An artificial intelligence system detected more thoracic aortic aneurysms during routine breast magnetic resonance imaging exams compared to standard clinical readings. The system improved detection rates by 3.5 times compared to radiologists' reports and demonstrated a 100% sensitivity in identifying cases previously detected by radiologists. The ANN's measurements deviated by an average of 0.524 mm from radiologists’ readings, and it showed consistent performance across MRI vendors and field strengths. Risk stratification applied to patients with ascending aortic diameters ≥ 3.5 cm identified cases at elevated risk of complications. Female patients with breast cancer or a history of breast cancer had slightly larger ascending aortic diameters and a higher risk of aneurysm presence.

Source: Nature Communications