DeepHealth ProstateAI
Quantib B.V.DeepHealth ProstateAI is an AI-based software designed to assist physicians in detecting and characterizing prostate cancer lesions from prostate MRI scans. It uses advanced neural networks to identify suspicious regions and classify their likelihood of cancer, helping radiologists make more informed decisions during prostate MRI exam interpretation.
Intended Use
DeepHealth ProstateAI is a Computer-Aided Detection and Diagnosis (CADe/x) software device developed to aid trained physicians in the detection and characterization of prostate cancer lesions using MR imaging data in patients aged 40 years and older. It analyzes T2W, ADC and DWI MR images combined with prostate gland segmentation input and outputs suspicious region candidates with segmentations and likelihood classifications. It is intended to assist in detecting prostate cancer across all grade groups, including clinically significant cancer, as a concurrent reading aid for physicians assessing prostate MRI exams.
Technology
The device uses convolutional neural networks based on a 3D Retina U-Net architecture within the nnDetection framework to automatically detect regions of interest (ROIs) for prostate cancer in multi-parametric MRI images (T2W, ADC, DWI). It requires input of a binary prostate gland segmentation from a cleared device and outputs ROIs with segmentations and categorical likelihood classifications (low, moderate, high suspicion) as DICOM or NIfTI files for PACS viewing. It integrates into PACS workflows and is designed as an adjunct to physician reading.
Performance
Performance testing included bench and clinical studies using independent, multi-institutional datasets. Bench testing evaluated image processing, detection, segmentation, and classification against expert annotations and pathology-confirmed references. Clinical validation comprised a multi-reader multi-case study and standalone assessment on 247 prostate MRI exams, demonstrating statistically significant improvement in detection with AI assistance and meeting segmentation accuracy targets. Testing confirmed safety and effectiveness across scanner vendors and protocols with no new safety questions compared to predicate device.
Predicate Devices
No predicate devices specified
Ready to Sharpen Your Edge?
Subscribe to join 11k+ 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.