A framework for combining a motion atlas with non-motion information to learn clinically useful biomarkers: Application to cardiac resynchronisation therapy response prediction
详细信息 查看全文
- 作者：Devis Peressuttia ; devis.1.peressutti@kcl.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Matthew Sinclaira ; Wenjia Baib ; Thomas Jacksona ; Jacobus Ruijsinka ; David Nordslettena ; Liya Asnera ; Myrianthi Hadjicharalambousa ; Christopher A. Rinaldia ; Daniel Rueckertb ; Andrew P. King ; a ; andrew.king@kcl.ac.uk" class="auth_mail" title="E-mail the corresponding author
- 关键词：Spatio-temporal atlas ; Multiple kernel learning ; Random projections ; Cardiac resynchronisation therapy
- 刊名：Medical Image Analysis
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：35
- 期：Complete
- 页码：669-684
- 全文大小：3976 K
文摘
- •
Framework to combine cardiac motion and deformation data with non-motion data.
- •
Motion atlas use for comparison of LV displacement, velocity, strain and strain rate.
- •
Random projections and multiple kernel learning are used to extract relevant features.
- •
Application to response prediction in cardiac resynchronisation therapy.
- •
94% and 91% classification accuracy of super-responders and non-responders.