• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SPIE Medical Imaging Conference >A Generative-Predictive Framework to Capture Altered Brain Activity in fMRI and its Association with Genetic Risk: Application to Schizophrenia
【24h】

A Generative-Predictive Framework to Capture Altered Brain Activity in fMRI and its Association with Genetic Risk: Application to Schizophrenia

机译：一种生成预测框架，用于捕获FMRI的改变的脑活动及其与遗传风险的关联：对精神分裂症的应用

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

We present a generative-predictive framework that captures the differences in regional brain activity betweena neurotypical cohort and a clinical population, as guided by patient-specific genetic risk. Our model assumesthat the functional activations in the neurotypical subjects are distributed around a population mean, and thatthe altered brain activity in neuropsychiatric patients is defined via deviations from this neurotypical mean.We employ group sparsity to identify a set of brain regions that simultaneously explain the salient functionaldifferences and specify a set of basis vector, that span the low dimensional data subspace. The patient-specificprojections onto this subspace are used as feature vectors to identify multivariate associations with geneticrisk. We have evaluated our model on a task-based fMRI dataset from a population study of schizophrenia. Wecompare our model with two baseline methods, regression using Least Absolute Shrinkage and Selection Operator(LASSO) and Random Forest (RF) regression, which establishes direct association between the brain activityduring a working memory task and schizophrenia polygenic risk. Our model demonstrates greater consistencyand robustness across bootstrapping experiments than the machine learning baselines. Moreover, the set of brainregions implicated by our model underlie the well documented executive cognitive deficits in schizophrenia.
机译：我们提出了一种生成的预测框架，捕捉区域脑活动之间的差异一种神经典型的队列和临床群体，以患者特异性遗传风险为指导。我们的型号假设神经典型主体中的功能激活分布在群体周围，是神经精神患者的改变的脑活动通过与这种神经典型的平均值的偏差定义。我们采用小组稀疏性来识别一组同时解释突出功能的大脑区域差异并指定一组基础向量，跨越低维数据子空间。患者特定的在该子空间上的投影用作特征向量，以识别与遗传学的多变量关联风险。我们在精神分裂症的人口研究中评估了我们在基于任务的FMRI数据集中的模型。我们使用两个基线方法进行比较我们的模型，使用最不绝对收缩和选择操作员回归（套索）和随机森林（RF）回归，其在大脑活动之间建立了直接关联在工作记忆任务和精神分裂症的多基因风险期间。我们的模型展示了更大的一致性跨自动启动实验的鲁棒性比机器学习基准。而且，大脑的一组我们的模型涉及的地区涉及精神分裂症的良好记录的执行认知缺陷。

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