Transpara is an AI-powered software designed to assist physicians in interpreting full-field digital mammography and digital breast tomosynthesis exams. It highlights suspicious regions that may indicate breast cancer, providing scores that indicate the likelihood of malignancy. This helps radiologists improve detection accuracy and workflow efficiency while supporting clinical decisions during breast cancer screening.
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.
Transpara is a software-only application using deep learning algorithms applied to FFDM and DBT images. It detects and characterizes suspicious calcifications and soft tissue lesions such as densities, masses, architectural distortions, and asymmetries. The output includes CAD marks, region scores (0-100), and an exam score (1-10) indicating likelihood of cancer. It processes DICOM images and supports multiple mammography vendors.
Performance was evaluated by verification, validation, and clinical reader studies. Validation used multi-vendor datasets showing non-inferior or better detection compared to prior versions. The pivotal reader study showed significant improvement in breast cancer detection AUC (0.833 to 0.863, p=0.0025), superior sensitivity, and reduced reading time when radiologists used Transpara with DBT exams.
No predicate devices specified
Submission
11/22/2019
FDA Approval
3/5/2020
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.