Using deep belief network modelling to characterize differences in brain morphometry in schizophrenia.
Using deep belief network modelling to characterize differences in brain morphometry in schizophrenia.
复制标题
DOI：
10.1038/srep38897
复制
发表时间：
2016-12-12
影响因子：
4.6
通讯作者：
Sato JR
中科院分区：
文献类型：
--
作者：
Pinaya WH;Gadelha A;Doyle OM;Noto C;Zugman A;Cordeiro Q;Jackowski AP;Bressan RA;Sato JR
基于神经影像学的模型有助于增加我们对精神分裂症病理生理学的理解，并可以揭示这种和其他临床疾病的潜在特征。然而，在报告的神经影像学结果的相当大的变化反映了疾病的异质性。能够表示不变特征的机器学习方法可以解决这个问题。在这项结构MRI研究中，我们训练了一种称为深度信念网络（DBN）的深度学习模型，以从脑形态测量数据中提取特征，并研究了其在区分健康对照（N = 83）和精神分裂症患者（N = 143）方面的表现。我们进一步分析了对首发精神病患者（N = 32）进行分类的性能。DBN强调了类之间的差异，特别是在额叶，颞叶，顶叶和岛叶皮质，以及一些皮质下区域，包括胼胝体，壳核和小脑。DBN作为分类器（准确度= 73.6%）比支持向量机（准确度= 68.1%）稍微更准确。最后，DBN在对首发患者进行分类时的错误率为56.3%，这表明从精神分裂症患者和健康对照中学习到的表征不适合定义这些患者。我们的数据表明，深度学习可以通过改善神经形态测量分析来提高我们对精神分裂症等精神疾病的理解。
Neuroimaging-based models contribute to increasing our understanding of schizophrenia pathophysiology and can reveal the underlying characteristics of this and other clinical conditions. However, the considerable variability in reported neuroimaging results mirrors the heterogeneity of the disorder. Machine learning methods capable of representing invariant features could circumvent this problem. In this structural MRI study, we trained a deep learning model known as deep belief network (DBN) to extract features from brain morphometry data and investigated its performance in discriminating between healthy controls (N = 83) and patients with schizophrenia (N = 143). We further analysed performance in classifying patients with a first-episode psychosis (N = 32). The DBN highlighted differences between classes, especially in the frontal, temporal, parietal, and insular cortices, and in some subcortical regions, including the corpus callosum, putamen, and cerebellum. The DBN was slightly more accurate as a classifier (accuracy = 73.6%) than the support vector machine (accuracy = 68.1%). Finally, the error rate of the DBN in classifying first-episode patients was 56.3%, indicating that the representations learned from patients with schizophrenia and healthy controls were not suitable to define these patients. Our data suggest that deep learning could improve our understanding of psychiatric disorders such as schizophrenia by improving neuromorphometric analyses.
登录
查看更多内容
影响因子：
4.5
作者：
Downhill, JE;Buchsbaum, MS;Siever, LJ
通讯作者：
Siever, LJ
影响因子：
32.8
作者：
Bengio, Yoshua
通讯作者：
Bengio, Yoshua
影响因子：
5.7
作者：
Kim J;Calhoun VD;Shim E;Lee JH
通讯作者：
Lee JH
影响因子：
5.7
作者：
Dale, AM;Fischl, B;Sereno, MI
通讯作者：
Sereno, MI
影响因子：
4.5
作者：
Keshavan, Matcheri S.;Nasrallah, Henry A.;Tandon, Rajiv
通讯作者：
Tandon, Rajiv