Clarius Prostate AI
K243853Clarius Mobile Health Corp. · cleared 2025-04-16 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.6)
“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.”
source quote (p.6)
“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. Image segmentation for border detection, and prostate view classification using a Deep Neural Network.”
source quote (p.9)
“Ultrasound image processing software application implementing artificial intelligence utilizing non-adaptive machine learning algorithms trained with clinical and/or artificial data intended for segmentation and measurements of ultrasound data.”
source quote (p.15)
“Modifications to Clarius Prostate 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 Prostate 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.”
source quote (p.12)
“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.”
Validation studies (3)
Retrospective clinical
n=139 patients · 10 site(s)
endpoints: verify that Clarius Prostate AI auto-measurements are non-inferior to manual measurements performed by qualified experts with relevant (i.e., Prostate) ultrasound experience.; determine whether Clarius Prostate AI prostate volume measurements are non-inferior to those obtained manually by human experts/qualified ultrasound users (if the magnitude of the difference (the absolute percent error) between Clarius Prostate AI and mean reviewer (human expert) measurements is greater than the magnitude of the mean difference (mean absolute percent error) between the reviewers themselves).; determine the correlation between Clarius Prostate AI segmentation and those of human experts, whether it can accurately identify transverse and sagittal prostate views.
Prospective clinical
sample size not stated
endpoints: evaluate the design and clinical usage of Clarius Prostate 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 prostate volume measurements.
Bench
sample size not stated
standards: IEC 62304:2006 + A1:2015, ISO 14971:2019, NEMA PS 3.1 - 3.20 (2022d), IEC 62366-1:2015 + A1:2020, ISO 15223-1:2021
Reported performance (3 observations)
source quote (p.14)
“Bland-Altman plots indicated strong agreement between Clarius Prostate AI and expert measurements, with the model showing high accuracy in view prediction (95%).”
source quote (p.14)
“The ICC scores for different probe models (i.e., C3 HD3, EC7 HD3) were 0.87 for endo-cavitary probes and 0.67 for curvilinear probes, highlighting expected variations in performance.”
source quote (p.14)
“The ICC scores for different probe models (i.e., C3 HD3, EC7 HD3) were 0.87 for endo-cavitary probes and 0.67 for curvilinear probes, highlighting expected variations in performance.”
Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.
Predicate network
Postmarket — what happened after clearance
Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.
Reimbursement — how devices like this got paid
Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).