Brain Development Imaging Laboratories, Department of Psychology, San Diego State University, San Diego, California.
Department of Bioinformatics and Medical Informatics, San Diego State University, San Diego, California.
Brain Connect. 2019 Oct;9(8):604-612. doi: 10.1089/brain.2019.0689. Epub 2019 Aug 23.
Machine learning techniques have been implemented to reveal brain features that distinguish people with autism spectrum disorders (ASDs) from typically developing (TD) peers. However, it remains unknown whether different neuroimaging modalities are equally informative for diagnostic classification. We combined anatomical magnetic resonance imaging (aMRI), diffusion weighted imaging (DWI), and functional connectivity MRI (fcMRI) using conditional random forest (CRF) for supervised learning to compare how informative each modality was in diagnostic classification. In-house data ( = 93) included 47 TD and 46 ASD participants, matched on age, motion, and nonverbal IQ. Four main analyses consistently indicated that fcMRI variables were significantly more informative than anatomical variables from aMRI and DWI. This was found (1) when the top 100 variables from CRF (run separately in each modality) were combined for multimodal CRF; (2) when only 19 top variables reaching >67% accuracy in each modality were combined in multimodal CRF; and (3) when the large number of initial variables (before dimension reduction) potentially biasing comparisons in favor of fcMRI was reduced using a less granular region of interest scheme. Consistent superiority of fcMRI was even found (4) when 100 variables per modality were randomly selected, removing any such potential bias. Greater informative value of functional than anatomical modalities may relate to the nature of fcMRI data, reflecting more closely behavioral condition, which is also the basis of diagnosis, whereas brain anatomy may be more reflective of neurodevelopmental history.
机器学习技术已被应用于揭示区分自闭症谱系障碍（ASD）患者和正常发育（TD）个体的大脑特征。然而，不同的神经影像学模态对于诊断分类是否同样具有信息量尚不清楚。我们使用条件随机场（CRF）结合解剖磁共振成像（aMRI）、弥散加权成像（DWI）和功能连接磁共振成像（fcMRI）进行监督学习，比较每种模态在诊断分类中的信息量。内部数据（n=93）包括 47 名 TD 和 46 名 ASD 参与者，在年龄、运动和非言语智商方面进行匹配。四项主要分析一致表明，fcMRI 变量比来自 aMRI 和 DWI 的解剖变量更具信息量。这是通过以下方式发现的：（1）在每个模态中分别运行的 CRF 的前 100 个变量的组合进行多模态 CRF；（2）在每个模态中仅组合达到 >67%准确率的 19 个前变量的多模态 CRF；（3）在使用较少粒度的感兴趣区域方案减少可能有利于 fcMRI 的初始变量数量（在降维之前）的情况下；（4）即使在每个模态随机选择 100 个变量的情况下，也能发现 fcMRI 的一致性优势，从而消除了任何这种潜在的偏差。功能模态比解剖模态更具信息量，这可能与 fcMRI 数据的性质有关，因为它更紧密地反映了行为条件，这也是诊断的基础，而大脑解剖可能更反映神经发育史。
