Multimodal fusion diagnosis of Alzheimer's disease based on FDG-PET generation

被引:7
|
作者
Tu, Yue [1 ]
Lin, Shukuan [1 ]
Qiao, Jianzhong [1 ]
Zhuang, Yilin [1 ]
Wang, Zhiqi [1 ]
Wang, Dai [1 ]
机构
[1] Northeastern Univ, Sch Comp Sci & Engn, Shenyang, Peoples R China
关键词
Alzheimer's disease; Computer-aided diagnosis; Manifold projection; Multilevel fusion; NEURAL-NETWORKS; REPRESENTATION; CLASSIFICATION; MRI;
D O I
10.1016/j.bspc.2023.105709
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Alzheimer's disease (AD) is a central nervous system disease that mainly appears in the aged. Early diagnosis of AD is valuable in delaying the progression of the disease. With the development of medical imaging technology, various medical images such as structural Magnetic Resonance Imaging (sMRI) and Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) can obtain the structural and functional lesions of the brain to assist in diagnosing diseases. However, FDG-PET is usually incomplete due to radiation and high costs. Most existing methods exclude missing modal subjects, which is remarkably one-sided. Meanwhile, how to extract the features of different levels of multimodal fusion is still a challenge. To solve these issues, we propose a Consistent Manifold Projection Generative Adversarial Network (CMPGAN) for FDG-PET generation and a Multilevel Multimodal Fusion Diagnosis Network (MMFDN) for diagnosing AD. First, we propose a CMPGAN model to project the distribution onto low-dimensional manifolds through consistent manifold projection, and present a distribution distance metric to optimize the model. Our proposed model can avoid problems of mode collapse and gradient disappearance. Then, we construct a multiscale feature-level feature extraction network based on our proposed radial medley unit and a voxel-level feature extraction network based on a harmonic voxel fusion matrix. The fusion of the two parts obtains the final diagnosis result. Experimental results indicate that our proposed method performs better than state-of-the-art methods in FDG-PET generation and AD diagnosis. Our approach also has the significance of guiding clinicians in diagnosing diseases.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] Superiority of FDG-PET over Amyvid imaging in diagnosis of Mild Cognitive Impairment and Alzheimer's disease
    Khosravi, Mohsen
    Newberg, Andrew
    Serruya, Mijail
    Wintering, Nancy
    Raynor, William
    Zadeh, Mahdi Zirakchian
    Werner, Thomas
    Alavi, Abass
    JOURNAL OF NUCLEAR MEDICINE, 2017, 58
  • [22] ALZHEIMER'S DISEASE DIAGNOSIS WITH FDG-PET BRAIN IMAGES BY USING MULTI-LEVEL FEATURES
    Pan, Xiaoxi
    Adel, Mouloud
    Fossati, Caroline
    Gaidon, Thierry
    Guedj, Eric
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 366 - 370
  • [23] FDG-PET as an independent biomarker for Alzheimer’s biological diagnosis: a longitudinal study
    Ya-Nan Ou
    Wei Xu
    Jie-Qiong Li
    Yu Guo
    Mei Cui
    Ke-Liang Chen
    Yu-Yuan Huang
    Qiang Dong
    Lan Tan
    Jin-Tai Yu
    Alzheimer's Research & Therapy, 11
  • [24] FDG-PET as an independent biomarker for Alzheimer's biological diagnosis: a longitudinal study
    Ou, Ya-Nan
    Xu, Wei
    Li, Jie-Qiong
    Guo, Yu
    Cui, Mei
    Chen, Ke-Liang
    Huang, Yu-Yuan
    Dong, Qiang
    Tan, Lan
    Yu, Jin-Tai
    ALZHEIMERS RESEARCH & THERAPY, 2019, 11 (1)
  • [25] An Effective Multimodal Image Fusion Method Using MRI and PET for Alzheimer's Disease Diagnosis
    Song, Juan
    Zheng, Jian
    Li, Ping
    Lu, Xiaoyuan
    Zhu, Guangming
    Shen, Peiyi
    FRONTIERS IN DIGITAL HEALTH, 2021, 3
  • [26] Classification and diagnosis model for Alzheimer's disease based on multimodal data fusion
    Fu, Yaqin
    Xu, Lin
    Zhang, Yujie
    Zhang, Linshuai
    Zhang, Pengfei
    Cao, Lu
    Jiang, Tao
    MEDICINE, 2024, 103 (52)
  • [27] Individual Metabolic Network for the Accurate Detection of Alzheimer's Disease Based on FDG-PET imaging
    Yao, Zhijun
    Hu, Bin
    Nan, Huailiang
    Zheng, Weihao
    Xie, Yuanwei
    2016 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2016, : 1328 - 1335
  • [28] Alzheimer's disease diagnosis via multimodal feature fusion
    Tu, Yue
    Lin, Shukuan
    Qiao, Jianzhong
    Zhuang, Yilin
    Zhang, Peng
    COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 148
  • [29] Generative FDG-PET and MRI Model of Aging and Disease Progression in Alzheimer's Disease
    Dukart, Juergen
    Kherif, Ferath
    Mueller, Karsten
    Adaszewski, Stanislaw
    Schroeter, Matthias L.
    Frackowiak, Richard S. J.
    Draganski, Bogdan
    PLOS COMPUTATIONAL BIOLOGY, 2013, 9 (04)
  • [30] Apathy as a feature of prodromal Alzheimer's disease: an FDG-PET ADNI study
    Delrieu, Julien
    Desmidt, Thomas
    Camus, Vincent
    Sourdet, Sandrine
    Boutoleau-Bretonniere, Claire
    Mullin, Emmanuel
    Vellas, Bruno
    Payoux, Pierre
    Lebouvier, Thibaud
    INTERNATIONAL JOURNAL OF GERIATRIC PSYCHIATRY, 2015, 30 (05) : 470 - 477