nerve AI uses a machine learning (ML) algorithm for measurement of the median nerve cross-sectional area on ultrasound image data acquired by the Clarius Ultrasound Scanner.
Modifications to Clarius Median Nerve AI will be made in accordance with its Predetermined Change Control Plan (PCCP). The PCCP provides a description of the device's planned modifications, a modification protocol to test, verify, validate, and implement the modifications in a manner that ensures the continued safety and effectiveness of the device, mitigating risks associated with changes to the Median Nerve AI model to not adversely impact the device's performance, safety, or effectiveness associated with its indications for use, and an impact assessment of the planned modifications.
The modifications outlined in the PCCP are summarized in the table below. In accordance with the PCCP, the modified Clarius Median Nerve AI algorithm will be adequately trained, tuned, tested, and locked before release of the modified Median Nerve AI model. Implemented modifications to the Clarius Median Nerve AI algorithm will be communicated to users via the Clarius App software update notification and through updated labelling.
Summary of planned modifications to Clarius Median Nerve AI per the PCCP:
| Modification | Rationale | Testing Methods | Impact Assessment |
|---|---|---|---|
| Modification of training hyperparameters (initial learning rate, width multiplier, dropout rate) | Improvement and optimization of Clarius Median Nerve AI's performance | Re-training of the Median Nerve AI model with modified hyperparameters to optimize its performance | Improved performance metrics of modified Median Nerve AI model with |
Page 16
| Modification | Rationale | Testing Methods | Impact Assessment |
|---|---|---|---|
| followed by internal testing and a comparison of the original Median Nerve AI model to the modified Median Nerve AI model (using performance metrics) followed with clinical performance testing (verification and validation). | increased accuracy and more robust measurements displayed to users. |
Benefit-Risk Analysis:
Benefits: Improved performance; generalization.
Risks: Overfitting; unintended bias.
Risk Mitigation:
Proper regularization techniques and cross-validation and dropout will be employed to mitigate overfitting. Internal testing and verification will be conducted to mitigate unintended biases. |
| Modification of post-processing algorithms (adjustments to measurement validity thresholds) | Improvement and optimization of Clarius Median Nerve AI's performance and robustness | Internal testing and a comparison of the original Median Nerve AI model to the modified Median Nerve AI model (using performance metrics) and clinical performance testing (verification and validation). | Improved performance metrics of modified Median Nerve AI model.
Benefit-Risk Analysis:
Benefits: Improved performance; generalization.
Risks: Overfitting; unintended bias.
Risk Mitigation:
Proper regularization techniques and cross-validation and |
Page 17
| Modification | Rationale | Testing Methods | Impact Assessment |
|---|---|---|---|
| dropout will be employed to mitigate overfitting. Internal testing and verification will be conducted to mitigate unintended biases. | |||
| Modification of data input sources (Clarius probes) | To add data from current Clarius scanners and future 510(k) cleared scanners to the Clarius Median Nerve AI model so the model can be deployed on more scanners. | Re-training of the Median Nerve AI model to expand its use with additional data input sources (i.e., 510(k)-cleared models of the Clarius Ultrasound Scanner), internal testing, and clinical performance testing (verification and validation) to assesses its performance with the new data input sources. | By accommodating a wider array of image geometries and characteristics with the use of new 510(k)-cleared Clarius ultrasound scanners, the updated Median Nerve AI model will be better equipped to handle different transducer models of the Clarius Ultrasound Scanner used in varying clinical scenarios. |
Benefit-Risk Analysis:
Benefits: Enhanced compatibility; Flexibility for diverse clinical settings.
Risks: Data skewing and concept drift.
Risk Mitigation:
Internal testing and verification datasets within the intended patient population will ensure that data skewing and concept drift are mitigated. |
Page 18
Conclusion & Summary of Substantial Equivalence
Based on the information presented in this Traditional 510(k) premarket notification and based on the fundamental scientific technology utilizing artificial intelligence/machine learning algorithms, technological characteristics, principle of operation, intended use, intended patient population, and environment of use, Clarius Median Nerve AI has been determined to be substantially equivalent in terms of safety and effectiveness to the legally marketed predicate device, Clarius AI.
The subject device and the predicate device employ radiological (ultrasound) image processing software applications which implement artificial intelligence/machine learning algorithms trained with clinical and/or artificial data intended for analysis of ultrasound data acquired by the Clarius Ultrasound Scanner, utilizing very similar machine-learning algorithms for detection, segmentation, and measurement of musculoskeletal structures.
Performance testing of Clarius Median Nerve AI, including the results from clinical verification and validation studies, has demonstrated that Clarius Median Nerve AI measurement output adequately aligns with expert clinicians' manual measurements, and thereby performs as intended for use in semi-automated median nerve measurements.
Any differences in the indications for use or technological characteristics between the subject device and the legally marketed predicate device do not raise any issues related to safety or effectiveness. Therefore, Clarius Median Nerve AI is as safe and effective as the predicate device, Clarius AI (K222406), and therefore substantially equivalent.