Meeting Banner
Abstract #3281

Algorithmic Quantification of Left Ventricle Segmentation in 4D Cardiac Magnetic Resonance Imaging Based on Spatio-Temporal Continuity

Lijia Wang1,2, Mengchao Pei1, Noel C. F. Codella3, Jonathan W. Weinsaft2,4, Martin R. Prince2, Yi Wang2,3

1Shanghai Key laboratory of Magnetic Resonance, East China Normal University, Shanghai, China, People's Republic of; 2Department of Radiology, Weill Medical College of Cornell University, New York, NY, United States; 3Department of Physiology, Biophysics, and Systems Biology, Weill Medical College of Cornell Universi, New York, NY, United States; 4Department of Medicine-Cardiology, Weill Medical College of Cornell University, New York, NY, United States


To reduce the intra- & inter- variabilities of manual intervention in left ventricle (LV) segmentation, an algorithmic LV segmentation method is proposed to select apical and basal LV positions based on spatio-temporal continuity of LV area and shape, enabling segment the entire LV at all the cardiac phases. This algorithm was validated on short axis cine SSFP data from 38 patients with IRB approval and HIPAA compliance by comparing with manual tracing, showing promise for rapid and accurate LV segmentation in routine clinical cardiac MRI.