首页> 外文会议>International Workshop on Machine Learning in Medical Imaging;International Conference on Medical Image Computing and Computer-Assisted Intervention >Interwound Structural and Functional Difference Between Preterm and Term Infant Brains Revealed by Multi-view CCA
【24h】

Interwound Structural and Functional Difference Between Preterm and Term Infant Brains Revealed by Multi-view CCA

机译:多视图CCA揭示早产和术语婴儿大脑之间的间歇结构和功能差异

获取原文

摘要

The perinatal period is a critical time of development of brain cortex, structural connection and function. Therefore, A premature exposure to the extrauterine environment is suggested to have the downstream consequences of abnormality in brain structure, function and cognition. A comparative study between the preterm infant brains and term ones at the term-equivalent age provides a valuable window to investigate the normal and abnormal developmental mechanism of these interwound developmental processes. Most of works focused only on one of these processes, and very few studies are found to interpret how these processes interact with each other and how such interactions have been altered on preterm infants' brains. To fill this gap, we propose a multi-view canonical correlation analysis (CCA) method with the locality preserving projection (LPP) constraint and the age regression constraint, by which interactions between these interwound structural and functional features are identified to maximize the discrimination between preterm and term groups. Our findings on the interaction patterns among structural and functional features find supports from previous reports and provide new knowledge to the development patterns of infant brains.
机译:围产期是脑皮层,结构连接和功能的关键时期。因此,建议脑部结构,功能和认知中具有异常的下游后果。期末婴儿大脑与术语等同年龄的术语之间的比较研究提供了有价值的窗口,以研究这些间歇性发育过程的正常和异常发育机制。大多数作品仅关注这些过程中的一个,并且发现很少有研究解释这些过程如何相互作用以及如何在早产儿的大脑上改变这种相互作用。为了填补这种差距,我们提出了一种多视图规范相关性分析(CCA)方法,其具有局部性保存投影(LPP)约束和年龄回归约束,通过该限制的年龄回归约束,识别出这些间隔结构和功能特征之间的相互作用来最大化与之间的识别早产和术语群体。我们在结构和功能特点之间的互动模式的研究结果发现,从以前的报告支持和婴儿大脑的发展模式提供新的知识。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号