Prostate MR AI (VA10A)
Siemens Healthcare GmbHProstate MR AI (VA10A) is a plug-in AI software device designed to assist radiologists in interpreting prostate MRI scans. It automatically segments the prostate gland, detects suspicious lesions, and assigns scores to help radiologists identify and classify potential prostate cancer. This tool supports clinicians by augmenting their workflow and improving diagnostic accuracy.
Intended Use
Plug-in Radiological Computer Assisted Detection and Diagnosis Software used with a separate hosting application as a concurrent reading aid for radiologists interpreting prostate MRI exams acquired according to PI-RADS, in adult men (40 years and older) with suspected cancer in treatment-naïve prostate glands. The software analyzes non-contrast T2W and DWI images to segment the prostate gland and detect suspicious regions for cancer, providing lesion scores by PI-RADS interpretation suggestion.
Technology
The device is a software-only AI algorithm trained on prostate MRI (T2W and DWI sequences) data acquired according to PI-RADS. It performs automatic segmentation of the prostate gland and its sub-regions (peripheral zone and non-peripheral zone), detects suspicious lesions, and classifies these by lesion scores and level of suspicion. It outputs lesion contours, suspicion maps, and summarized scores to a hosting application for radiologist review and interaction. The software integrates as a plug-in module augmenting the syngo.MR General Engine workflow through a separate license.
Performance
Nonclinical and clinical performance testing demonstrated accuracy and safety of the AI algorithm. Nonclinical tests showed median Dice scores >0.9 for prostate segmentation and lesion detection sensitivity ≥0.8 with false positive rates below one per case. Clinical evaluation via multi-reader multi-case studies showed statistically significant improvement in radiologist diagnostic performance with the device, measured by AUC ROC metrics and lesion-level accuracy. Testing included diverse patient cohorts including African American patients and multiple MR hardware vendors. The device met primary and secondary clinical endpoints showing improved sensitivity and specificity when used as a reading aid.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
6/20/2024
8 months - 2
FDA Approval
3/5/2025
Other devices from Siemens Healthcare GmbH
Ready to Sharpen Your Edge?
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.