Improving Diagnosis of Autism Spectrum Disorder and Disentangling its Heterogeneous Functional Connectivity Patterns Using Capsule Networks.
Improving Diagnosis of Autism Spectrum Disorder and Disentangling its Heterogeneous Functional Connectivity Patterns Using Capsule Networks.
复制标题
DOI：
10.1109/isbi45749.2020.9098524
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Fan Y
中科院分区：
文献类型：
--
作者：
Jiao Z;Li H;Fan Y
功能连接（FC）分析是一种辅助自闭症谱系障碍（ASD）诊断并阐明其神经生理基础的有吸引力的工具。许多机器学习方法已经被开发出来，用于基于功能连接测量区分自闭症患者和健康对照，并识别自闭症的异常功能连接模式。特别是，一些研究表明，深度学习模型在自闭症诊断方面能够比传统机器学习方法取得更好的性能。尽管现有的机器学习方法已经取得了有前景的分类性能，但它们没有明确地对自闭症的异质性进行建模，无法解开自闭症的异质功能连接模式。为了实现更好的诊断以及对自闭症更好的理解，我们采用胶囊网络（CapsNets）构建分类器，基于功能连接测量区分自闭症患者和健康对照，并将自闭症患者分层为具有不同功能连接模式的组。基于一个大型多站点数据集的评估结果表明，我们的方法不仅比最先进的替代机器学习方法获得了更好的分类性能，而且还基于胶囊网络分类模型的矢量化分类输出识别出了具有临床意义的自闭症患者亚组。
Functional connectivity (FC) analysis is an appealing tool to aid diagnosis and elucidate the neurophysiological underpinnings of autism spectrum disorder (ASD). Many machine learning methods have been developed to distinguish ASD patients from healthy controls based on FC measures and identify abnormal FC patterns of ASD. Particularly, several studies have demonstrated that deep learning models could achieve better performance for ASD diagnosis than conventional machine learning methods. Although promising classification performance has been achieved by the existing machine learning methods, they do not explicitly model heterogeneity of ASD, incapable of disentangling heterogeneous FC patterns of ASD. To achieve an improved diagnosis and a better understanding of ASD, we adopt capsule networks (CapsNets) to build classifiers for distinguishing ASD patients from healthy controls based on FC measures and stratify ASD patients into groups with distinct FC patterns. Evaluation results based on a large multi-site dataset have demonstrated that our method not only obtained better classification performance than state-of-the-art alternative machine learning methods, but also identified clinically meaningful subgroups of ASD patients based on their vectorized classification outputs of the CapsNets classification model.
登录
查看更多内容
影响因子：
25.8
作者：
Cerliani, Leonardo;Mennes, Maarten;Thomas, Rajat M.;Di Martino, Adriana;Thioux, Marc;Keysers, Christian
通讯作者：
Keysers, Christian
DOI：
10.1038/nrneurol.2013.278
发表时间：
2014-02
期刊：
Nature reviews. Neurology
影响因子：
--
作者：
通讯作者：
--
影响因子：
4.2
作者：
Heinsfeld, Anibal Solon;Franco, Alexandre Rosa;Meneguzzi, Felipe
通讯作者：
Meneguzzi, Felipe
影响因子：
2.9
作者：
Nielsen JA;Zielinski BA;Fletcher PT;Alexander AL;Lange N;Bigler ED;Lainhart JE;Anderson JS
通讯作者：
Anderson JS
影响因子：
10.9
作者：
Parisot, Sarah;Ktena, Sofia Ira;Rueckert, Daniel
通讯作者：
Rueckert, Daniel