Deep learning models for MRI classification face two recurring problems: they are typically limited by low sample size, and are abstracted by their own complexity (the “black box problem”). In this paper, we train a convolutional neural network (CNN) with the largest multi-source, functional MRI (fMRI) connectomic dataset ever compiled, consisting of 43,858 datapoints. We apply this model to a cross-sectional comparison of autism spectrum disorder (ASD) versus typically developing (TD) controls that has proved difficult to characterize with inferential statistics. To contextualize these findings, we additionally perform classifications of gender and task versus rest. Employing class-balancing to build a training set, we trained [Formula: see text] modified CNNs in an ensemble model to classify fMRI connectivity matrices with overall AUROCs of 0.6774, 0.7680, and 0.9222 for ASD versus TD, gender, and task versus rest, respectively. Additionally, we aim to address the black box problem in this context using two visualization methods. First, class activation maps show which functional connections of the brain our models focus on when performing classification. Second, by analyzing maximal activations of the hidden layers, we were also able to explore how the model organizes a large and mixed-center dataset, finding that it dedicates specific areas of its hidden layers to processing different covariates of data (depending on the independent variable analyzed), and other areas to mix data from different sources. Our study finds that deep learning models that distinguish ASD from TD controls focus broadly on temporal and cerebellar connections, with a particularly high focus on the right caudate nucleus and paracentral sulcus.

中文翻译：

---

在自闭症和其他任务中的大型混合站点 fMRI 数据集上集成深度学习

用于 MRI 分类的深度学习模型面临两个反复出现的问题：它们通常受到样本量小的限制，并且被自身的复杂性抽象化（“黑盒问题”）。在本文中，我们训练了一个卷积神经网络 (CNN)，该网络具有有史以来最大的多源功能 MRI (fMRI) 连接组数据集，由 43,858 个数据点组成。我们将此模型应用于自闭症谱系障碍 (ASD) 与典型发育 (TD) 对照的横断面比较，这些对照已被证明难以用推论统计来表征。为了将这些发现背景化，我们还对性别和任务与休息进行了分类。使用类平衡来构建训练集，我们在一个集成模型中训练 [公式：见文本] 修改后的 CNN，以对总体 AUROC 为 0 的 fMRI 连接矩阵进行分类。ASD 与 TD、性别和任务与休息分别为 6774、0.7680 和 0.9222。此外，我们的目标是使用两种可视化方法来解决这种情况下的黑盒问题。首先，类激活图显示了我们的模型在执行分类时关注的大脑功能连接。其次，通过分析隐藏层的最大激活，我们还能够探索模型如何组织大型混合中心数据集，发现它专门将隐藏层的特定区域用于处理不同的数据协变量（取决于独立的变量分析）和其他领域以混合来自不同来源的数据。我们的研究发现，将 ASD 与 TD 控制区分开来的深度学习模型广泛关注时间和小脑连接，