Autism has previously been characterized by both structural and functional differences in brain connectivity. However, while the literature on single-subject derivations of functional connectivity is extensively developed, similar methods of structural connectivity or similarity derivation from T1 MRI are less studied. We introduce a technique of deriving symmetric similarity matrices from regional histograms of grey matter volumes estimated from T1-weighted MRIs. We then validated the technique by inputting the similarity matrices into a convolutional neural network (CNN) to classify between participants with autism and age-, motion-, and intracranial-volume-matched controls from six different databases (29,288 total connectomes, mean age = 30.72, range 0.42–78.00, including 1555 subjects with autism). We compared this method to similar classifications of the same participants using fMRI connectivity matrices as well as univariate estimates of grey matter volumes. We further applied graph-theoretical metrics on output class activation maps to identify areas of the matrices that the CNN preferentially used to make the classification, focusing particularly on hubs. While this study used a large sample size, the majority of data was from a young age group; furthermore, to make a viable machine learning study, we treated autism, a highly heterogeneous condition, as a binary label. Thus, these results are not necessarily generalizable to all subtypes and age groups in autism. Our models gave AUROCs of 0.7298 (69.71% accuracy) when classifying by only structural similarity, 0.6964 (67.72% accuracy) when classifying by only functional connectivity, and 0.7037 (66.43% accuracy) when classifying by univariate grey matter volumes. Combining structural similarity and functional connectivity gave an AUROC of 0.7354 (69.40% accuracy). Analysis of classification performance across age revealed the greatest accuracy in adolescents, in which most data were present. Graph analysis of class activation maps revealed no distinguishable network patterns for functional inputs, but did reveal localized differences between groups in bilateral Heschl’s gyrus and upper vermis for structural similarity. This study provides a simple means of feature extraction for inputting large numbers of structural MRIs into machine learning models. Our methods revealed a unique emphasis of the deep learning model on the structure of the bilateral Heschl’s gyrus when characterizing autism.

中文翻译：

---

单参与者结构相似性矩阵比 MRI 中自闭症功能更能提高参与者分类的准确性


自闭症以前的特点是大脑连接的结构和功能差异。然而，虽然有关功能连接的单主体推导的文献已广泛发展，但从 T1 MRI 中推导结构连接或相似性的类似方法却很少研究。我们引入了一种从 T1 加权 MRI 估计的灰质体积区域直方图导出对称相似矩阵的技术。然后，我们通过将相似性矩阵输入卷积神经网络 (CNN) 来验证该技术，对来自六个不同数据库（总共 29,288 个连接体，平均年龄 = 30.72，范围 0.42–78.00，包括 1555 名自闭症受试者）。我们将该方法与使用功能磁共振成像连接矩阵以及灰质体积的单变量估计对相同参与者进行的类似分类进行了比较。我们进一步在输出类激活图上应用图论度量来识别 CNN 优先用于分类的矩阵区域，特别关注集线器。虽然这项研究使用了大样本量，但大部分数据来自年轻群体；此外，为了进行可行的机器学习研究，我们将自闭症这种高度异质的疾病视为二元标签。因此，这些结果不一定适用于自闭症的所有亚型和年龄组。当仅按结构相似性进行分类时，我们的模型给出的 AUROC 为 0.7298（69.71% 准确度）；当仅按功能连接进行分类时，我们的模型给出的 AUROC 为 0.6964（67.72% 准确度）；当按单变量灰质体积分类时，我们的模型给出的 AUROC 为 0.7037（66.43% 准确度）。 结合结构相似性和功能连接性，AUROC 为 0.7354（准确度为 69.40%）。对不同年龄段分类表现的分析显示，青少年的准确度最高，其中存在大多数数据。类激活图的图形分析揭示了功能输入没有可区分的网络模式，但确实揭示了双侧赫施尔回和上蚓部组之间结构相似性的局部差异。这项研究提供了一种简单的特征提取方法，用于将大量结构 MRI 输入到机器学习模型中。我们的方法揭示了深度学习模型在表征自闭症时对双侧赫施尔回结构的独特重视。