Wee Chong-Yaw, Yap Pew-Thian, Zhang Daoqiang, Denny Kevin, Wang Lihong, Shen Dinggang
Department of Radiology and Biomedical Research Imaging Center (BRIC), University of North Carol at Chapel Hill, NC, USA.
Med Image Comput Comput Assist Interv. 2011;14(Pt 2):277-84. doi: 10.1007/978-3-642-23629-7_34.
Alzheimer's disease (AD), is difficult to diagnose due to the subtlety of cognitive impairment. Recent emergence of reliable network characterization techniques based on diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) has made the understanding of neurological disorders at a whole-brain connectivity level possible, providing new avenues for brain classification. Taking a multi-kernel SVM, we attempt to integrate these two imaging modalities for improving classification performance. Our results indicate that the multimodality classification approach performs better than the single modality approach, with statistically significant improvement in accuracy. It was also found that the prefrontal cortex, orbitofrontal cortex, temporal pole, anterior and posterior cingulate gyrus, precuneus, amygdala, thalamus, parahippocampal gyrus and insula regions provided the most discriminant features for classification, in line with the results reported in previous studies. The multimodality classification approach allows more accurate early detection of brain abnormalities with larger sensitivity, and is important for treatment management of potential AD patients.
阿尔茨海默病（AD）由于认知障碍的微妙性而难以诊断。基于扩散张量成像（DTI）和静息态功能磁共振成像（rs-fMRI）的可靠网络表征技术的最新出现，使得在全脑连通性水平上理解神经疾病成为可能，为脑部分类提供了新途径。采用多核支持向量机，我们试图整合这两种成像方式以提高分类性能。我们的结果表明，多模态分类方法比单模态方法表现更好，在准确性上有统计学意义的提高。还发现前额叶皮质、眶额皮质、颞极、前扣带回和后扣带回、楔前叶、杏仁核、丘脑、海马旁回和脑岛区域为分类提供了最具判别力的特征，这与先前研究报告的结果一致。多模态分类方法能够以更高的敏感性更准确地早期检测脑异常，对潜在AD患者的治疗管理很重要。
