Neural Imaging Computation and Analysis Group, State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences Beijing, China.
Front Syst Neurosci. 2012 Sep 3;6:63. doi: 10.3389/fnsys.2012.00063. eCollection 2012.
Attention deficit/hyperactivity disorder (ADHD) is one of the most common diseases in school-age children. To date, the diagnosis of ADHD is mainly subjective and studies of objective diagnostic method are of great importance. Although many efforts have been made recently to investigate the use of structural and functional brain images for the diagnosis purpose, few of them are related to ADHD. In this paper, we introduce an automatic classification framework based on brain imaging features of ADHD patients and present in detail the feature extraction, feature selection, and classifier training methods. The effects of using different features are compared against each other. In addition, we integrate multimodal image features using multi-kernel learning (MKL). The performance of our framework has been validated in the ADHD-200 Global Competition, which is a world-wide classification contest on the ADHD-200 datasets. In this competition, our classification framework using features of resting-state functional connectivity (FC) was ranked the 6th out of 21 participants under the competition scoring policy and performed the best in terms of sensitivity and J-statistic.
注意缺陷多动障碍（ADHD）是学龄儿童中最常见的疾病之一。迄今为止，ADHD 的诊断主要是主观的，因此研究客观的诊断方法非常重要。尽管最近已经有许多研究致力于使用结构和功能脑图像进行诊断目的，但其中很少有研究与 ADHD 相关。在本文中，我们介绍了一种基于 ADHD 患者脑成像特征的自动分类框架，并详细介绍了特征提取、特征选择和分类器训练方法。比较了使用不同特征的效果。此外，我们还使用多核学习（MKL）集成了多模态图像特征。我们的框架的性能已在 ADHD-200 全球竞赛中得到验证，该竞赛是一个针对 ADHD-200 数据集的全球分类竞赛。在该竞赛中，我们的分类框架使用静息态功能连接（FC）的特征，在竞赛评分政策下排名第 6，在灵敏度和 J 统计量方面表现最佳。
