作者: Wenjia Bai , Devis Peressutti , Ozan Oktay , Wenzhe Shi , Declan P. O’Regan
DOI: 10.1007/978-3-319-20309-6_1
关键词:
摘要: Motion, together with shape, reflect important aspects of cardiac function. In this work, a new method is proposed for learning motion descriptor from data-driven perspective. The resulting can characterise the global pattern left ventricle much lower dimension than original data. It has demonstrated its predictive power on two exemplar classification tasks large cohort 1093 normal subjects.