Review of Functional Magnetic Resonance Imagingin Diagnosis of Mild Cognitive Impairment
An Xingwei1,2, Zhou Yutao1, Di Yang1, Liu Shuang1,2, Ming Dong1,2,3#*
1(Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China) 2(Tianjin Center for Brain Science, Tianjin 300072, China) 3(Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin 300072, China)
Abstract Nowadays Alzheimer's disease (AD) has severely influenced and limited personal daily life and even posed a grave threat to the life and health of patients. Mild cognitive impairment (MCI) is the prodromal stage of AD, and accurate diagnosis can help to interfere or reduce the conversion of patients to Alzheimer's disease. At present, functional magnetic resonance imaging (fMRI) technology have been widely used in the detection and diagnosis of MCI. This article introduced the research status of fMRI in MCI from the aspects of feature extraction, feature selection, data dimensionality reduction and classification recognition. First, the commonly used resolution indicators such as low-frequency amplitude, local consistency, and functional connection for feature extraction was introduced. Second, features selection and data dimension reduction methods were introduced, and the efficient machine learning and deep learning algorithms in classification and recognition were summarized. This paper also proposed the remained problems and made perspectives to the future research.
An Xingwei,Zhou Yutao,Di Yang, et al. Review of Functional Magnetic Resonance Imagingin Diagnosis of Mild Cognitive Impairment[J]. Chinese Journal of Biomedical Engineering, 2022, 41(1): 100-107.
[1] Kamagata K, Andica C, Hatano T, et al. Advanced diffusion magnetic resonance imaging in patients with Alzheimer‘s and Parkinson's diseases [J]. Neural Regeneration Research, 2020, 15(9): 1590-1600. [2] Hou YJ, Dan XL, Babbar M, et al. Ageing as a risk factor for neurodegenerative disease [J]. Nature Reviews Neurology, 2019, 15(10): 565-581. [3] Aisen PS, Cummings J, Jack CR, Jr, et al. On the path to 2025: understanding the Alzheimer's disease continuum[J]. Alzheimers Res Ther, 2017, 9(1): 60. [4] Jie B, Zhang D, Gao W, et al. Integration of network topological and connectivity properties for neuroimaging classification [J]. IEEE Trans Biomed Eng, 2014, 61(2): 576-589. [5] Li Y, Liu J, Tang Z, et al. Deep spatial-temporal feature fusion from adaptive dynamic functional connectivity for MCI identification[J]. IEEE Trans Med Imaging, 2020, 39(9): 2818-2830. [6] Brookmeyer R, Johnson E, Ziegler-Graham K, et al. Forecasting the global burden of Alzheimer's disease [J]. Alzheimers Dement, 2007, 3(3): 186-191. [7] Galvin JE. Prevention of Alzheimer's disease: lessons learned and applied [J]. J Am Geriatr Soc, 2017, 65(10): 2128-2133. [8] Anter AM, Wei Y, Su J, et al. A robust swarm intelligence-based feature selection model for neuro-fuzzy recognition of mild cognitive impairment from resting-state fMRI [J]. Information Sciences, 2019, 503: 670-687. [9] Eyler LT, Elman JA, Hatton SN, et al. Resting state abnormalities of the default mode network in mild cognitive impairment: A systematic review and meta-analysis [J]. J Alzheimers Dis, 2019, 70(1): 107-120. [10] Wang M, Lian C, Yao D, et al. Spatial-temporal dependency modeling and network hub detection for functional MRI analysis via convolutional-recurrent network [J]. IEEE Trans Biomed Eng, 2019, 67(8): 2241-2252. [11] Yanase J, Triantaphyllou E. A systematic survey of computer-aided diagnosis in medicine: past and present developments [J]. Expert Systems with Applications, 2019,138:112821. [12] Tian ZY, Qian L, Fang L, et al. Frequency-specific changes of resting brain activity in parkinson's disease: a machine learning approach [J]. Neuroscience, 2020, 436: 170-183. [13] Rathore S, Habes M, Iftikhar M A, et al. A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages [J]. Neuroimage, 2017, 155: 530-548. [14] Zuo XN, Di Martino A, Kelly C, et al. The oscillating brain: complex and reliable[J]. Neuroimage, 2010, 49(2): 1432-1445. [15] Long Z, Jing B, Yan H, et al. A support vector machine-based method to identify mild cognitive impairment with multi-level characteristics of magnetic resonance imaging [J]. Neuroscience, 2016, 331: 169-176. [16] Wang Z, Jia X, Chen H, et al. Abnormal spontaneous brain activity in early Parkinson's disease with mild cognitive impairment: A resting-state fMRI study[J]. Front Physiol, 2018, 9: 1093. [17] Marchitelli R, Aiello M, Cachia A, et al. Simultaneous resting-state FDG-PET/fMRI in Alzheimer disease: relationship between glucose metabolism and intrinsic activity[J]. Neuroimage, 2018, 176: 246-258. [18] Wang C, Xiao Z, Wu J. Functional connectivity-based classification of autism and control using SVM-RFECV on rs-fMRI data [J]. Phys Med, 2019, 65: 99-105. [19] Xia J, Fan J, Liu W, et al. Functional connectivity within the salience network differentiates autogenous- from reactive-type obsessive-compulsive disorder [J]. Prog Neuropsychopharmacol Biol Psychiatry, 2020, 98: 109813. [20] Lv H, Wang Z, Tong E, et al. Resting-state functional MRI: Everything that nonexperts have always wanted to know [J]. AJNR Am J Neuroradiol, 2018, 39(8): 1390-1399. [21] Zang Y, Jiang T, Lu Y, et al. Regional homogeneity approach to fMRI data analysis [J]. Neuroimage, 2004, 22(1): 394-400. [22] Cheng JN, Yang H, Zhang JT. Donepezil's effects on brain functions of patients with Alzheimer disease: A regional homogeneity study based on resting-state functional magnetic resonance imaging [J]. Clinical Neuropharmacology, 2019, 42(2): 42-48. [23] Cai S, Wang Y, Kang Y, et al. Differentiated regional homogeneity in progressive mild cognitive impairment: a study with post hoc label[J]. Am J Alzheimers Dis Other Demen, 2018, 33(6): 373-384. [24] Bi X A, Hu X, Wu H, et al. Multimodal data analysis of Alzheimer's disease based on clustering evolutionary random forest [J]. IEEE J Biomed Health Inform, 2020, 24(10): 2973-2983. [25] Pei C, Sun Y, Zhu J, et al. Ensemble learning for early-response prediction of antidepressant treatment in major depressive disorder[J]. J Magn Reson Imaging, 2019, 52(1): 161-171. [26] Khosla M, Jamison K, Ngo G H, et al. Machine learning in resting-state fMRI analysis [J]. Magn Reson Imaging, 2019, 64: 101-121. [27] Jie B, Liu M, Lian C, et al. Developing novel weighted correlation kernels for convolutional neural networks to extract hierarchical functional connectivities from fMRI for disease diagnosis [J]. Mach Learn Med Imaging, 2018, 11046: 1-9. [28] Chen X, Zhang H, Gao Y, et al. High-order resting-state functional connectivity network for MCI classification [J]. Hum Brain Mapp, 2016, 37(9): 3282-3296. [29] Preti MG, Bolton TAW, Van De Ville D. The dynamic functional connectome: State-of-the-art and perspectives [J]. Neuroimage, 2017, 160: 41-54. [30] Chen Y, Wang W, Zhao X, et al. Age-Related decline in the variation of dynamic functional connectivity: a resting state analysis [J]. Front Aging Neurosci, 2017, 9: 203. [31] Cheng L, Zhu Y, Sun J, et al. Principal states of dynamic functional connectivity reveal the link between resting-state and task-state brain: An fMRI study[J]. Int J Neural Syst, 2018, 28(7): 1850002. [32] Viviano RP, Raz N, Yuan P, et al. Associations between dynamic functional connectivity and age, metabolic risk, and cognitive performance [J]. Neurobiol Aging, 2017, 59: 135-143. [33] Xia Y, Chen Q, Shi L, et al. Tracking the dynamic functional connectivity structure of the human brain across the adult lifespan [J]. Hum Brain Mapp, 2019, 40(3): 717-728. [34] Liegeois R, Li J, Kong R, et al. Resting brain dynamics at different timescales capture distinct aspects of human behavior [J]. Nat Commun, 2019, 10(1): 2317. [35] Wang Y, Li C, Su R. Functional magnetic resonance imaging classification based on random forest algorithm in Alzheimer's disease[C] // 2019 International Conference on Image and Video Processing, and Artificial Intelligence. Shanghai: ICVIP, 2019:2538059. [36] Dimitriadis SI, Liparas D, Alzheimer's disease neuroimaging I. How random is the random forest? Random forest algorithm on the service of structural imaging biomarkers for Alzheimer's disease: from Alzheimer's disease neuroimaging initiative (ADNI) database [J]. Neural Regen Res, 2018, 13(6): 962-970. [37] Georges N, Mhiri I, Rekik I. Identifying the best data-driven feature selection method for boosting reproducibility in classification tasks [J]. Pattern Recognition, 2020, 101:107183. [38] Ota K, Oishi N, Ito K, et al. A comparison of three brain atlases for MCI prediction [J]. J Neurosci Methods, 2014, 221: 139-150. [39] Cai SP, Chong T, Peng YL, et al. Altered functional brain networks in amnestic mild cognitive impairment: A resting-state fMRI study[J]. Brain Imaging and Behavior, 2017, 11(3): 619-631. [40] Ahmad F, Zulifqar H, Malik T. Classification of Alzheimer disease among susceptible brain regions [J]. International Journal of Imaging Systems and Technology, 2019, 29(3): 222-233. [41] Salas-Gonzalez D, Gorriz J M, Ramirez J, et al. Feature selection using factor analysis for Alzheimer's diagnosis using F-18-FDG PET images [J]. Medical Physics, 2010, 37(11): 6084-6095. [42] Liang SG, Li YF, Zhang Z, et al. Classification of first-episode schizophrenia using multimodal brain features: a combined structural and diffusion imaging study [J]. Schizophrenia Bulletin, 2019, 45(3): 591-599. [43] Forouzannezhad P, Abbaspour A, Fang C, et al. A survey on applications and analysis methods of functional magnetic resonance imaging for Alzheimer's disease [J]. J Neurosci Methods, 2019, 317: 121-140. [44] Zhang Y, Liu S, Yu X. Individual identification for different age groups using functional connectivity strength [J]. Neurol Sci, 2020, 41(2): 417-426. [45] Wee CY, Yap PT, Zhang D, et al. Identification of MCI individuals using structural and functional connectivity networks [J]. Neuroimage, 2012, 59(3): 2045-2056. [46] Rondina JM, Ferreira LK, de Souza Duran FL, et al. Selecting the most relevant brain regions to discriminate Alzheimer's disease patients from healthy controls using multiple kernel learning: a comparison across functional and structural imaging modalities and atlases [J]. Neuroimage Clin, 2018, 17: 628-641. [47] French BM, Dawson MRW, Dobbs AR. Classification and staging of dementia of the Alzheimer type - A comparison between neural networks and linear discriminant analysis [J]. Archives of Neurology, 1997, 54(8): 1001-1009. [48] Kam TE, Zhang H, Shen D. A novel deep learning framework on brain functional networks for early MCI diagnosis[J]. Med Image Comput Comput Assist Interv, 2018, 11072: 293-301. [49] Kam TE, Zhang H, Jiao Z, et al. Deep learning of static and dynamic brain functional networks for early MCI detection [J]. IEEE Trans Med Imaging, 2020, 39(2): 478-487. [50] Bi X, Zhao X, Huang H, et al. Functional brain network classification for Alzheimer's disease detection with deep features and extreme learning machine [J]. Cognitive Computation, 2019, 12(3): 513-527. [51] Jacobs HIL, Hopkins DA, Mayrhofer HC, et al. The cerebellum in Alzheimer's disease: Evaluating its role in cognitive decline [J]. Brain, 2018, 141(1): 37-47. [52] Du J, Zhu H, Zhou J, et al. structural brain network disruption at preclinical stage of cognitive impairment due to cerebral small vessel disease [J]. Neuroscience, 2020, 449: 99-115.
