Search Results

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