Mutliresolutional ensemble PartialNet for Alzheimer detection using magnetic resonance imaging data

被引:14
作者
Razzak, Imran [1 ]
Naz, Saeeda [2 ]
Ashraf, Abida [2 ]
Khalifa, Fahmi [3 ]
Bouadjenek, Mohamed Reda [1 ]
Mumtaz, Shahid [4 ]
机构
[1] Deakin Univ, Sch Informat Technol, Level 5,Builiding KA, Geelong, Vic 3217, Australia
[2] Govt Girls Postgrad Coll 1, Dept Comp Sci, HED, Abbotabad, KP, Pakistan
[3] Mansoura Univ, Elect & Commun Engn, Mansoura, Egypt
[4] Inst Telecomunicacoes Aveiro, Aveiro, Portugal
关键词
Alzheimer; brain disorder; DenseNet; ensemble learning; PartialNet; FEATURE REPRESENTATION; DEEP; SEGMENTATION; DIAGNOSIS;
D O I
10.1002/int.22856
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Alzheimer's disease (AD) is an irreversible and progressive disorder where a large number of brain cells and their connections degenerate and die, eventually destroy the memory and other important mental functions that affect memory, thinking, language, judgment, and behavior. Not a single test can effectively determine AD; however, CT and magnetic resonance imaging (MRI) can be used to observe the decrease in size of different areas (mainly temporal and parietal lobes). This paper proposes an integrative deep ensemble learning framework to obtain better predictive performance for AD diagnosis. Unlike DenseNet, we present a multiresolutional ensemble PartialNet tailored to Alzheimer detection using brain MRIs. PartialNet incorporates the properties of identity mappings, diversified depth as well as deep supervision, thus, considers feature reuse that in turn results in better learning. Additionally, the proposed ensemble PartialNet demonstrates better characteristics in terms of vanishing gradient, diminishing forward flow with better training time, and a low number of parameters compared with DenseNet. Experiments performed on benchmark AD neuroimaging initiative data set that showed considerable performance gain (2 + % up arrow $\uparrow $) and (1.2 + % up arrow $\uparrow $) for multiclass and binary class in AD detection in comparison to state-of-the-art methods.
引用
收藏
页码:6613 / 6630
页数:18
相关论文
共 35 条
  • [1] Deep transfer learning for alzheimer neurological disorder detection
    Ashraf, Abida
    Naz, Saeeda
    Shirazi, Syed Hamad
    Razzak, Imran
    Parsad, Mukesh
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (20) : 30117 - 30142
  • [2] Alzheimer's disease diagnostics by a 3D deeply supervised adaptable convolutional network
    Asl, Ehsan Hosseini
    Ghazal, Mohammed
    Mahmoud, Ali
    Aslantas, Ali
    Shalaby, Ahmed
    Casanova, Manual
    Barnes, Gregory
    Gimel'farb, Georgy
    Keynton, Robert
    El Baz, Ayman
    [J]. FRONTIERS IN BIOSCIENCE-LANDMARK, 2018, 23 : 584 - 596
  • [3] Bäckström K, 2018, I S BIOMED IMAGING, P149, DOI 10.1109/ISBI.2018.8363543
  • [4] Ebrahimi-Ghahnavieh A, 2019, 2019 IEEE INTERNATIONAL CONFERENCE ON INDUSTRY 4.0, ARTIFICIAL INTELLIGENCE, AND COMMUNICATIONS TECHNOLOGY (IAICT), P133, DOI [10.1109/iciaict.2019.8784845, 10.1109/ICIAICT.2019.8784845]
  • [5] Farooq A, 2017, IEEE CONF IMAGING SY, P111
  • [6] Subtypes of Alzheimer's Disease Display Distinct Network Abnormalities Extending Beyond Their Pattern of Brain Atrophy
    Ferreira, Daniel
    Pereira, Joana B.
    Volpe, Giovanni
    Westman, Eric
    [J]. FRONTIERS IN NEUROLOGY, 2019, 10
  • [7] A NOVEL METHOD FOR EARLY DIAGNOSIS OF ALZHEIMER'S DISEASE BASED ON PSEUDO ZERNIKE MOMENT FROM STRUCTURAL MRI
    Gorji, H. T.
    Haddadnia, J.
    [J]. NEUROSCIENCE, 2015, 305 : 361 - 371
  • [8] Gupta Ashish., 2013, Proceedings of the 30th International Conference on International Conference on Machine Learning, V28, pIII
  • [9] Early diagnosis of Alzheimer's disease using combined features from voxel-based morphometry and cortical, subcortical, and hippocampus regions of MRI T1 brain images
    Gupta, Yubraj
    Lee, Kun Ho
    Choi, Kyu Yeong
    Lee, Jang Jae
    Kim, Byeong Chae
    Kwon, Goo Rak
    [J]. PLOS ONE, 2019, 14 (10):
  • [10] Hon M, 2017, IEEE INT C BIOINFORM, P1166, DOI 10.1109/BIBM.2017.8217822