ORIGINAL RESEARCH article
Front. Neurosci.
Sec. Brain Imaging Methods
Volume 19 - 2025 | doi: 10.3389/fnins.2025.1637291
This article is part of the Research TopicAdvances in brain diseases: leveraging multimodal data and artificial intelligence for diagnosis, prognosis, and treatmentView all articles
A Lightweight Triple-Modal Fusion Network for Progressive Mild Cognitive Impairment Prediction in Alzheimer's Disease
Provisionally accepted- 1Hangzhou Dianzi University, Hangzhou, China
- 2Department of Laboratory Medicine, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China
- 3Department of Radiation Oncology, Shenzhen People's Hospital (the Second Clinical Medical College, Ji'nan University; the First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, China
- 4School of Information Technology, Zhejiang Institute of Economics and Trade, Hangzhou, China
- 5Department of Radiology, The Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
- 6Department of Interventional Vascular Surgery, the Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
- 7Shenzhen Hospital of Southern Medical University, Shenzhen, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
As a progressive neurodegeneration, Alzheimer's disease (AD) represents the primary etiology of dementia among the elderly. Early identification of individuals with mild cognitive impairment (MCI) who are likely to convert to AD is essential for timely diagnosis and therapeutic intervention.Although multimodal neuroimaging and clinical data provide complementary information, existing fusion models often face challenges such as high computational complexity and limited interpretability. To address these limitations, we introduce TriLightNet, an innovative lightweight triple-modal fusion network designed to integrate structural MRI, functional PET, and clinical tabular data for predicting MCI-to-AD conversion. TriLightNet incorporates a hybrid backbone that combines Kolmogorov-Arnold Networks with PoolFormer for efficient feature extraction. Additionally, it introduces a Hybrid Block Attention Module to capture subtle interactions between image and clinical features and employs a MultiModal Cascaded Attention mechanism to enable progressive and efficient fusion across the modalities. These components work together to streamline multimodal data integration while preserving meaningful insights. Extensive experiments conducted on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate the effectiveness of TriLightNet, showcasing superior performance compared to stateof-the-art methods. Specifically, the model achieves an accuracy of 81.25%, an AUROC of 0.8146, 1 Sample et al.and an F1-score of 69.39%, all while maintaining reduced computational costs. Furthermore, its interpretability was validated using the Integrated Gradients method, which revealed clinically relevant brain regions contributing to the predictions, enhancing its potential for meaningful clinical application. Our code is available at https://github.com/sunyzhi55/TriLightNet.
Keywords: Alzheimer's disease, Mild Cognitive Impairment, Triple-Modal Fusion, Lightweight neural network, attention mechanism, Integrated gradients
Received: 30 May 2025; Accepted: 04 Aug 2025.
Copyright: © 2025 Shen, Hu, Zhang, Fu, Xu, Lyu, Xie, Shi, Shi, Li and Gao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Lisi Li, Shenzhen Hospital of Southern Medical University, Shenzhen, China
Yuantong Gao, Department of Radiology, The Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.