Robust, Generalizable, and Interpretable Artificial Intelligence-Derived Brain Fingerprints of Autism and Social Communication Symptom Severity.
Robust, Generalizable, and Interpretable Artificial Intelligence-Derived Brain Fingerprints of Autism and Social Communication Symptom Severity.
复制标题
DOI：
10.1016/j.biopsych.2022.02.005
复制
发表时间：
2022-10-15
影响因子：
10.6
通讯作者：
中科院分区：
文献类型：
--
作者：
自闭症谱系障碍(ASD)是最普遍的神经发育障碍之一；然而，ASD的神经生物学仍然知之甚少，因为动力不足的个体研究得出的不一致的结果排除了对临床症状的可靠和可解释的神经生物学标志物和预测因子的识别。我们利用多个脑成像队列和可解释人工智能(XAI)的令人兴奋的最新进展，开发了一个新的时空深层神经网络(StDNN)模型，该模型识别稳健和可解释的动态脑标记，将ASD与神经典型对照区分开来，并预测临床症状严重程度。在对来自多点遵守队列(N=834)的数据的交叉验证分析中，stDNN获得了始终如一的高分类精度。至关重要的是，stDNN还准确地对来自独立斯坦福大学(N=202)和GENDAAR(N=90)队列的数据进行了分类，而无需额外的培训。StDNN不能区分注意缺陷多动障碍和神经典型对照，突出了模型的特异性。Xai揭示，大脑功能与后扣带皮质(PCC)和楔前叶、背外侧和腹外侧额前皮质以及颞上沟相关，它们分别支撑着默认模式网络(DMN)、认知控制和人类语音处理系统，最明显地将ASD与三个队列中的神经典型对照区分开来。此外，与DMN的PCC和楔前结节相关的特征可以作为核心社交和沟通缺陷严重程度的可靠预测因子，但不能预测ASD中的限制性/重复行为。我们的发现在独立队列中重复，揭示了ASD精神病理学的强大个性化功能脑指纹，这可能导致更客观和准确的表型特征和有针对性的治疗。
Autism spectrum disorder (ASD) is among the most pervasive neurodevelopmental disorders; yet the neurobiology of ASD is still poorly understood as inconsistent findings from underpowered individual studies preclude the identification of robust and interpretable neurobiological markers and predictors of clinical symptoms. We leverage multiple brain imaging cohorts and exciting recent advances in explainable artificial intelligence (XAI), to develop a novel spatiotemporal deep neural network (stDNN) model, which identifies robust and interpretable dynamic brain markers that distinguish ASD from neurotypical controls and predict clinical symptom severity. stDNN achieved consistently high classification accuracies in cross-validation analysis of data from the multisite ABIDE cohort (N = 834). Crucially, stDNN also accurately classified data from independent Stanford (N = 202) and GENDAAR (N = 90) cohorts without additional training. stDNN could not distinguish attention-deficit hyperactivity disorder from neurotypical controls, highlighting the model specificity. XAI revealed that brain features associated with the posterior cingulate cortex (PCC) and precuneus, dorsolateral and ventrolateral prefrontal cortex, and superior temporal sulcus, which anchor the default mode network (DMN), cognitive control and human voice processing systems, respectively, most clearly distinguished ASD from neurotypical controls in the three cohorts. Furthermore, features associated with PCC and precuneus nodes of the DMN emerged as robust predictors of the severity of core social and communication deficits but not restricted/repetitive behaviors in ASD. Our findings, replicated across independent cohorts, reveal robust individualized functional brain fingerprints of ASD psychopathology, which could lead to more objective and precise phenotypic characterization and targeted treatments.
登录
查看更多内容
影响因子：
3.9
作者：
Gotham, Katherine;Pickles, Andrew;Lord, Catherine
通讯作者：
Lord, Catherine
人脑网络组图谱：基于连接架构的新大脑图谱
DOI：
10.1093/cercor/bhw157
发表时间：
2016-08
期刊：
Cerebral cortex (New York, N.Y. : 1991)
影响因子：
--
作者：
Fan L;Li H;Zhuo J;Zhang Y;Wang J;Chen L;Yang Z;Chu C;Xie S;Laird AR;Fox PT;Eickhoff SB;Yu C;Jiang T
通讯作者：
Jiang T
DOI：
10.1016/j.bpsc.2017.10.005
发表时间：
2018-03
期刊：
Biological psychiatry. Cognitive neuroscience and neuroimaging
影响因子：
--
作者：
Cai W;Chen T;Szegletes L;Supekar K;Menon V
通讯作者：
Menon V
影响因子：
11
作者：
Di Martino, A.;Yan, C-G;Li, Q.;Denio, E.;Castellanos, F. X.;Alaerts, K.;Anderson, J. S.;Assaf, M.;Bookheimer, S. Y.;Dapretto, M.;Deen, B.;Delmonte, S.;Dinstein, I.;Ertl-Wagner, B.;Fair, D. A.;Gallagher, L.;Kennedy, D. P.;Keown, C. L.;Keysers, C.;Lainhart, J. E.;Lord, C.;Luna, B.;Menon, V.;Minshew, N. J.;Monk, C. S.;Mueller, S.;Mueller, R. A.;Nebel, M. B.;Nigg, J. T.;O'Hearn, K.;Pelphrey, K. A.;Peltier, S. J.;Rudie, J. D.;Sunaert, S.;Thioux, M.;Tyszka, J. M.;Uddin, L. Q.;Verhoeven, J. S.;Wenderoth, N.;Wiggins, J. L.;Mostofsky, S. H.;Milham, M. P.
通讯作者：
Milham, M. P.
影响因子：
4.4
作者：
Aghdam, Maryam Akhavan;Sharifi, Arash;Pedram, Mir Mohsen
通讯作者：
Pedram, Mir Mohsen