End-stage renal disease accompanied by mild cognitive impairment: A study and analysis of trimodal brain network fusion

Abstract

The function and structure of brain networks (BN) may undergo changes in patients with end-stage renal disease (ESRD), particularly in those accompanied by mild cognitive impairment (ESRDaMCI). Many existing methods for fusing BN focus on extracting interaction features between pairs of network nodes from each mode and combining them. This approach overlooks the correlation between different modal features during feature extraction and the potentially valuable information that may exist between more than two brain regions. To address this issue, we propose a model using a multi-head self-attention mechanism to fuse brain functional networks, white matter structural networks, and gray matter structural networks, which results in the construction of brain fusion networks (FBN). Initially, three networks are constructed: the brain function network, the white matter structure network, and the individual-based gray matter structure network. The multi-head self-attention mechanism is then applied to fuse the three types of networks, generating attention weights that are transformed into an optimized model. The optimized model introduces hypergraph popular regular term and L1 norm regular term, leading to the formation of FBN. Finally, FBN is employed in the diagnosis and prediction of ESRDaMCI to evaluate its classification performance and investigate the correlation between discriminative brain regions and cognitive dysfunction. Experimental results demonstrate that the optimal classification accuracy achieved is 92.80%, which is at least 3.63% higher than the accuracy attained using other methods. This outcome confirms the effectiveness of our proposed method. Additionally, the identification of brain regions significantly associated with scores on the Montreal cognitive assessment scale may shed light on the underlying pathogenesis of ESRDaMCI.

Fig 1. Brain fusion network construction framework.

First, the brain function network was constructed using the time series extracted from fMRI, the brain white matter structure network was constructed using FN extracted from DKI, and the individual-based brain gray matter structure network was constructed using KV extracted from DKI. On this basis, the multi-head self-attention mechanism is used to learn the three modes of network interactively, and the attention weight is trained. Then, the value vector is combined to obtain the feature connections and converted into the optimization model. According to the generated feature connections, the hypergraph is constructed, and the HMR and L₁ norm regular terms are introduced into the optimization model to obtain FBN.

Fig 2. Classification accuracy of different head numbers.

Fig 3. Classification accuracy of different neighbors.

Fig 4. Classification accuracy of different regularization parameters.

The best parameter combination is λ = 2⁻², β = 2⁻⁵, and the corresponding ACC is 92.8024%.

Fig 5. Discriminative brain regions.

(a) Sagittal, (b) Axial, (c) Coronal.