Zhuang Juntang, Dvornek Nicha C, Li Xiaoxiao, Ventola Pamela, Duncan James S
Biomedical Engineering, Yale University, New Haven, CT USA.
Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT USA.
Med Image Comput Comput Assist Interv. 2019 Oct;11766:700-708. doi: 10.1007/978-3-030-32248-9_78. Epub 2019 Oct 10.
Determining biomarkers for autism spectrum disorder (ASD) is crucial to understanding its mechanisms. Recently deep learning methods have achieved success in the classification task of ASD using fMRI data. However, due to the black-box nature of most deep learning models, it's hard to perform biomarker selection and interpret model decisions. The recently proposed invertible networks can accurately reconstruct the input from its output, and have the potential to unravel the black-box representation. Therefore, we propose a novel method to classify ASD and identify biomarkers for ASD using the connectivity matrix calculated from fMRI as the input. Specifically, with invertible networks, we explicitly determine the decision boundary and the projection of data points onto the boundary. Like linear classifiers, the difference between a point and its projection onto the decision boundary can be viewed as the . We then define the as the explanation weighted by the gradient of prediction the input, and identify biomarkers based on this importance measure. We perform a regression task to further validate our biomarker selection: compared to using all edges in the connectivity matrix, using the top 10% important edges we generate a lower regression error on 6 different severity scores. Our experiments show that the invertible network is both effective at ASD classification and interpretable, allowing for discovery of reliable biomarkers.
确定自闭症谱系障碍（ASD）的生物标志物对于理解其发病机制至关重要。最近，深度学习方法在使用功能磁共振成像（fMRI）数据进行ASD分类任务中取得了成功。然而，由于大多数深度学习模型的黑箱性质，很难进行生物标志物选择和解释模型决策。最近提出的可逆网络可以从其输出准确重建输入，并有可能揭示黑箱表示。因此，我们提出了一种新颖的方法，使用从fMRI计算得到的连通性矩阵作为输入来对ASD进行分类并识别ASD的生物标志物。具体来说，利用可逆网络，我们明确确定决策边界以及数据点在边界上的投影。与线性分类器一样，一个点与其在决策边界上的投影之间的差异可以被视为……我们然后将……定义为由预测相对于输入的梯度加权的解释，并基于此重要性度量识别生物标志物。我们执行回归任务以进一步验证我们的生物标志物选择：与使用连通性矩阵中的所有边相比，使用最重要的前10%的边，我们在6个不同严重程度评分上产生了更低的回归误差。我们的实验表明，可逆网络在ASD分类方面既有效又可解释，能够发现可靠的生物标志物。
