An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data.
An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data.
复制标题
DOI：
10.1016/j.media.2022.102413
复制
发表时间：
2022-05
影响因子：
10.9
通讯作者：
Sui, Jing
中科院分区：
文献类型：
--
作者：
Zhao, Min;Yan, Weizheng;Luo, Na;Zhi, Dongmei;Fu, Zening;Du, Yuhui;Yu, Shan;Jiang, Tianzi;Calhoun, Vince D;Sui, Jing
功能性磁共振成像（FMRI）作为研究精神病的有前途的工具，可以分解为有用的成像特征，例如独立组件（IC）的时间课程（TC）和功能网络连接性（FNC），该功能网络连接（FNC）通过TC交叉互动的临时动态进行了临时的特征。然而，很少有研究能够通过此方面的方式来利用其完整性信息，以学习多个方面的最佳表示。具体来说，提出了C-RN NAM的临时动态依赖性（AM），以自动从TC节点中学习判别性知识，而DNN则用于确定最大的歧视FNC模式，并通过层次依赖层次构建了一个conterfiation note temant conterf temant not temant。被验证多站点的精神分裂症（SZ，N〜1100）和公共自闭症数据集（Abide，n〜1522），以2.8-8.9％的替代模型，包括使用静态FNC或TCS的8个模型，使用了4个模型，使用了4.3％的自动化大多数组歧视大脑区域都可以易于归因和可视化，提供有意义的生物学解释性，并突出提出的HDLFCA模型在鉴定有效的神经影像生物标志物中的巨大潜力。
Functional magnetic resonance imaging (fMRI) as a promising tool to investigate psychotic disorders can be decomposed into useful imaging features such as time courses (TCs) of independent components (ICs) and functional network connectivity (FNC) calculated by TC cross-correlation. TCs reflect the temporal dynamics of brain activity and the FNC characterizes temporal coherence across intrinsic brain networks. Both features have been used as input to deep learning approaches with decent results. However, few studies have tried to leverage their complementary information to learn optimal representations at multiple facets. Motivated by this, we proposed a Hybrid Deep Learning Framework integrating brain Connectivity and Activity (HDLFCA) together by combining convolutional recurrent neural network (C-RNN) and deep neural network (DNN), aiming to improve classification accuracy and interpretability simultaneously. Specifically, C-RNNAM was proposed to extract temporal dynamic dependencies with an attention module (AM) to automatically learn discriminative knowledge from TC nodes, while DNN was applied to identify the most group-discriminative FNC patterns with layer-wise relevance propagation (LRP). Then, both prediction outputs were concatenated to build a new feature matrix, generating the final decision by logistic regression. The effectiveness of HDLFCA was validated on both multi-site schizophrenia (SZ, n ~ 1100) and public autism datasets (ABIDE, n ~ 1522) by outperforming 12 alternative models at 2.8–8.9% accuracy, including 8 models using either static FNC or TCs and 4 models using dynamic FNC. Appreciable classification accuracy was achieved for HC vs. SZ (85.3%) and HC vs. Autism (72.4%) respectively. More importantly, the most group-discriminative brain regions can be easily attributed and visualized, providing meaningful biological interpretability and highlighting the great potential of the proposed HDLFCA model in the identification of valid neuroimaging biomarkers.