Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease using structural MR and FDG-PET images

被引：0
|
作者：
Donghuan Lu
Karteek Popuri
Gavin Weiguang Ding
Rakesh Balachandar
Mirza Faisal Beg
机构：
[1] Simon Fraser University,School of Engineering Science
[2] University of California,Magnetic Resonance Unit at the VA Medical Center and Radiology, Medicine, Psychiatry and Neurology
[3] University of California,San Diego School of Medicine
[4] Mayo Clinic,Rush University Medical Center
[5] Mayo Clinic,USF Health Byrd Alzheimer’s Institute
[6] University of California,undefined
[7] University of Pennsylvania,undefined
[8] University of Southern California,undefined
[9] University of California,undefined
[10] MPH Brigham and Women’s Hospital/Harvard Medical School,undefined
[11] Indiana University,undefined
[12] Washington University St. Louis,undefined
[13] Oregon Health and Science University,undefined
[14] University of California–San Diego,undefined
[15] University of Michigan,undefined
[16] Baylor College of Medicine,undefined
[17] Columbia University Medical Center,undefined
[18] University of Alabama,undefined
[19] Mount Sinai School of Medicine,undefined
[20] Rush University,undefined
[21] Wien Center,undefined
[22] Johns Hopkins University,undefined
[23] New York University,undefined
[24] Duke University Medical Center,undefined
[25] University of Kentucky,undefined
[26] University of Rochester Medical Center,undefined
[27] University of California,undefined
[28] University of Texas Southwestern Medical School,undefined
[29] Emory University,undefined
[30] University of Kansas,undefined
[31] Medical Center,undefined
[32] University of California,undefined
[33] Mayo Clinic,undefined
[34] Yale University School of Medicine,undefined
[35] McGill University,undefined
[36] Montreal-Jewish General Hospital,undefined
[37] Sunnybrook Health Sciences,undefined
[38] U.B.C. Clinic for AD & Related Disorders,undefined
[39] Cognitive Neurology - St. Joseph’s,undefined
[40] Cleveland Clinic Lou Ruvo Center for Brain Health,undefined
[41] Northwestern University,undefined
[42] Premiere Research Inst (Palm Beach Neurology),undefined
[43] Georgetown University Medical Center,undefined
[44] Brigham and Women’s Hospital,undefined
[45] Stanford University,undefined
[46] Banner Sun Health Research Institute,undefined
[47] Boston University,undefined
[48] Howard University,undefined
[49] Case Western Reserve University,undefined
[50] University of California,undefined
来源：
Scientific Reports | / 8卷
关键词：
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Alzheimer’s Disease (AD) is a progressive neurodegenerative disease where biomarkers for disease based on pathophysiology may be able to provide objective measures for disease diagnosis and staging. Neuroimaging scans acquired from MRI and metabolism images obtained by FDG-PET provide in-vivo measurements of structure and function (glucose metabolism) in a living brain. It is hypothesized that combining multiple different image modalities providing complementary information could help improve early diagnosis of AD. In this paper, we propose a novel deep-learning-based framework to discriminate individuals with AD utilizing a multimodal and multiscale deep neural network. Our method delivers 82.4% accuracy in identifying the individuals with mild cognitive impairment (MCI) who will convert to AD at 3 years prior to conversion (86.4% combined accuracy for conversion within 1–3 years), a 94.23% sensitivity in classifying individuals with clinical diagnosis of probable AD, and a 86.3% specificity in classifying non-demented controls improving upon results in published literature.
引用
收藏
相关论文
共 50 条
  • [1] Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer's Disease using structural MR and FDG-PET images
    Lu, Donghuan
    Popuri, Karteek
    Ding, Gavin Weiguang
    Balachandar, Rakesh
    Beg, Mirza Faisal
    [J]. SCIENTIFIC REPORTS, 2018, 8
  • [2] Multiscale deep neural network based analysis of FDG-PET images for the early diagnosis of Alzheimer's disease
    Lu, Donghuan
    Popuri, Karteek
    Ding, Gavin Weiguang
    Balachandar, Rakesh
    Beg, Mirza Faisal
    [J]. MEDICAL IMAGE ANALYSIS, 2018, 46 : 26 - 34
  • [3] Deep learning based diagnosis of Alzheimer's disease using FDG-PET images
    Kishore, Nand
    Goel, Neelam
    [J]. NEUROSCIENCE LETTERS, 2023, 817
  • [4] Early Diagnosis of Alzheimer's Disease by Ensemble Deep Learning Using FDG-PET
    Zheng, Chuanchuan
    Xia, Yong
    Chen, Yuanyuan
    Yin, Xiaoxia
    Zhang, Yanchun
    [J]. INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING, 2018, 11266 : 614 - 622
  • [5] Classification of Alzheimer's Disease by Combination of Convolutional and Recurrent Neural Networks Using FDG-PET Images
    Liu, Manhua
    Cheng, Danni
    Yan, Weiwu
    [J]. FRONTIERS IN NEUROINFORMATICS, 2018, 12
  • [6] Multimodal fusion diagnosis of Alzheimer's disease based on FDG-PET generation
    Tu, Yue
    Lin, Shukuan
    Qiao, Jianzhong
    Zhuang, Yilin
    Wang, Zhiqi
    Wang, Dai
    [J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 89
  • [7] Deep Learning for Diagnosis of Alzheimer's Disease with FDG-PET Neuroimaging
    Bastos, Jose
    Silva, Filipe
    Georgieva, Petia
    [J]. PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2022), 2022, 13256 : 95 - 107
  • [8] Broad learning for early diagnosis of Alzheimer's disease using FDG-PET of the brain
    Duan, Junwei
    Liu, Yang
    Wu, Huanhua
    Wang, Jing
    Chen, Long
    Chen, C. L. Philip
    [J]. FRONTIERS IN NEUROSCIENCE, 2023, 17
  • [9] Dementia diagnosis by ensemble deep neural networks using FDG-PET scans
    Yigit, Altug
    Bastanlar, Yalin
    Isik, Zerrin
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2022, 16 (08) : 2203 - 2210
  • [10] Dementia diagnosis by ensemble deep neural networks using FDG-PET scans
    Altuğ Yiğit
    Yalın Baştanlar
    Zerrin Işık
    [J]. Signal, Image and Video Processing, 2022, 16 : 2203 - 2210
12345