{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T03:01:50Z","timestamp":1793156510802,"version":"4.5.0"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>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.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Extensive experiments conducted on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate the effectiveness of TriLightNet, showcasing superior performance compared to state-of-the-art methods. Specifically, the model achieves an accuracy of 81.25%, an AUROC of 0.8146, and an F1-score of 69.39%, all while maintaining reduced computational costs.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>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 <jats:ext-link>https:\/\/github.com\/sunyzhi55\/TriLightNet<\/jats:ext-link>.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnins.2025.1637291","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T05:27:50Z","timestamp":1756186070000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["A lightweight triple-modal fusion network for progressive mild cognitive impairment prediction in Alzheimer's disease"],"prefix":"10.3389","volume":"19","author":[{"given":"Xiangyu","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renfeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunzhan","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiamin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Degang","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbiao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deen","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changsheng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuantong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3473541","article-title":"Enhancing early Alzheimer's disease detection through big data and ensemble few-shot learning","author":"Atitallah","year":"2024","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3750","DOI":"10.1109\/JBHI.2024.3373703","article-title":"Predicting progression from mild cognitive impairment to Alzheimer's dementia with adversarial attacks","volume":"28","author":"Bayta\u015f","year":"2024","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B3","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1109\/JBHI.2024.3472462","article-title":"Longitudinal Alzheimer's disease progression prediction with modality uncertainty and optimization of information flow","volume":"29","year":"2025","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.00946","article-title":"Gkan: Explainable diagnosis of Alzheimer's disease using graph neural network with Kolmogorov-Arnold networks","author":"Ding","year":"2025","journal-title":"arXiv"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv"},{"key":"B6","doi-asserted-by":"publisher","first-page":"103503","DOI":"10.1016\/j.media.2025.103503","article-title":"Hyperfusion: a hypernetwork approach to multimodal integration of tabular and medical imaging data for predictive modeling","volume":"102","author":"Duenias","year":"2025","journal-title":"Med. Image Anal"},{"key":"B7","doi-asserted-by":"publisher","first-page":"124780","DOI":"10.1016\/j.eswa.2024.124780","article-title":"Alzheimer's disease diagnosis from single and multimodal data using machine and deep learning models: achievements and future directions","volume":"255","author":"Elazab","year":"2024","journal-title":"Expert Syst. Appl"},{"key":"B8","doi-asserted-by":"publisher","first-page":"5416","DOI":"10.3390\/s21165416","article-title":"A personalized computer-aided diagnosis system for mild cognitive impairment (MCI) using structural MRI (sMRI)","volume":"21","author":"El-Gamal","year":"2021","journal-title":"Sensors"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.06559","article-title":"Tabkan: advancing tabular data analysis using Kolmogorov-Arnold network","author":"Eslamian","year":"2025","journal-title":"arXiv"},{"key":"B10","doi-asserted-by":"publisher","first-page":"102529","DOI":"10.1016\/j.compmedimag.2025.102529","article-title":"Class balancing diversity multimodal ensemble for Alzheimer's disease diagnosis and early detection","volume":"123","author":"Francesconi","year":"2025","journal-title":"Comput. Med. Imaging Graph"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.08806","article-title":"Tabkanet: tabular data modeling with Kolmogorov-Arnold network and transformer","author":"Gao","year":"2024","journal-title":"arXiv"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e0067346","DOI":"10.1371\/journal.pone.0067346","article-title":"Brainage in mild cognitive impaired patients: predicting the conversion to Alzheimer's disease","volume":"8","author":"Gaser","year":"2013","journal-title":"PLoS ONE"},{"key":"B13","first-page":"1","article-title":"\u201cNNMAMBA: 3D biomedical image segmentation, classification and landmark detection with state space model,\u201d","volume-title":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","author":"Gong","year":"2025"},{"key":"B14","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s12553-024-00823-0","article-title":"Early detection of dementia using artificial intelligence and multimodal features with a focus on neuroimaging: a systematic literature review","volume":"14","author":"Grigas","year":"2024","journal-title":"Health Technol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1527582","DOI":"10.3389\/fninf.2025.1527582","article-title":"Contrastive self-supervised learning for neurodegenerative disorder classification","volume":"19","author":"Gryshchuk","year":"2025","journal-title":"Front. Neuroinform"},{"key":"B16","doi-asserted-by":"publisher","first-page":"107545","DOI":"10.1016\/j.bspc.2025.107545","article-title":"Multimodal fusion diagnosis of the Alzheimer's disease via lightweight CNN-LSTM model using magnetic resonance imaging (MRI)","volume":"104","author":"Haq","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"B17","first-page":"770","article-title":"\u201cDeep residual learning for image recognition,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"B18","first-page":"7132","article-title":"\u201cSqueeze-and-excitation networks,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hu","year":"2018"},{"key":"B19","first-page":"1","article-title":"\u201cITCFN: incomplete triple-modal co-attention fusion network for mild cognitive impairment conversion prediction,\u201d","volume-title":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","author":"Hu","year":"2025"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2061","DOI":"10.1109\/JBHI.2024.3512417","article-title":"A lightweight deep convolutional neural network extracting local and global contextual features for the classification of Alzheimer's disease using structural MRI","volume":"29","author":"Jabason","year":"2025","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B21","first-page":"547","article-title":"\u201cVisual-attribute prompt learning for progressive mild cognitive impairment prediction,\u201d","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Kang","year":"2023"},{"key":"B22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IJCNN48605.2020.9206975","article-title":"\u201cTowards best practice in explaining neural network decisions with LRP,\u201d","volume-title":"2020 International Joint Conference on Neural Networks (IJCNN)","author":"Kohlbrenner","year":"2020"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3412926","article-title":"RLAD: a reliable hippo-guided multi-task model for Alzheimer's disease diagnosis","author":"Lei","year":"2024","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2587","DOI":"10.1093\/bioinformatics\/btac113","article-title":"HFBSURV: hierarchical multimodal fusion with factorized bilinear models for cancer survival prediction","volume":"38","author":"Li","year":"2022","journal-title":"Bioinformatics"},{"key":"B25","doi-asserted-by":"crossref","first-page":"2572","DOI":"10.1145\/3543507.3583554","article-title":"\u201cIMF: interactive multimodal fusion model for link prediction,\u201d","volume-title":"Proceedings of the ACM Web Conference 2023","author":"Li","year":"2023"},{"key":"B26","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1109\/WACV61041.2025.00021","article-title":"\u201cDiamond: dementia diagnosis with multi-modal vision transformers using MRI and pet,\u201d","volume-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Li","year":"2025"},{"key":"B27","first-page":"2980","article-title":"\u201cFocal loss for dense object detection,\u201d","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Lin","year":"2017"},{"key":"B28","first-page":"14420","article-title":"\u201cEfficientvit: memory efficient vision transformer with cascaded group attention,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2023"},{"key":"B29","doi-asserted-by":"publisher","first-page":"102266","DOI":"10.1016\/j.media.2021.102266","article-title":"Assessing clinical progression from subjective cognitive decline to mild cognitive impairment with incomplete multi-modal neuroimages","volume":"75","author":"Liu","year":"2022","journal-title":"Med. Image Anal"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.19756","article-title":"Kan: Kolmogorov-Arnold networks","author":"Liu","year":"2024","journal-title":"arXiv"},{"key":"B31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/INDICON.2016.7839026","article-title":"\u201cRobust algorithm for early detection of Alzheimer's disease using multiple feature extractions,\u201d","volume-title":"2016 IEEE Annual India Conference (INDICON)","author":"Mathew","year":"2016"},{"key":"B32","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1016\/j.neuroimage.2014.10.002","article-title":"Machine learning framework for early mri-based Alzheimer's conversion prediction in MCI subjects","volume":"104","author":"Moradi","year":"2015","journal-title":"Neuroimage"},{"key":"B33","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.jalz.2005.06.003","article-title":"Ways toward an early diagnosis in Alzheimer's disease: the Alzheimer's disease neuroimaging initiative (ADNI)","volume":"1","author":"Mueller","year":"2005","journal-title":"Alzheimers Dement"},{"key":"B34","doi-asserted-by":"publisher","first-page":"103225","DOI":"10.1016\/j.media.2024.103225","article-title":"MMGPL: multimodal medical data analysis with graph prompt learning","volume":"97","author":"Peng","year":"2024","journal-title":"Med. Image Anal"},{"key":"B35","first-page":"1","article-title":"\u201cA benchmarking study of Kolmogorov-Arnold networks on tabular data,\u201d","volume-title":"In 2024 IEEE 18th International Conference on Application of Information and Communication Technologies (AICT)","author":"Poeta","year":"2024"},{"key":"B36","doi-asserted-by":"publisher","first-page":"3161","DOI":"10.1109\/TMI.2024.3386937","article-title":"3D multimodal fusion network with disease-induced joint learning for early Alzheimer's disease diagnosis","volume":"43","author":"Qiu","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B37","first-page":"618","article-title":"\u201cGrad-cam: visual explanations from deep networks via gradient-based localization,\u201d","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Selvaraju","year":"2017"},{"key":"B38","first-page":"3319","article-title":"\u201cAxiomatic attribution for deep networks,\u201d","volume-title":"International Conference on Machine Learning, Volume 70","author":"Sundararajan","year":"2017"},{"key":"B39","first-page":"6105","article-title":"\u201cEfficientnet: rethinking model scaling for convolutional neural networks,\u201d","author":"Tan","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, Volume 97 of Proceedings of Machine Learning Research"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.36227\/techrxiv.174803834.41610666\/v1","author":"Verma","year":"2025","journal-title":"VGG-KAN: A Hybrid Approach for Alzheimer's Disease Diagnosis using Kolmogorov Arnold Network"},{"key":"B41","doi-asserted-by":"publisher","first-page":"6429","DOI":"10.1109\/JBHI.2024.3357453","article-title":"Hope: hybrid-granularity ordinal prototype learning for progression prediction of mild cognitive impairment","volume":"28","author":"Wang","year":"2024","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B42","doi-asserted-by":"publisher","first-page":"119929","DOI":"10.1016\/j.neuroimage.2023.119929","article-title":"Deep neural network heatmaps capture Alzheimer's disease patterns reported in a large meta-analysis of neuroimaging studies","volume":"269","author":"Wang","year":"2023","journal-title":"Neuroimage"},{"key":"B43","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1109\/ICCECE65250.2025.10985338","article-title":"\u201cApplication of Kolmogorov-Arnold networks combined with graph convolutional networks in Alzheimer's disease diagnosis,\u201d","volume-title":"2025 5th International Conference on Consumer Electronics and Computer Engineering (ICCECE)","author":"Wang","year":"2025"},{"key":"B44","doi-asserted-by":"publisher","first-page":"101694","DOI":"10.1016\/j.media.2020.101694","article-title":"Convolutional neural networks for classification of Alzheimer's disease: overview and reproducible evaluation","volume":"63","author":"Wen","year":"2020","journal-title":"Med. Image Anal"},{"key":"B45","first-page":"3","article-title":"\u201cCBAM: convolutional block attention module,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV), Volume 11211","author":"Woo","year":"2018"},{"key":"B46","first-page":"10819","article-title":"\u201cMetaformer is actually what you need for vision,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yu","year":"2022"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.08245","article-title":"Flex-MOE: modeling arbitrary modality combination via the flexible mixture-of-experts","author":"Yun","year":"2024","journal-title":"arXiv"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1109\/TMI.2024.3486086","article-title":"Asynchronous functional brain network construction with spatiotemporal transformer for MCI classification","volume":"44","author":"Zhang","year":"","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B49","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/JBHI.2024.3472011","article-title":"A modality-flexible framework for Alzheimer's disease diagnosis following clinical routine","volume":"29","author":"Zhang","year":"","journal-title":"IEEE J. Biomed. Health Inf"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1637291\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T05:27:54Z","timestamp":1756186074000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1637291\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,26]]},"references-count":49,"alternative-id":["10.3389\/fnins.2025.1637291"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2025.1637291","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,26]]},"article-number":"1637291"}}