Tang Yibin, Sun Jia, Wang Chun, Zhong Yuan, Jiang Aimin, Liu Gang, Liu Xiaofeng
College of Internet of Things Engineering, Hohai University, Changzhou 213000, Jiangsu, China.
Department of Mood Disorders, Nanjing Brain Hospital, and Nanjing Medical University, Nanjing 210000, Jiangsu, China.
Artif Intell Med. 2022 Jan;123:102209. doi: 10.1016/j.artmed.2021.102209. Epub 2021 Nov 16.
Attention Deficit Hyperactivity Disorder (ADHD) is a highly prevalent neurodevelopmental disease of school-age children. Early diagnosis is crucial for ADHD treatment, wherein its neurobiological diagnosis (or classification) is helpful and provides the objective evidence to clinicians. The existing ADHD classification methods suffer two problems, i.e., insufficient data and feature noise disturbance from other associated disorders. As an attempt to overcome these difficulties, a novel deep-learning classification architecture based on a binary hypothesis testing framework and a modified auto-encoding (AE) network is proposed in this paper. The binary hypothesis testing framework is introduced to cope with insufficient data of ADHD database. Brain functional connectivities (FCs) of test data (without seeing their labels) are incorporated during feature selection along with those of training data and affect the sequential deep learning procedure under binary hypotheses. On the other hand, the modified AE network is developed to capture more effective features from training data, such that the difference of inter- and intra-class variability scores between binary hypotheses can be enlarged and effectively alleviate the disturbance of feature noise. On the test of ADHD-200 database, our method significantly outperforms the existing classification methods. The average accuracy reaches 99.6% with the leave-one-out cross validation. Our method is also more robust and practically convenient for ADHD classification due to its uniform parameter setting across various datasets.
注意缺陷多动障碍（ADHD）是学龄儿童中一种高度流行的神经发育疾病。早期诊断对ADHD治疗至关重要，其中神经生物学诊断（或分类）很有帮助，并为临床医生提供客观依据。现有的ADHD分类方法存在两个问题，即数据不足以及来自其他相关疾病的特征噪声干扰。作为克服这些困难的一种尝试，本文提出了一种基于二元假设检验框架和改进自编码器（AE）网络的新型深度学习分类架构。引入二元假设检验框架以应对ADHD数据库数据不足的问题。在特征选择过程中，将测试数据（不看其标签）的脑功能连接（FC）与训练数据的脑功能连接合并，并在二元假设下影响顺序深度学习过程。另一方面，开发改进的AE网络以从训练数据中捕获更有效的特征，从而扩大二元假设之间类间和类内变异分数的差异，并有效减轻特征噪声的干扰。在ADHD - 200数据库测试中，我们的方法明显优于现有的分类方法。采用留一法交叉验证时，平均准确率达到99.6%。由于我们的方法在各种数据集上具有统一的参数设置，因此对于ADHD分类也更稳健且实际应用更方便。
