Transpara 1.7.2
ScreenPoint Medical B.V.Transpara 1.7.2 is an AI-based software tool that helps radiologists detect and assess suspicious regions in breast mammography and tomosynthesis exams. It highlights potential cancerous lesions, scores their likelihood of malignancy, and provides an overall exam score to assist in clinical decision making, enhancing the accuracy and efficiency of breast cancer screening.
Intended Use
Transpara software is intended for use as a concurrent reading aid for physicians interpreting screening full-field digital mammography exams and digital breast tomosynthesis exams from compatible FFDM and DBT systems, to identify regions suspicious for breast cancer and assess their likelihood of malignancy.
Technology
Transpara is a software-only AI application that uses deep learning algorithms trained on a large database of biopsy-proven breast cancer and normal tissue images. It processes FFDM and DBT images to detect suspicious calcifications and soft tissue lesions, providing CAD marks, regional suspicion scores, exam likelihood scores, and links between corresponding regions in different views.
Performance
Verification testing showed satisfaction of software requirements. Standalone performance tested on a large independent multi-center dataset (10,690 exams including 1,472 cancer cases) demonstrated sensitivity of 95.0% at 0.30 FP/image for 2D mammography and 93.2% at 0.34 FP/volume for DBT. ROC AUC was 0.945 for both 2D and DBT exams, showing non-inferior detection performance compared to the predicate device.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
5/9/2022
2 months - 2
FDA Approval
8/3/2022
Other devices from ScreenPoint Medical B.V.
- Transpara (2.1.0)2024 • 510K
- Transpara Density 1.0.02023 • 510K
- Transpara 1.7.02021 • 510K
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.