TY - JOUR
T1 - Modality-Aware Discriminative Fusion Network for Integrated Analysis of Brain Imaging Genomics
AU - Sheng, Xiaoqi
AU - Cai, Hongmin
AU - Nie, Yongwei
AU - He, Shengfeng
AU - Cheung, Yiu-Ming
AU - Chen, Jiazhou
N1 - This work was supported in part by the National Key Research and Development Program of China under Grant 2022YFE0112200; in part by the Key Research and Development Program of Guangzhou under Grant 2023B01J0002; in part by the National Natural Science Foundation of China under Grant 62325204, Grant U21A20520, Grant 62102153, Grant 62272326, and Grant 62172112; in part by the Science and Technology Project of Guangdong Province under Grant 2022A0505050014; in part by the Key-Area Research and Development Program of Guangzhou City under Grant 202206030009; in part by the Natural Science Foundation of Guangdong Province of China under Grant 2022A1515011162 and Grant 2023A1515012894; in part by Guangdong Natural Science Funds for Distinguished Young Scholar under Grant 2023B1515020097; in part by Singapore MOE Tier 1 Funds under Grant MSS23C002; in part by NRF Singapore under AI Singapore Program under Grant AISG3-GV-2023-011; and in part by the Alzheimer’s Disease Neuroimaging Initiative (ADNI).
PY - 2024/8/23
Y1 - 2024/8/23
N2 - Mild cognitive impairment (MCI) represents an early stage of Alzheimer’s disease (AD), characterized by subtle clinical symptoms that pose challenges for accurate diagnosis. The quest for the identification of MCI individuals has highlighted the importance of comprehending the underlying mechanisms of disease causation. Integrated analysis of brain imaging and genomics offers a promising avenue for predicting MCI risk before clinical symptom onset. However, most existing methods face challenges in: 1) mining the brain network-specific topological structure and addressing the single nucleotide polymorphisms (SNPs)-related noise contamination and 2) extracting the discriminative properties of brain imaging genomics, resulting in limited accuracy for MCI diagnosis. To this end, a modality-aware discriminative fusion network (MA-DFN) is proposed to integrate the complementary information from brain imaging genomics to diagnose MCI. Specifically, we first design two modality-specific feature extraction modules: the graph convolutional network with edge-augmented self-attention module (GCN-EASA) and the deep adversarial denoising autoencoder module (DAD-AE), to capture the topological structure of brain networks and the intrinsic distribution of SNPs. Subsequently, a discriminative-enhanced fusion network with correlation regularization module (DFN-CorrReg) is employed to enhance inter-modal consistency and between-class discrimination in brain imaging and genomics. Compared to other state-of-the-art approaches, MA-DFN not only exhibits superior performance in stratifying cognitive normal (CN) and MCI individuals but also identifies disease-related brain regions and risk SNPs locus, which hold potential as putative biomarkers for MCI diagnosis.
AB - Mild cognitive impairment (MCI) represents an early stage of Alzheimer’s disease (AD), characterized by subtle clinical symptoms that pose challenges for accurate diagnosis. The quest for the identification of MCI individuals has highlighted the importance of comprehending the underlying mechanisms of disease causation. Integrated analysis of brain imaging and genomics offers a promising avenue for predicting MCI risk before clinical symptom onset. However, most existing methods face challenges in: 1) mining the brain network-specific topological structure and addressing the single nucleotide polymorphisms (SNPs)-related noise contamination and 2) extracting the discriminative properties of brain imaging genomics, resulting in limited accuracy for MCI diagnosis. To this end, a modality-aware discriminative fusion network (MA-DFN) is proposed to integrate the complementary information from brain imaging genomics to diagnose MCI. Specifically, we first design two modality-specific feature extraction modules: the graph convolutional network with edge-augmented self-attention module (GCN-EASA) and the deep adversarial denoising autoencoder module (DAD-AE), to capture the topological structure of brain networks and the intrinsic distribution of SNPs. Subsequently, a discriminative-enhanced fusion network with correlation regularization module (DFN-CorrReg) is employed to enhance inter-modal consistency and between-class discrimination in brain imaging and genomics. Compared to other state-of-the-art approaches, MA-DFN not only exhibits superior performance in stratifying cognitive normal (CN) and MCI individuals but also identifies disease-related brain regions and risk SNPs locus, which hold potential as putative biomarkers for MCI diagnosis.
KW - Brain imaging genomics
KW - early diagnosis
KW - mild cognitive impairment (MCI)
KW - multimodal fusion
U2 - 10.1109/TNNLS.2024.3439530
DO - 10.1109/TNNLS.2024.3439530
M3 - Journal article
SN - 2162-237X
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
ER -