DL Approach for Automated, Accurate Quantification of RV Dysfunction in PE

Background: Acute pulmonary embolism (APE) is a major contributor to cardiovascular mortality and frequently leads to rapid clinical deterioration due to abrupt increases in pulmonary vascular resistance and right ventricular (RV) overload. CT pulmonary angiogram (CTPA) is the frontline imaging modality for detecting pulmonary emboli. Because of its accessibility, speed, and high diagnostic yield beyond confirming clot presence, CTPA derived metrics such as the right ventricular to left ventricular diameter ratio (RV/LV), pulmonary artery to ascending aorta ratio (PA/AA), and septal angle (SA). They offer insight into hemodynamic stress and the likelihood of short-term adverse events. However, these measurements are traditionally acquired manually, require substantial expertise, and are subject to notable inter-observer variability limiting routine integration into risk stratification. Workflow advances in deep learning (DL) have facilitated reliable automated vessel and cardiac cham more...