Abstract #2628

Segmentation of the Right Ventricle in 4-Chamber Cine Cardiac MR Images

Jose A. Rosado-Toro¹, Ryan Avery², Maria I. Altbach³, Aiden Abidov⁴, and Jeffrey J. Rodriguez¹

¹Electrical and Computer Engineering, University of Arizona, Tucson, AZ, United States, ²Radiology, University of Arizona, Tucson, AZ, United States, ³Medical Imaging, University of Arizona, Tucson, AZ, United States, ⁴Medicine, University of Arizona, Tucson, AZ, United States

We present a semi-automated algorithm for right ventricle segmentation in 4-chamber cardiac MR images. The algorithm takes post-processor landmarks in the end-diastolic and end-systolic frames and generates a segmentation of the right ventricle throughout the cardiac cycle. For the 175 images we analyzed (i.e., 7 patients with 25 frames per patient), the Dice metric was within human variability.

This abstract and the presentation materials are available to members only; a login is required.

Join Here