Clarius Prostate AI

Clarius Prostate AI is a Class II Medical Image Management and Processing System designed for semi-automatic prostate volume measurement using ultrasound data, aiming to enhance clinical efficiency and accuracy. Its science relies on a machine learning algorithm validated through non-clinical and clinical studies demonstrating non-inferiority to manual expert measurements, with future modifications managed under a Predetermined Change Control Plan.

Clarius Mobile Health Corp.'s device, Clarius Prostate AI, has been found substantially equivalent to legally marketed devices for its intended use. This device, classified as a Medical Image Management and Processing System (Class II), is designed for semi-automatic measurements of prostate volume based on ultrasound data acquired by Clarius Ultrasound Scanners. The determination allows the device to be marketed, subject to general controls including annual registration, device listing, good manufacturing practice, and labeling requirements. The device's safety and effectiveness were affirmed through comprehensive non-clinical and clinical performance testing. Clinical studies demonstrated that Clarius Prostate AI's automated measurements were non-inferior to manual measurements performed by qualified experts, exhibiting high accuracy and meeting user needs. Future modifications to the device's machine learning algorithm will adhere to a Predetermined Change Control Plan, ensuring continued safety and effectiveness. Manufacturers must also comply with various ongoing requirements such as the Quality System regulation, medical device reporting, labeling, and unique device identification rules.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the specific machine learning algorithm used by Clarius Prostate AI compare in efficiency and accuracy to other AI-based prostate volume measurement systems?; What are the specific parameters or metrics used to define "non-inferiority" in the clinical studies, and what was the observed variability between automated and manual measurements?; Beyond prostate volume, could the Clarius Prostate AI be expanded to assist with other prostate imaging tasks or diagnostic features?; What is the long-term plan for validating the continued accuracy and safety of the device's machine learning algorithm under the Predetermined Change Control Plan, especially with real-world data drift?; What impact does the integration of Clarius Prostate AI have on clinical workflow and diagnostic throughput compared to traditional manual measurement methods?