Potential time and recall benefits for adaptive AI breast MRI screening

Motivation: Full MRI breast cancer screening protocols are time-intensive and abbreviated protocols have relatively high recall. An AI-driven hybrid protocol could combine the strengths of both protocols. Goal(s): To determine the theoretical bounds of time and recall for an adaptive protocol. Approach: We calculated the maximum and minimum overlap between cases identified by radiologists and AI for the abbreviated protocol. Results: An AI driven protocol could improve MRI screening by reducing acquisition time and recall rates, compared to the full and abbreviated protocol respectively. Impact: The AI-based hybrid protocol could improve MRI screening by reducing acquisition time and recall rates, enhancing patient-centric care, improving MRI availability and achieving better breast cancer screening.