当前位置: X-MOL 学术NeuroImage › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
fMRI volume classification using a 3D convolutional neural network robust to shifted and scaled neuronal activations
NeuroImage ( IF 4.7 ) Pub Date : 2020-12-01 , DOI: 10.1016/j.neuroimage.2020.117328
Hanh Vu 1 , Hyun-Chul Kim 1 , Minyoung Jung 1 , Jong-Hwan Lee 1
Affiliation  

Deep-learning methods based on deep neural networks (DNNs) have recently been successfully utilized in the analysis of neuroimaging data. A convolutional neural network (CNN) is a type of DNN that employs a convolution kernel that covers a local area of the input sample and moves across the sample to provide a feature map for the subsequent layers. In our study, we hypothesized that a 3D-CNN model with down-sampling operations such as pooling and/or stride would have the ability to extract robust feature maps from the shifted and scaled neuronal activations in a single functional MRI (fMRI) volume for the classification of task information associated with that volume. Thus, the 3D-CNN model would be able to ameliorate the potential misalignment of neuronal activations and over-/under-activation in local brain regions caused by imperfections in spatial alignment algorithms, confounded by variability in blood-oxygenation-level-dependent (BOLD) responses across sessions and/or subjects. To this end, the fMRI volumes acquired from four sensorimotor tasks (left-hand clenching, right-hand clenching, auditory attention, and visual stimulation) were used as input for our 3D-CNN model to classify task information using a single fMRI volume. The classification performance of the 3D-CNN was systematically evaluated using fMRI volumes obtained from various minimal preprocessing scenarios applied to raw fMRI volumes that excluded spatial normalization to a template and those obtained from full preprocessing that included spatial normalization. Alternative classifier models such as the 1D fully connected DNN (1D-fcDNN) and support vector machine (SVM) were also used for comparison. The classification performance was also assessed for several k-fold cross-validation (CV) schemes, including leave-one-subject-out CV (LOOCV). Overall, the classification results of the 3D-CNN model were superior to that of the 1D-fcDNN and SVM models. When using the fully-processed fMRI volumes with LOOCV, the mean error rates (± the standard error of the mean) for the 3D-CNN, 1D-fcDNN, and SVM models were 2.1% (± 0.9), 3.1% (± 1.2), and 4.1% (± 1.5), respectively (p = 0.041 from a one-way ANOVA). The error rates for 3-fold CV were higher (2.4% ± 1.0, 4.2% ± 1.3, and 10.1% ± 2.0; p < 0.0003 from a one-way ANOVA). The mean error rates also increased considerably using the raw fMRI 3D volume data without preprocessing (26.2% for the 3D-CNN, 75.0% for the 1D-fcDNN, and 75.0% for the SVM). Furthermore, the ability of the pre-trained 3D-CNN model to handle shifted and scaled neuronal activations was demonstrated in an online scenario for five-class classification (i.e., four sensorimotor tasks and the resting state) using the real-time fMRI of three participants. The resulting classification accuracy was 78.5% (± 1.4), 26.7% (± 5.9), and 21.5% (± 3.1) for the 3D-CNN, 1D-fcDNN, and SVM models, respectively. The superior performance of the 3D-CNN compared to the 1D-fcDNN was verified by analyzing the resulting feature maps and convolution filters that handled the shifted and scaled neuronal activations and by utilizing an independent public dataset from the Human Connectome Project.

中文翻译:

使用 3D 卷积神经网络的 fMRI 体积分类对移位和缩放的神经元激活具有鲁棒性

基于深度神经网络 (DNN) 的深度学习方法最近已成功用于神经影像数据的分析。卷积神经网络 (CNN) 是一种 DNN,它采用卷积核覆盖输入样本的局部区域并在样本上移动,为后续层提供特征图。在我们的研究中,我们假设具有下采样操作(例如池化和/或步幅)的 3D-CNN 模型能够从单个功能性 MRI (fMRI) 体积中移位和缩放的神经元激活中提取稳健的特征图,用于与该卷关联的任务信息的分类。因此,3D-CNN 模型将能够改善由空间对齐算法的缺陷引起的神经元激活的潜在错位和局部大脑区域的过度/激活不足,以及由血氧水平依赖 (BOLD) 响应的可变性混淆跨会话和/或主题。为此,从四个感觉运动任务(左手握紧、右手握紧、听觉注意力和视觉刺激)中获得的 fMRI 体积被用作我们的 3D-CNN 模型的输入,以使用单个 fMRI 体积对任务信息进行分类。使用从各种最小预处理场景中获得的 fMRI 体积系统地评估 3D-CNN 的分类性能,这些 fMRI 体积应用于原始 fMRI 体积,这些体积排除了对模板的空间归一化,以及从包括空间归一化的完整预处理中获得的那些体积。替代分类器模型,例如一维全连接 DNN (1D-fcDNN) 和支持向量机 (SVM) 也用于比较。还评估了几种 k 折交叉验证 (CV) 方案的分类性能,包括留一主题 CV (LOOCV)。总体而言,3D-CNN 模型的分类结果优于 1D-fcDNN 和 SVM 模型。当使用具有 LOOCV 的完全处理的 fMRI 体积时,3D-CNN、1D-fcDNN 和 SVM 模型的平均错误率(± 平均值的标准误差)为 2。分别为 1% (± 0.9)、3.1% (± 1.2) 和 4.1% (± 1.5)(单向方差分析的 p = 0.041)。3 倍 CV 的错误率更高(2.4% ± 1.0、4.2% ± 1.3 和 10.1% ± 2.0;单向方差分析的 p < 0.0003)。使用未经预处理的原始 fMRI 3D 体数据的平均错误率也显着增加(3D-CNN 为 26.2%,1D-fcDNN 为 75.0%,SVM 为 75.0%)。此外,预训练的 3D-CNN 模型处理移位和缩放神经元激活的能力在五类分类(即四个感觉运动任务和静息状态)的在线场景中使用三个实时 fMRI 进行了证明。参与者。3D-CNN、1D-fcDNN 和 SVM 模型的分类准确率分别为 78.5% (± 1.4)、26.7% (± 5.9) 和 21.5% (± 3.1)。
更新日期:2020-12-01
down
wechat
bug