ProFound Detection V4.0 is an AI-powered software designed to assist radiologists by detecting suspicious soft tissue densities and calcifications in 3D digital breast tomosynthesis (DBT) images. It helps identify potential malignant lesions by marking findings and providing confidence scores, thus supporting earlier and more accurate breast cancer detection during image interpretation.
ProFound Detection V4.0 is a computer-assisted detection and diagnosis (CAD) software device intended to be used concurrently by interpreting physicians while reading digital breast tomosynthesis (DBT) exams from compatible DBT systems. The system detects soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in the 3D DBT slices. The detections and Certainty of Finding and Case Scores assist interpreting physicians in identifying soft tissue densities and calcifications that may be confirmed or dismissed by the interpreting Physician.
ProFound Detection V4.0 utilizes neural network architectures for image processing and AISupported CAD of DBT images, assigning Certainty of Finding and Case Scores which indicate the algorithm's confidence of malignancy in each finding and case. It includes a Predetermined Change Control Plan (PCCP) to extend support to multiple DBT image acquisition systems with algorithm training, tuning, and locking prior to commercial release.
Performance testing demonstrated that ProFound Detection V4.0 is non-inferior and in some measures superior to the predicate device (ProFound AI V3.0), with sensitivity around 90% and improved specificity. Testing involved retrospective evaluation of 952 DBT cases with biopsy-proven cancers and various demographics, using clinical reference standards. Unit and integration testing confirmed expected results.
No predicate devices specified
Submission
2/13/2024
FDA Approval
11/8/2024
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.