Transpara is an AI-powered software tool that helps doctors identify suspicious areas in mammograms that might be breast cancer. It highlights these areas, provides scores indicating the likelihood of cancer, and supports physicians in making more accurate diagnoses. This assists in earlier and more reliable detection of breast cancer during screening.
The ScreenPoint Transpara system is intended for use as a concurrent reading aid for physicians interpreting screening mammograms, to identify regions suspicious for breast cancer and assess their likelihood of malignancy.
Software-only device using algorithms trained on large datasets of biopsy-proven breast cancer, benign lesions, and normal tissue mammograms to detect suspicious calcifications and soft tissue lesions. Processes images from multiple mammography vendors using DICOM CAD SR protocol, applying machine learning components for detection and scoring likelihood of malignancy.
Validation studies showed high sensitivity (94.1% for calcifications, 72.0% for soft tissue lesions) with low false positive rates, performed on a multi-vendor dataset independent from training data. A clinical reader study (14 radiologists, 240 cases) demonstrated a significant increase in diagnostic performance (AUC improvement from 0.866 to 0.886) when using Transpara, with no significant increase in reading time.
No predicate devices specified
Submission
6/27/2018
FDA Approval
11/21/2018
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.