Laboratory for Social and Neural Systems Research, SNS-Lab, University of Zurich, Rämistrasse 100, CH-8091, Zurich, Switzerland.
Institute for Biomedical Engineering, ETH Zurich and University of Zurich, Zurich, Switzerland.
MAGMA. 2024 Dec;37(6):1031-1046. doi: 10.1007/s10334-024-01197-0. Epub 2024 Aug 29.
Despite the prevalent use of the general linear model (GLM) in fMRI data analysis, assuming a pre-defined hemodynamic response function (HRF) for all voxels can lead to reduced reliability and may distort the inferences derived from it. To overcome the necessity of presuming a specific model for the hemodynamic response, we introduce a semi-supervised automatic detection (SAD) method.
The proposed SAD method employs a Bi-LSTM neural network to classify high temporal resolution fMRI data. Network training utilized an fMRI dataset with 75-ms temporal resolution in an iterative scheme. Classification performance was evaluated on a second fMRI dataset from the same participant, collected on a different day. Comparative analysis with the standard GLM approach was conducted to evaluate the cooperative effectiveness of the SAD method.
The SAD method performed well based on the classification scores: true-positive rate = 0.961, area under the receiver operating curve = 0.998, true-negative rate = 0.99, F1-score = 0.979, False-negative rate = 0.038, false-discovery rate = 0.002, false-positive rate = 0.002 at 75-ms temporal resolution.
SAD can detect hemodynamic responses at 75-ms temporal resolution without relying on a specific shape of an HRF. Future work could expand the use cases to include more participants and different fMRI paradigms.
尽管在 fMRI 数据分析中普遍使用了广义线性模型（GLM），但是假设所有体素都有一个预先定义的血液动力学响应函数（HRF）可能会降低可靠性，并且可能会扭曲从中得出的推论。为了克服对血液动力学响应假设特定模型的必要性，我们引入了一种半监督自动检测（SAD）方法。
所提出的 SAD 方法使用 Bi-LSTM 神经网络对高时间分辨率 fMRI 数据进行分类。网络训练利用了具有 75-ms 时间分辨率的 fMRI 数据集，采用迭代方案进行。分类性能在来自同一参与者的第二个 fMRI 数据集上进行评估，该数据集是在不同的日子采集的。与标准 GLM 方法进行了比较分析，以评估 SAD 方法的协同有效性。
SAD 方法基于分类得分表现良好：真阳性率=0.961，接收者操作曲线下面积=0.998，真阴性率=0.99，F1 分数=0.979，假阴性率=0.038，假发现率=0.002，假阳性率=0.002，时间分辨率为 75-ms。
SAD 可以在不依赖于特定 HRF 形状的情况下检测到 75-ms 时间分辨率的血液动力学响应。未来的工作可以扩展用例，包括更多的参与者和不同的 fMRI 范式。
