College of Engineering, Southern University of Science and Technology, Shenzhen, 518055, China; Centre for High Performance Computing, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China.
Centre for High Performance Computing, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China.
Comput Biol Med. 2022 Sep;148:105854. doi: 10.1016/j.compbiomed.2022.105854. Epub 2022 Jul 15.
The development of noninvasive brain imaging such as resting-state functional magnetic resonance imaging (rs-fMRI) and its combination with AI algorithm provides a promising solution for the early diagnosis of Autism spectrum disorder (ASD). However, the performance of the current ASD classification based on rs-fMRI still needs to be improved. This paper introduces a classification framework to aid ASD diagnosis based on rs-fMRI. In the framework, we proposed a novel filter feature selection method based on the difference between step distribution curves (DSDC) to select remarkable functional connectivities (FCs) and utilized a multilayer perceptron (MLP) which was pretrained by a simplified Variational Autoencoder (VAE) for classification. We also designed a pipeline consisting of a normalization procedure and a modified hyperbolic tangent (tanh) activation function to replace the classical tanh function, further improving the model accuracy. Our model was evaluated by 10 times 10-fold cross-validation and achieved an average accuracy of 78.12%, outperforming the state-of-the-art methods reported on the same dataset. Given the importance of sensitivity and specificity in disease diagnosis, two constraints were designed in our model which can improve the model's sensitivity and specificity by up to 9.32% and 10.21%, respectively. The added constraints allow our model to handle different application scenarios and can be used broadly.
非侵入性脑成像技术（如静息态功能磁共振成像 rs-fMRI）的发展及其与人工智能算法的结合，为自闭症谱系障碍（ASD）的早期诊断提供了有前途的解决方案。然而，目前基于 rs-fMRI 的 ASD 分类性能仍有待提高。本文介绍了一种基于 rs-fMRI 的 ASD 诊断分类框架。在该框架中，我们提出了一种基于阶跃分布曲线（DSDC）差异的新的滤波器特征选择方法，以选择显著的功能连接（FC），并利用简化变分自动编码器（VAE）预训练的多层感知机（MLP）进行分类。我们还设计了一个包含归一化过程和修正双曲正切（tanh）激活函数的流水线，以替代经典的 tanh 函数，进一步提高模型的准确性。我们的模型通过 10 次 10 折交叉验证进行评估，平均准确率为 78.12%，优于在同一数据集上报告的最新方法。考虑到疾病诊断中敏感性和特异性的重要性，我们的模型中设计了两个约束条件，这两个约束条件可以将模型的敏感性和特异性分别提高 9.32%和 10.21%。添加的约束条件使我们的模型能够处理不同的应用场景，并具有广泛的适用性。
