Search Results

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.

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.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance document for Clarius Median Nerve AI:

Acceptance Criteria and Device Performance

1. A table of acceptance criteria and the reported device performance:

Equivalence/error margin: 3 mm² | Non-inferiority demonstrated: |
| Clinical Performance - Cross-sectional Area (CSA) Measurement | p-value for non-inferiority

Ask a specific question about this device

Clarius Prostate AI is intended for semi-automatic measurements of prostate volume on ultrasound data acquired by the Clarius Ultrasound Scanner (i.e., curvilinear and endo-cavitary 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 Prostate AI is intended for use in adult male patients only.

Clarius Prostate AI is a machine learning algorithm that is integrated into the Clarius App software as part of the comprehensive Clarius Ultrasound Scanner system for use in prostate ultrasound imaging applications. Clarius Prostate AI is intended for use by trained healthcare practitioners for measurement of prostate volume on ultrasound data acquired by the Clarius Ultrasound Scanner system (i.e., curvilinear and endo-cavitary 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., Prostate) from the Clarius App in which Clarius Prostate AI will engage to segment the prostate gland and place calipers for measurement of prostate volume.

Clarius Prostate AI operates by performing the following tasks:

• Automatic detection and measurement of prostate length
• Automatic detection and measurement of prostate width
• Automatic detection and measurement of prostate height
• Automatic detection of the corresponding image view

Clarius Prostate AI operates by performing automatic measurements of prostate height, width, and length, and calculates prostate volume. The user has the option to manually adjust the measurements made by Clarius Prostate AI by moving the caliper crosshairs. Clarius Prostate AI does not perform any functions that could not be accomplished manually by a trained and qualified user. Clarius Prostate AI is intended for use in B-Mode only.

Clarius Prostate 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 Prostate AI is indicated for use in adult male patients only.

Clarius Prostate 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 Prostate AI is not a stand-alone software device.

Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance letter for Clarius Prostate AI:

Clarius Prostate AI: Acceptance Criteria and Study Details

1. Table of Acceptance Criteria and Reported Device Performance

The primary acceptance criterion for Clarius Prostate AI's performance was its non-inferiority to manual measurements performed by qualified experts in prostate volume measurement.

2. Sample Size and Data Provenance for the Test Set

• Sample Size: 139 subjects.
• Data Provenance: Retrospective analysis of anonymized ultrasound images obtained from multiple clinical sites in the United States, Canada, Peru, United Kingdom, Germany, Argentina, Jamaica, Barbados, Greece, Bulgaria, and Italy. The patient data was predominantly from US-based institutions, representing different ethnic groups and ages. Institutions included in the Clarius Prostate AI model training, tuning, and internal testing datasets were explicitly excluded from this study to ensure independence.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: The document refers to "qualified experts with relevant (i.e., Prostate) ultrasound experience" and "experienced ultrasound reviewers/clinicians." However, the exact number of experts used to establish ground truth for the test set is not specified in the provided text.
• Qualifications: "Qualified experts with relevant (i.e., Prostate) ultrasound experience" and "experienced ultrasound reviewers/clinicians." Specific details like their specialty (e.g., radiologist, urologist), years of experience, or board certifications are not provided.

4. Adjudication Method for the Test Set

The adjudication method used for the test set is not explicitly stated. It mentions that "the absolute percent (%) difference between reviewer pairs was calculated" and that "Each reviewer was blinded to the Clarius Prostate AI output and the other reviewers' annotations as well." This suggests a comparison between individual expert measurements and the AI, and potentially among experts, but not a formal adjudication process like 2+1 or 3+1 to establish a single adjudicated ground truth for each case.

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

There is no mention of a formal Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance. The study described focuses on the standalone performance of the AI in comparison to human expert manual measurements.

6. Standalone (Algorithm Only) Performance

Yes, a standalone performance evaluation of the algorithm (Clarius Prostate AI without human-in-the-loop assistance) was conducted. The primary and secondary objectives described in the "Summary of the Clinical Verification Study" section directly evaluate the Clarius Prostate AI's automated measurements against human expert manual measurements. The device is primarily described as an "assistive tool" and performs "semi-automatic measurements," but the clinical verification study specifically assesses the automated output of the AI model.

7. Type of Ground Truth Used

The ground truth used for the clinical verification study was expert consensus/manual measurements. The study compared the AI's measurements to "manual measurements performed by qualified experts with relevant (i.e., Prostate) ultrasound experience."

8. Sample Size for the Training Set

The document states that the Clarius Prostate AI Deep Neural Network (DNN) model was developed and trained using "three data sets: training, tuning, and testing." It specifies that the clinical verification data was "entirely independent from the training, tuning (validation) and internal testing datasets." However, the sample size for the training set is not explicitly provided in the given text.

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

The document states that the "DNN parameters and weights were updated based on the validation (tuning) data at each epoch" and that the "The test data was fully independent and labelled by experts." While it implies expert labeling for the test data, the exact method for establishing ground truth for the training set is not explicitly detailed. It generally states "using a deep learning image segmentation algorithm" and "trained with clinical and/or artificial data," but specific details on how the labels for the training data were generated (e.g., number of annotators, their qualifications, or adjudication) are not provided.

Ask a specific question about this device

Clarius OB Al is intended to assist in measurements of fetal biometric parameters (i.e., head circumference, abdominal circumference, femur length, bi-parietal diameter, crown rump length) on ultrasound data acquired by the Clarius Ultrasound Scanner (i.e., curvilinear scanner). 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 OB Al is indicated for use in adult patients only.

Clarius OB Al is a machine learning algorithm that is incorporated into the Clarius App software as part of the complete Clarius Ultrasound Scanner system for use in obstetric (OB) ultrasound imaging applications. Clarius OB Al is intended for use by trained healthcare practitioners for non-invasive measurements of fetal biometric parameters on ultrasound data acquired by the Clarius Ultrasound Scanner system (i.e., curvilinear scanner) using a deep learning image segmentation algorithm.

During the ultrasound imaging procedure, the anatomical site is selected through a preset software selection (i.e., OB, Early OB) within the Clarius App in which Clarius OB Al will engage to segment the fetal anatomy and place calipers for measurement of fetal biometric parameters.

Clarius OB Al operates by performing the following tasks:

• Automatic detection and measurement of head circumference (HC)
• Automatic detection and measurement of abdominal circumference (AC)
• Automatic detection and measurement of femur length (FL)
• Automatic detection and measurement of bi-parietal diameter (BPD)
• Automatic detection and measurement of crown rump length (CRL)

Clarius OB Al operates by performing automatic measurements of fetal biometric parameters. The user has the option to manually adjust the measurements made by Clarius OB Al by moving the caliper crosshairs. Clarius OB Al does not perform any functions that could not be accomplished manually by a trained and qualified user. Clarius OB AI is intended for use in B-Mode only.

Clarius OB Al is an assistive tool intended to inform clinical management and is not intended to replace The clinician retains the ultimate responsibility of ascertaining the clinical decision-making. measurements based on standard practices and clinical judgment. Clarius OB Al is indicated for use in adult patients only.

Clarius OB Al is incorporated 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 transducer (previously 510(k)-cleared in K213436). Clarius OB Al is not a stand-alone software device.

Here's a summary of the acceptance criteria and study details for the Clarius OB AI device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

Clarius Bladder AI is intended for semi-automatic non-invasive measurements of bladder volume on ultrasound data acquired by the Clarius Ultrasound Scanner (i.e., curvilinear and phased array scanners). The user shall be a healthcare professional trained and qualified in ultrasound. The ultimate responsibility of ascertaining the measurements based on standard practices and clinical judgment. Clarius Bladder AI is indicated for use in adult patients only.

Clarius Bladder AI is a radiological (ultrasound) image processing software application which implements artificial intelligence (Al), utilizing non-adaptive machine learning algorithms, and is incorporated into the Clarius App software for use as part of the complete Clarius Ultrasound Scanner system product offering in bladder ultrasound imaging applications. Clarius Bladder Al is intended for use by trained healthcare practitioners for non-invasive measurements of bladder volume on ultrasound data acquired by the Clarius Ultrasound Scanner system (i.e., curvilinear and phased array scanners) using an artificial intelligence (AI) image segmentation algorithm.

During the ultrasound imaging procedure, the anatomical site (bladder) is selected through a preset software selection (i.e., bladder) within the Clarius App in which Clarius Bladder Al will engage to segment the bladder and place calipers for calculation of bladder volume.

Clarius Bladder Al operates by performing the following automations:

• . Automatic detection and measurement of bladder depth
• . Automatic detection and measurement of bladder width
• . Automatic detection and measurement of bladder height
• . Automatic detection of the corresponding image view (sagittal vs. transverse)

Clarius Bladder Al operates by performing automatic measurements of bladder height, width, and length, and calculates bladder volume. The user has the option to manually adjust the measurements made by Clarius Bladder Al by moving the caliper crosshairs. Clarius Bladder Al does not perform any functions that could not be accomplished manually by a trained and qualified user. Clarius Bladder Al is intended for use in B-Mode only.

Clarius Bladder 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 Bladder Al is indicated for use in adult patients only.

Clarius Bladder AI is incorporated 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 Bladder Al is not a stand-alone software device.

Here's a breakdown of the acceptance criteria and the study details for the Clarius Bladder AI device, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The core acceptance criterion for Clarius Bladder AI's automated measurements was non-inferiority to manual measurements performed by qualified experts, with an equivalence margin of 25% for the mean difference between percentage differences of bladder volume measurements.

Prospective Study: p-value of 1.36e-14 (confirming non-inferiority). Mean difference between percent differences of clinical expert mean and Bladder AI mean was -0.0228 (95% CI -0.074, 0.028). |
| Agreement with Experts: Strong agreement between Clarius Bladder AI measurements and the mean of expert clinicians' measurements, and with individual expert measurements. | Both retrospective and prospective studies reported strong agreement between Clarius Bladder AI and expert measurements, as well as high inter-rater reliability (Intraclass Correlation Coefficients for inter-rater reliability were calculated and found to be strong). Average Dice scores and Jaccard index were also calculated, indicating good segmentation agreement. |
| Clinical Usability: Performs as intended in a representative user environment, meets product requirements, is clinically usable, and meets user needs for semi-automated bladder volume measurements. | Clinical validation study results showed consistent results among all users, meeting pre-defined acceptance criteria, demonstrating that Clarius Bladder AI performs as intended and meets user needs. Users were able to activate, image, perform live segmentation, automatic measurements, manual adjustments, and save measurements. |

2. Sample Size and Data Provenance for Test Set

Retrospective Study:

• Sample Size: 66 subjects (10 female, 38 male, gender of remaining unknown)
• Data Provenance: Anonymized multi-center database of images from predominantly the United States. Institutions included in the model training and tuning datasets were excluded from this study. Retrospective.

Prospective Study:

• Sample Size: 58 subjects (40 female, 18 male)
• Data Provenance: Conducted at a healthcare institution in the United States. Images were obtained prospectively.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: 3 reviewers (referred to as "clinical truthers" or "clinical experts") for both the retrospective and prospective studies.
• Qualifications of Experts: Described as "qualified experts with relevant (i.e., bladder) ultrasound experience."
  • For the retrospective study: "qualified experts with relevant (i.e., bladder) ultrasound experience."
  • For the prospective study: "qualified experts with clinical experience in bladder ultrasound."

4. Adjudication Method for the Test Set

The ground truth for bladder volume in both retrospective and prospective studies was established as the mean bladder volume measurement among the three clinical experts. Each reviewer was blinded to the Clarius Bladder AI output and the other reviewers' annotations.

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

The provided information does not explicitly describe a traditional MRMC comparative effectiveness study designed to measure the effect size of human readers improving with AI vs. without AI assistance.

Instead, the studies focused on demonstrating the non-inferiority of the AI device's standalone measurements compared to the mean of multiple human expert measurements. While comparisons were made between reviewer pairs (inter-rater reliability), and between the AI output and individual/mean expert measurements, the studies did not seem to directly evaluate human performance with the AI assistance versus human performance without it in a controlled MRMC setting to quantify a "human improvement" effect size.

6. Standalone Performance Study (Algorithm Only)

Yes, a standalone (algorithm only) performance study was done. The core of both the retrospective and prospective verification studies was to evaluate the Clarius Bladder AI's automated measurements directly against expert manual measurements, demonstrating its performance without human intervention (other than initial image acquisition and potential later manual adjustment by the user, which was a separate feature). The non-inferiority claims are based on this standalone performance.

7. Type of Ground Truth Used

The ground truth used was expert consensus, specifically defined as the mean bladder volume measurement among three clinical experts.

8. Sample Size for the Training Set

• Training Dataset: 1352 subjects (353 female, 999 male).
  • Note: This also includes a validation (tuning) dataset which was 10% of the training data.

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

The deep neural network (DNN) model was trained using the raw training dataset. The summary states that the test data (which was independent) was "labelled by experts." While it doesn't explicitly detail the ground truth establishment for the training set itself, it can be inferred that similar expert labeling or a robust annotation process would have been used to generate the ground truth for the images used in training. The summary highlights that the validation (tuning) data was independent, and the test data was "labelled by experts," suggesting expert annotation for ground truth across relevant datasets. The overall context points to expert-derived ground truth for model development.

Ask a specific question about this device

The Clarius Ultrasound Scanner is a software-based ultrasound imaging system and accessories, intended for diagnostic imaging. It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: ophthalmic, fetal, abdominal, intra-operative (non-neurological), pediatric, small organ, cephalic (adult), trans-rectal, trans-vaginal, musculo-skeletal (conventional, superficial), urology, cardiac (adult, pediatric), peripheral vessel, carotid, and procedural guidance of needles into the body.

The system is a transportable ultrasound system intended for use in environments where is provided by trained healthcare professionals.

The Clarius Ultrasound Scanner is a portable, general-purpose, software-controlled, diagnostic ultrasound system used to acquire and display high-resolution, real-time ultrasound data through an off-the-shelf (OTS) iOS or Android device. The Clarius Ultrasound Scanner comprises a series of wireless transducers employing Bluetooth and Wi-Fi-based technology to communicate with traditional tablet/smartphone devices via direct Wi-Fi. This allows the user to export ultrasound images and display them across a range of portable personal devices.

The Clarius Ultrasound Scanner system is a transportable ultrasound system intended for use in environments where healthcare is provided by trained healthcare professionals, including the emergency medical services (EMS) environment. The Clarius Ultrasound Scanner is intended for use by qualified healthcare practitioners (e.g., doctors, nurses, sonographers) who are trained in the use of ultrasound imaging technology.

The Clarius Scanner PAL HD3 ("PAL HD3") (subject device of this 510(k) premarket notification) is a multipurpose dual-array transducer that incorporates high-frequency linear array (equivalent to the L15 HD3 transducer cleared under K213436)) and low-frequency phased array (equivalent to the PA HD3 transducer cleared under K213436) ultrasound functionalities where the two separate transducer ceramics are arranged side-by-side within the same transducer model (PAL HD3). The Clarius Scanner PAL HD3 is a new Clarius HD3 transducer variant introduced into the HD3 product line of the Clarius Ultrasound Scanner device family and represents a design modification to the existing PA HD3 transducer of the Clarius Ultrasound Scanner system, which was most recently 510(k)-cleared under K213436.

The Clarius Scanner PAL HD3 has two separate transducer ceramics positioned side-by-side which consist of the linear array and the phased array. The Clarius Scanner PAL HD3 offers a wide frequency range of 1 – 15 MHz within a single transducer. The body and electronics of the PAL HD3 scanner are identical to the currently released HD3 scanner models (the PA HD3 and the L15 HD3) of the Clarius Ultrasound Scanner device family (cleared under K213436); the main difference is in the scanner head. The Clarius Scanner PAL HD3 will allow clinicians to switch between the phased array and the linear array without having to use two separate scanners during exams and procedures.

The Clarius Ultrasound Scanner, subject of this 510(k) premarket notification, comprises the following:
Transducer/ Scanner: PAL HD3
Software: Clarius Ultrasound App (Clarius App) for iOS; Clarius Ultrasound App (Clarius App) for Android
Accessories: Clarius Charger HD3; Clarius Power Fan HD3

The provided document, a 510(k) Premarket Notification from the FDA to Clarius Mobile Health Corp., does not contain any information about acceptance criteria or a study that proves the device meets specific performance criteria.

Instead, it is a clearance letter from the FDA stating that the new device, the Clarius Ultrasound Scanner with the PAL HD3 transducer, has been found "substantially equivalent" to a previously marketed predicate device (K213436). The document explicitly states:

"The Clarius Ultrasound Scanner (PAL HD3 transducer model) did not require clinical studies to support the determination of substantial equivalence."

This means that a detailed clinical performance study with defined acceptance criteria, test sets, expert adjudication, or MRMC studies, as requested in your prompt, was not performed or submitted for this specific 510(k) clearance due to the nature of the "substantial equivalence" determination for this device modification.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance: No such data is present.
2. Sample size used for the test set and data provenance: No test set described.
3. Number of experts and qualifications for ground truthing: No ground truthing process described.
4. Adjudication method for the test set: No adjudication described.
5. MRMC comparative effectiveness study results: No such study was done.
6. Standalone (algorithm only) performance: This device is an ultrasound scanner, not an AI algorithm.
7. Type of ground truth used: No ground truth used as no clinical study was performed.
8. Sample size for the training set: Not applicable as this is not an AI/ML device requiring a training set in the context of clinical performance.
9. How ground truth for the training set was established: Not applicable.

The document focuses on demonstrating substantial equivalence through:

• Comparison of Indications for Use: The new device has the same indications for use as the predicate.
• Comparison of Technological Characteristics: The new device (PAL HD3) combines two transducer types (phased array and linear array) that were already present in separate models of the predicate device (PA HD3 and L15 HD3). The body and electronics are identical.
• Compliance with Recognized Standards: The device underwent non-clinical performance testing to demonstrate compliance with relevant safety and performance standards (e.g., IEC 60601 series, ISO 14971) indicating electrical safety, EMC, usability, and acoustic output.

In summary, the provided text explains why a detailed clinical performance study with acceptance criteria was not required for this 510(k) clearance, rather than describing such a study.

Ask a specific question about this device

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., L 7 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 iudgment.

Clarius AI is a radiological (ultrasound) image processing software application which implements artificial intelligence (Al), including non-adaptive machine learning algorithms, and is incorporated into the Clarius App software for use as part of the complete Clarius Ultrasound Scanner system product offering in musculoskeletal (MSK) ultrasound imaging applications. Clarius Al (MSK model) is intended for use by trained healthcare practitioners for non-invasive measurements of ultrasound data from musculoskeletal (MSK) ultrasound imaging acquired by the Clarius Ultrasound Scanner system using an artificial intelligence (AI) image segmentation algorithm. Clarius AI (MSK model) is intended to semi-automatically place adjustable calipers and provide supplementary information to the user regarding tendon thickness measurements (i.e., foot/plantar fascia, ankle/Achilles' tendon, knee/patellar tendon). Clarius Al is 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 Al is indicated for use in adult patients only.

During the ultrasound imaging procedure, the anatomical site is selected through a preset software selection (e.g., foot, ankle, knee), in which the Clarius Al will engage to segment the correlating tendon. Clarius Al analyzes ultrasound images in real-time and outputs probabilities for each pixel within the image for determination of the particular tendon thickness.

The combination of all the pixels meeting a programmed threshold will render an overlay being displayed on top of the ultrasound image with a pre-programmed transparency so that the ultrasound greyscale is still visible. Once the user has obtained the best view, imaging can be manually paused, in which the Clarius Al will further analyze the tendon segmentation to determine the greatest thickness, in number of pixels, and subsequently place two measurement calipers that correspond to the top and bottom of the tendon at its thickest region, outputting a value in millimeters. The user can then manually alter the measurement calipers to make any necessary adjustments if desired. Clarius Al does not perform any functions that could not be accomplished manually by a trained and qualified user.

Clarius AI (MSK model) is incorporated into the Clarius App software and is intended for use with the following Clarius Ultrasound Scanner system transducers (previously 510(k)-cleared in K180799, K192107, and K213436):

Clarius Ultrasound Transducers: L7 and L15
Clarius App Software: Clarius Ultrasound App (Clarius App) for iOS; Clarius Ultrasound App (Clarius App) for Android

The Clarius AI device is intended for semi-automatic placement of calipers for non-invasive measurements of musculoskeletal structures (e.g., Achilles' tendon, plantar fascia, patellar tendon) on ultrasound data. The device's performance was evaluated through non-clinical and clinical testing to demonstrate its safety and effectiveness.

Here’s a breakdown of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the Clarius AI device, particularly regarding measurement accuracy, are based on achieving non-inferiority to manual measurements made by expert clinicians. The specific criterion for clinical significance was defined as a difference of greater than 20% from normal thickness measurements.

• 0.6 mm for plantar fascia
• 1 mm for patellar tendon
• 1.2 mm for Achilles' tendon. | The automatic measurement was found to be non-inferior to manual measurements within this clinically significant margin. |
  | Automatic segmentation to have a high degree of overlap with ground truth. | Average Dice score of 96% and mean IoU of 94% for tendon segmentation. |

2. Sample Sizes and Data Provenance

• Test Set (Validation Phase):

  • Sample Size: 73 subjects, resulting in a total of 2,503 ultrasound images/frames.
  • Data Provenance: Retrospective analysis of anonymized ultrasound images. Images were captured in-house from volunteer subjects and by clinical partners, mainly located in the USA. The data was anonymized and queried from Clarius Cloud storage.

• Training Set:

  • Sample Size: A total of 20,287 images.
  • Data Provenance: Images were captured in-house from volunteer subjects and by clinical partners, mainly located in the USA. The data was anonymized and queried from Clarius Cloud storage.

3. Number of Experts and Qualifications for Ground Truth - Test Set

The document mentions "expert clinicians" and "licensed clinicians with relevant (i.e., musculoskeletal) ultrasound experience" were involved in establishing the ground truth for the test set (manual measurements). However, the exact number of experts and their specific qualifications (e.g., years of experience, board certification) are not explicitly stated in the provided text. The study states "reviewer pairs" for calculating manual measurement differences, implying at least two reviewers per case for comparison.

4. Adjudication Method for the Test Set

The provided text does not explicitly detail an adjudication method (e.g., 2+1, 3+1). It states that the "difference between auto-measurements and mean manual measurements" was compared to the "mean difference between manual measurements within the clinically significant margin." This suggests that multiple manual measurements were obtained, and their mean was used for comparison, rather than a specific consensus or adjudication process described.

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

The provided text describes a verification test where "Clarius AI auto-measurements are non-inferior to manual measurements performed by licensed clinicians." While this compares AI performance against human performance, it doesn't describe a typical MRMC study designed to assess how human readers improve with AI assistance versus without AI assistance (i.e., an effect size of AI assistance on human readers). The focus was on the AI's standalone accuracy relative to human measurements.

6. Standalone Performance (Algorithm Only without Human-in-the-Loop)

Yes, a standalone performance evaluation was largely conducted for the AI algorithm. The core of the "Measurement Accuracy" testing compared the automatic thickness measurement directly against the mean manual measurements, indicating the algorithm's performance without specific human-in-the-loop assistance influencing the AI's initial output for that specific evaluation. The segmentation accuracy (Dice score and IoU) also represents standalone algorithm performance. While the AI semi-automatically places calipers and allows for manual adjustment, the non-inferiority study specifically evaluated the AI's auto-measurement against expert manual measurements.

7. Type of Ground Truth Used

• Expert Consensus / Manual Measurements: For the measurement accuracy study, the ground truth was established by "mean manual measurements performed by licensed clinicians with relevant (i.e., musculoskeletal) ultrasound experience."
• Expert Annotation (Segmentation): For the segmentation evaluation, the ground truth was described as "segmentation ground truth" where "the tendon regions in the images were annotated by a clinical scientist as the ground truth."

8. Sample Size for the Training Set

A total of 20,287 images were used for the training phase.

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

For the training phase, "the tendon regions in the images were annotated by a clinical scientist as the ground truth." This indicates that human experts (clinical scientists) manually outlined or labeled the tendon regions in the ultrasound images to create the reference data used to train the machine learning model.

Ask a specific question about this device

The Clarius Ultrasound Scanner is a software-based ultrasound imaging system and accessories, intended for diagnostic imaging. It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: ophthalmic, fetal, abdominal, intra-operative (non-neurological), pediatric, small organ, cephalic (adult), trans-rectal, trans-vaginal, musculo-skeletal (conventional, superficial), urology, gynecology, cardiac (adult, pediatric), peripheral vessel, carotid, and procedural guidance of needles into the body.

The system is a transportable ultrasound system intended for use in environments where healthcare is provided by trained healthcare professionals.

The Clarius Ultrasound Scanner is a portable, general-purpose, software-controlled, diagnostic ultrasound system used to acquire and display high-resolution, real-time ultrasound data through an off-the-shelf (OTS) iOS or Android device. The Clarius Ultrasound Scanner comprises a series of wireless transducers employing Bluetooth and Wi-Fi-based technology to communicate with traditional tablet/smartphone devices via direct Wi-Fi. This allows the user to export ultrasound images and display them across a range of portable personal devices.

The system is a transportable ultrasound system intended for use in environments where is provided by trained healthcare professionals, including the emergency medical services (EMS) environment.

The Clarius Ultrasound Scanner comprises the following:
Transducers/ Scanners (various models): C3 HD3, C7 HD3, EC7 HD3, L7 HD3, L15 HD3, PA HD3, L20 HD3
Software: Clarius Ultrasound App (Clarius App) for iOS; Clarius Ultrasound App (Clarius App) for Android
Accessories: Clarius Charger, Clarius Fan

This document does not contain information about acceptance criteria or specific study results for the Clarius Ultrasound Scanner related to diagnostic accuracy performance metrics (e.g., sensitivity, specificity, AUC).

The provided text from the FDA 510(k) summary focuses on demonstrating substantial equivalence to a predicate device by comparing:

• Intended Use and Indications for Use: These are identical between the subject and predicate devices.
• Technological Characteristics: Principle of operation, transducer types, software, modes of operation, wireless communication, and portability are similar. The only noted difference is the power source (internal integrated for the subject device vs. removable for the predicate).
• Compliance with Recognized Standards: Both devices comply with a comprehensive list of medical device safety, EMC, usability, and acoustic output standards (e.g., IEC 60601 series, ISO 10993, NEMA UD 2 & 3, IEC 62304, IEC 62366-1, ISO 14971).

The "Non-Clinical Performance Testing" section broadly states that "The device's safety and performance were verified by tests conducted by Clarius and accredited third-party laboratories. Validation testing was performed to ensure that the final product is capable of meeting the requirements for the specified clinical applications and performs as intended to meet users' needs, while demonstrating substantial equivalence to the predicate device." However, it does not provide specific acceptance criteria or quantitative performance results from these tests. These tests likely pertain to the engineering and safety standards listed, rather than diagnostic performance metrics typically associated with AI/ML devices.

Therefore, I cannot provide the requested information from the given text, particularly regarding a table of acceptance criteria and reported device performance (in terms of diagnostic accuracy), details on sample size, data provenance, expert ground truth establishment, adjudication methods, MRMC studies, or standalone algorithm performance. The device described is a general diagnostic ultrasound system, not an AI/ML-driven diagnostic aid that would typically have such performance criteria explicitly detailed in a 510(k) summary for clinical performance.

Ask a specific question about this device

The Clarius Ultrasound Scanner is a software-based ultrasound imaging system and accessories, intended for diagnostic imaging. It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: ophthalmic, fetal, abdominal, intra-operative (non-neurological), pediatric, small organ, cephalic (adult), trans-rectal, trans-vaginal, musculo-skeletal (conventional, superficial), urology, gynecology, cardiac (adult, pediatric), peripheral vessel, carotid, and procedural guidance of needles into the body.

The system is a transportable ultrasound system intended for use in environments where is provided by trained healthcare professionals.

The Clarius Ultrasound Scanner is a portable, general-purpose, software-controlled, diagnostic ultrasound system used to acquire and display high-resolution, real-time ultrasound data through an off-the-shelf (OTS) iOS or Android device. The Clarius Ultrasound Scanner comprises a series of wireless transducers employing Bluetooth and Wi-Fi-based technology to communicate with traditional tablet/smartphone devices via direct Wi-Fi. This allows the user to export ultrasound images and display them across a range of portable personal devices.

The system is a transportable ultrasound system intended for use in environments where is provided by trained healthcare professionals, including the emergency medical services (EMS) environment.

The Clarius Ultrasound Scanner is a software-based ultrasound imaging system with various transducers. The acceptance criteria and the study proving the device meets these criteria are described below.

1. Table of Acceptance Criteria and Reported Device Performance:

The reported performance of the subject device (Clarius Ultrasound Scanner) is identical to the predicate device (Clarius Ultrasound Scanner, K180799) across all listed criteria, indicating substantial equivalence.

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

The provided document does not mention a specific "test set" or its sample size for evaluating the performance of the new transducer models. The study primarily relies on demonstrating substantial equivalence to a previously cleared predicate device.

• Data Provenance: Not explicitly stated for a dedicated test set. The submission focuses on nonclinical performance data related to compliance with various international standards, rather than direct human subject testing for the new transducer models.

3. Number of Experts and Qualifications for Ground Truth:

Not applicable. The document states that "The Clarius Ultrasound Scanner did not require clinical testing to establish substantial equivalence." Therefore, no experts were used to establish ground truth for a clinical test set. The substantial equivalence argument is based on technical specifications and adherence to recognized standards.

4. Adjudication Method for the Test Set:

Not applicable, as no clinical test set requiring expert adjudication was conducted or described in the provided information.

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

No MRMC comparative effectiveness study was mentioned or performed as per the provided document. The submission focuses on comparing the new device models to a predicate device based on technical and functional equivalence.

6. Standalone Performance Study (Algorithm Only):

The document does not describe a standalone algorithm-only performance study. The "Clarius Ultrasound Scanner" is described as a comprehensive ultrasound imaging system, not a device primarily driven by an AI algorithm requiring standalone performance evaluation in the context of this submission. The device is software-based but its performance evaluation within this 510(k) submission is related to hardware compliance and functional equivalence, not AI-driven diagnostic performance that would necessitate standalone algorithm studies.

7. Type of Ground Truth Used:

Not applicable. As clinical testing was not required for substantial equivalence, no clinical ground truth (e.g., expert consensus, pathology, outcomes data) was established or used for the evaluation of the subject device in this submission. The "ground truth" for the device's capabilities is implicitly established by its adherence to recognized industry standards for medical electrical equipment and its equivalence to the predicate device’s established performance.

8. Sample Size for the Training Set:

Not applicable. The provided information relates to a 510(k) submission for new transducer models, demonstrating substantial equivalence to a predicate device. It does not mention machine learning or AI models requiring a training set for diagnostic or analytical performance.

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

Not applicable, as no training set for a machine learning or AI model was mentioned in the provided text.

Ask a specific question about this device

The Clarius Ultrasound Scanner is a software-based ultrasound imaging system and accessories, intended for diagnostic imaging. It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: ophthalmic, fetal, abdominal, intra-operative (non-neurological), pediatric, small organ, cephalic (adult), trans-rectal, trans-vaginal, musculo-skeletal (conventional, superficial), urology, gynecology, cardiac (adult, pediatric), peripheral vessel, carotid, and procedural guidance of needles into the body.

The system is a transportable ultrasound system intended for use in environments where is provided by trained healthcare professionals.

The Clarius Ultrasound Scanner is a portable, general-purpose, software-controlled, diagnostic ultrasound system used to acquire and display high-resolution, real-time ultrasound data through an off-the-shelf iOS or Android device. The Clarius Ultrasound Scanner comprises a series of wireless transducers employing Bluetooth and Wi-Fi-based technology to communicate with traditional tablet/smartphone devices via direct Wi-Fi. This allows the user to export ultrasound images and display them across a range of portable personal devices.

Piezoelectric material in the systems transmits high frequency, non-ionizing sound waves to the designated region of the body and converts the subsequent echoes detected into electronic signals in order to construct an image of the internal structures of an anatomical field. This image is sent wirelessly to an external iOS or Android viewing device on which the image can be displayed. The transducer houses a battery and power generator, multichannel beam former, pre-scan converter, and Wi-Fi components. The battery is removable and comes with a separate charger. Communication between the transducer and the compatible viewing device is performed via Wi-Fi Direct® (Ad-Hoc mode with security) for easy pairing.

The Clarius Ultrasound System product/package components include:

1. Software:
   . The Clarius Ultrasound App (Clarius App) for iOS; OR
   The Clarius Ultrasound App (Clarius App) for Android. ●
2. Transducers/Scanners:
   Clarius Scanner C3 (C3 Convex Transducer);
   . Clarius Scanner EC7 (EC7 Convex Endocavitary Transducer);
   Clarius Scanner C7 (C7 Convex Transducer); OR ●
   Clarius Scanner L7 (L7 Linear Transducer).
3. Accessories:
   a. Clarius-Built:
   o Battery Pack (Li-ion);
   Battery Charger; O
   Clarius Dock (Optional; charging station); and O
   Clarius Fan (Optional). O
   b. OEM/Off-the-Shelf Product(s):
   Medical Power Supply (Off-the-shelf power adaptor from SL Power Electronics; O Model Number ME20A1203B02; approved in the US); and
   Medical Power Supply (Optional for use with Clarius Dock; off-the-shelf power o adaptor from MEAN WELL Enterprises Co., Ltd.; Model Number GSM160B12-R7B; approved in the US).

The concept of the Clarius Ultrasound System transducers and software is to provide an easy to use, highperformance, low-cost, ultrasound platform for teaching and clinical applications. The Clarius Ultrasound Scanner is intended for use in professional healthcare facilities where healthcare is provided by trained medical professionals. The device is also intended for use in Emergency Medical Service, ambulance, or rotary aircraft environments.

The Clarius Ultrasound Scanner is a diagnostic ultrasound system. The provided text, a 510(k) summary, outlines its substantial equivalence to predicate devices, thus demonstrating it meets acceptance criteria through a comparison study rather than independent performance testing against predefined metrics.

Here's a breakdown of the requested information based on the provided document:

Acceptance Criteria and Device Performance

The acceptance criteria are not directly stated as quantitative performance metrics (e.g., sensitivity, specificity for a specific diagnostic task). Instead, the device's acceptance is based on demonstrating "substantial equivalence" to legally marketed predicate devices. This means the device performs at a level comparable to, or as safely and effectively as, the predicate devices for its intended use, without raising new questions of safety or effectiveness.

The "reported device performance" is implicitly demonstrated through its substantial equivalence to the predicate devices and compliance with relevant nonclinical performance standards.

The table below outlines the comparison criteria used to establish substantial equivalence, which serves as the framework for acceptance.

Study Proving Acceptance Criteria

The study described is a comparison study for substantial equivalence under the FDA's 510(k) pathway. It demonstrates that the Clarius Ultrasound Scanner does not introduce any new technology or indications for use that differ significantly from legally marketed predicate devices, thus concluding that it is substantially equivalent in safety and effectiveness.

1. Sample size used for the test set and the data provenance:

   • The document states: "The Clarius Ultrasound Scanner did not require clinical testing to establish substantial equivalence to the predicate devices indicated."
   • Therefore, there was no separate "test set" of clinical data for the subject device to quantify its performance against specific acceptance criteria. The equivalence is established by comparing the design, technological characteristics, intended use, and indications for use of the subject device to the previously cleared predicate devices.
   • The provenance of data for the predicate devices is not detailed in this document.

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

   • Since no clinical testing was performed for the subject device, no experts were used to establish ground truth for a test set in the context of this 510(k) summary. The "ground truth" for the predicate devices' clearance would have been established during their respective regulatory processes, not during this submission.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Not applicable as no clinical test set requiring adjudication was used for this submission.

4. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • No MRMC comparative effectiveness study was done, as this submission did not involve clinical performance testing of the device's diagnostic accuracy or the impact of AI assistance on human readers. The device is purely an imaging system; the provided document does not mention AI components for image analysis or interpretation.

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

   • Not applicable. This is an ultrasound imaging system, and the document focuses on establishing substantial equivalence based on hardware, software, intended use, and modes of operation, not on an algorithm's standalone diagnostic performance. No AI algorithm in a standalone capacity is mentioned.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • For the purposes of this 510(k) submission, the "ground truth" for acceptance is the established safety and effectiveness of the predicate devices as determined by their prior FDA clearances. The subject device is deemed safe and effective because it is substantially equivalent to these already cleared devices, not through new clinical ground truth establishment for its own performance.

7. The sample size for the training set:

   • Not applicable. The document does not describe any machine learning components that would require a "training set" of data for this device.

8. How the ground truth for the training set was established:

   • Not applicable. As there is no described training set, there methods for establishing ground truth for it are absent.

Ask a specific question about this device

The Clarius Ultrasound Scanner is a software-based ultrasound imaging system and accessories, intended for diagnostic imaging in B-mode, M-mode, Color Doppler, Power Doppler, and Combined (B+M; B+Color Doppler; and B+Power Doppler). It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: ophthalmic, fetal, abdominal, intra-operative (non-neurological), pediatric, small organ, cephalic (adult), musculo-skeletal (conventional, superficial), urology, gynecology, cardiac (adult, pediatric), fetal echo, peripheral vessel, carotid, and procedural guidance of needles into the body.

The system is a transportable ultrasound system intended for use in environments where is provided by trained healthcare professionals.

The Clarius Ultrasound System is a portable, general-purpose, software-controlled, diagnostic ultrasound system used to acquire and display high-resolution, real-time ultrasound data through a commercial off the-shelf (COTS) iOS or Android device. The Clarius Ultrasound System comprises a series of wireless transducers employing Bluetooth and Wi-Fi-based technology to communicate with traditional tablet/smartphone devices via direct Wi-Fi. This allows the user to export ultrasound images and display them across a range of portable personal devices.

Piezoelectric material in the systems transmits high frequency, non-ionizing sound waves to the designated region of the body and converts the subsequent echoes detected to electronic signals in order to construct an image of the internal structures of an anatomical field. This image is sent wirelessly to an external (COTS) iOS or Android viewing device on which the image can be displayed. The transducer houses a battery and power generator, multichannel beam former, pre-scan converter, and Wi-Fi components. The battery is removable and comes with a separate charger. Communication between the transducer and the compatible viewing device will be via Wi-Fi Direct® (Ad-Hoc mode with security) for easy pairing.

The Clarius Ultrasound System product/package components include:

1. Software:
   The Ultrasound App (Clarius App) for iOS; OR
   The Ultrasound App (Clarius App) for Android.
2. Transducers/Scanners:
   Clarius C3 Scanner (C3 Convex Transducer);
   Clarius C3 Scanner (C3 Convex Transducer) with Clarius C3-L Clip-on;
   Clarius C7 Scanner (C7 Convex Transducer); OR
   Clarius L7 Scanner (L7 Linear Transducer).
3. Accessories:
   a. Clarius-Built:
   Battery Pack (Li-ion); and
   Battery Charger.
   b. OEM/Off-The-Shelf Product(s):
   Medical Power Supply (Off-the-shelf power adaptor from SL Power Electronics, USA; Model Number ME20A1203B02; Approved in the US); and
   Aquasonic 100 Ultrasound Transmission Gel (Off-the-shelf ultrasound gel from Parker Laboratories Inc., USA; Approved in the US).

The concept of the Clarius Ultrasound System transducers and software is primarily to provide an easy to use, high-performance, low-cost, ultrasound platform for teaching and clinical applications. The Clarius Ultrasound System is intended for use in professional healthcare facilities where healthcare is provided by trained medical professionals. The device is also intended for use in Emergency Medical Service, ambulance, or rotary aircraft environments.

The provided text describes a 510(k) premarket notification for the Clarius Ultrasound Scanner, indicating that clinical testing was not required to establish substantial equivalence.

Therefore, the document does not contain the information requested regarding acceptance criteria related to a study proving the device meets those criteria. Specifically, it states:

"The Clarius Ultrasound Scanner did not require clinical testing to establish substantial equivalence." (Page 14)

As a result, I cannot provide:

1. A table of acceptance criteria and reported device performance.
2. Sample size used for the test set or data provenance.
3. Number of experts or their qualifications for ground truth.
4. Adjudication method for the test set.
5. Information about an MRMC comparative effectiveness study or its effect size.
6. Information about standalone performance (algorithm only).
7. The type of ground truth used.
8. The sample size for the training set.
9. How the ground truth for the training set was established.

The document focuses on demonstrating substantial equivalence to predicate devices (FUJIFILM SonoSite Edge Ultrasound System K133454 and previous Clarius Ultrasound System K163138) through comparison of technical specifications, intended uses, and modes of operation, and compliance with various nonclinical performance standards like IEC and ISO.

Ask a specific question about this device