Department of Artificial Intelligence, Yonsei University, 03722 Seoul, Republic of Korea.
Department of Computer Science, Yonsei University, 03722 Seoul, Republic of Korea.
J Integr Neurosci. 2024 Jul 17;23(7):135. doi: 10.31083/j.jin2307135.
Autism spectrum disorder (ASD) is a neurodevelopmental disorder exhibiting heterogeneous characteristics in patients, including variability in developmental progression and distinct neuroanatomical features influenced by sex and age. Recent advances in deep learning models based on functional connectivity (FC) graphs have produced promising results, but they have focused on generalized global activation patterns and failed to capture specialized regional characteristics and accurately assess disease indications.
To overcome these limitations, we propose a novel deep learning method that models FC with multi-head attention, which enables simultaneous modeling of the intricate and variable patterns of brain connectivity associated with ASD, effectively extracting abnormal patterns of brain connectivity. The proposed method not only identifies region-specific correlations but also emphasizes connections at specific, transient time points from diverse perspectives. The extracted FC is transformed into a graph, assigning weighted labels to the edges to reflect the degree of correlation, which is then processed using a graph neural network capable of handling edge labels.
Experiments on the autism brain imaging data exchange (ABIDE) I and II datasets, which include a heterogeneous cohort, showed superior performance over the state-of-the-art methods, improving accuracy by up to 3.7%p. The incorporation of multi-head attention in FC analysis markedly improved the distinction between typical brains and those affected by ASD. Additionally, the ablation study validated diverse brain characteristics in ASD patients across different ages and sexes, offering insightful interpretations.
These results emphasize the effectiveness of the method in enhancing diagnostic accuracy and its potential in advancing neurological research for ASD diagnosis.
自闭症谱系障碍（ASD）是一种神经发育障碍，患者表现出异质性特征，包括发育进展的可变性和受性别和年龄影响的独特神经解剖特征。基于功能连接（FC）图的深度学习模型的最新进展取得了有希望的结果，但它们侧重于广义的全局激活模式，未能捕捉专门的区域特征并准确评估疾病指征。
为了克服这些限制，我们提出了一种新的深度学习方法，该方法使用多头注意力来对 FC 进行建模，从而能够同时对与 ASD 相关的大脑连接的复杂和多变模式进行建模，有效地提取大脑连接的异常模式。该方法不仅可以识别特定区域的相关性，还可以从多个角度强调特定、瞬时时间点的连接。提取的 FC 被转换为一个图，为边缘分配加权标签以反映相关性的程度，然后使用能够处理边缘标签的图神经网络对其进行处理。
在包括异质队列的自闭症脑成像数据交换（ABIDE）I 和 II 数据集上的实验表明，该方法优于最先进的方法，准确性提高了 3.7%p。在 FC 分析中引入多头注意力可以显著提高典型大脑和受 ASD 影响的大脑之间的区分度。此外，消融研究验证了不同年龄和性别的 ASD 患者的不同大脑特征，提供了有见地的解释。
这些结果强调了该方法在提高诊断准确性方面的有效性，以及其在推进 ASD 诊断的神经科学研究方面的潜力。
