Xiao Chen1, Masoud Edalati2, Qi Liu2, Xingxian Shou2, Abhishek Sharma1, Mary P. Watkins3, Daniel J. Lenihan3, Linzhi Hu2, Gregory M. Lanza3, Terrence Chen1, and Shanhui Sun1
1United Imaging Intelligence, Cambridge, MA, United States, 2UIH America, Inc., Houston, TX, United States, 3Cardiology, Washington University School of Medicine, St. Louis, MO, United States
1United Imaging Intelligence, Cambridge, MA, United States, 2UIH America, Inc., Houston, TX, United States, 3Cardiology, Washington University School of Medicine, St. Louis, MO, United States
A deep-learning-based fully-automated myocardium strain assessment system is proposed and validated for accurate strain analyses on patient data.
Workflow of the proposed fully automated cardiac strain and function analyses.
Summary of global and segmental Ell and Ecc using fastSENC and autoFT for oncology and non-oncology patients. Mean (std) numbers are reported.
