Genius AI Detection 2.0
Hologic, Inc.Genius AI Detection 2.0 is a software tool that uses artificial intelligence and deep learning to help radiologists detect and evaluate potential breast abnormalities in 3D mammography (digital breast tomosynthesis) images. It marks suspicious soft tissue densities and calcifications, provides confidence scores, and supports radiologists in their interpretation during the exam reading, enhancing breast cancer screening accuracy and efficiency.
Intended Use
Genius AI Detection is a computer-aided detection and diagnosis (CADe/CADx) software device intended to be used with compatible digital breast tomosynthesis (DBT) systems to identify and mark regions of interest including soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in DBT exams from compatible DBT systems and provide confidence scores that offer assessment for Certainty of Findings and a Case Score. The device intends to aid in the interpretation of digital breast tomosynthesis exams in a concurrent fashion, where the interpreting physician confirms or dismisses the findings during the reading of the exam.
Technology
Genius AI Detection 2.0 uses deep learning networks to analyze digital breast tomosynthesis images slice-by-slice, detecting lesions suspicious for cancer (masses, architectural distortions, asymmetries, and calcifications). It outputs the location, outline, confidence scores for each lesion, and a case score, packaged in a DICOM Mammography CAD SR object for display on compliant workstations concurrently with the exam reading. It supports multiple mammography platforms including the Envision Mammography Platform and Hologic's Selenia Dimensions.
Performance
Performance testing included software verification (unit, integration, system tests) confirming requirements were met. Clinical performance was evaluated using a multi-center dataset comparing images from the predicate device’s standard of care system to the Envision Mammography Platform, showing no significant difference in sensitivity, specificity, or false positive rates. Additional testing demonstrated effective detection on implant-displaced views. Overall results showed no loss of safety or effectiveness with the new platform compatibility.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
10/25/2024
9 months - 2
FDA Approval
7/31/2025
Other devices from Hologic, Inc.
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.