Share：
Share this content in WeChat
X
[Chinese][PDF]349170
• Review •
Application of machine learning in the diagnosis of brain dysfunction by magnetic resonance imaging
QI Guoqing  WU Dong  HU Bo  WANG Wen 

Cite this article as: Qi GQ, Wu D, Hu B, et al. Application of machine learning in the diagnosis of brain dysfunction by magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2021, 12(10): 85-88. DOI:10.12015/issn.1674-8034.2021.10.022.


[Abstract] The combination of MRI and machine learning (ML) algorithm to establish a diagnostic model has been widely used in the research and clinical diagnosis of brain dysfunction. In this paper, five ML algorithms commonly used in MRI images of brain diseases are summarized and discussed, including linear regression model, K-nearest neighbor, support vector machine, random forest and deep learning. The main content includes their theories, current applications, application scopes and limitations. Future research should focus on the data mining of brain image features, the establishment of standardized databases, the integration of multimodal MRI data and the integration of ML algorithms.
[Keywords] machine learning；artificial intelligence；brain dysfunction；neuroimaging；magnetic resonance imaging

QI Guoqing1   WU Dong1   HU Bo2   WANG Wen2*  

1 First Cadet Regiment, School of Basic Medicine, Air Force Medical University, Xi'an 710032, China

2 Department of Radiology, Tangdu Hospital, Air Force Medical University, Xi'an 710038, China

Wang W, E-mail: wangwen@fmmu.edu.cn

Conflicts of interest   None.

ACKNOWLEDGMENTS Special Fund for Military Medical Innovation Project (No.18CXZ016); Hovering Program of Fourth Military Medical University (No. axjhww).
Received  2021-05-23
Accepted  2021-07-06
DOI: 10.12015/issn.1674-8034.2021.10.022
Cite this article as: Qi GQ, Wu D, Hu B, et al. Application of machine learning in the diagnosis of brain dysfunction by magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2021, 12(10): 85-88. DOI:10.12015/issn.1674-8034.2021.10.022.

[1]
Feigin VL, Nichols E, Alam T, et al. Global, regional, and national burden of neurological disorders, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016[J]. Lancet Neurol, 2019, 18(5): 459-480. DOI: 10.1016/S1474-4422(18)30499-X.
[2]
Huang YQ, Wang Y, Wang H, et al. Prevalence of mental disorders in China: a cross-sectional epidemiological study[J]. Lancet Psychiat, 2019, 6(3): 211-224. DOI: 10.1016/S2215-0366(18)30511-X.
[3]
Turner R, Le Bihan D, Moonen CT, et al. Echo-planar time course MRI of cat brain oxygenation changes[J]. Magn Reson Med, 1991, 22(1): 159-166. DOI: 10.1002/mrm.1910220117.
[4]
Pini L, Pievani M, Bocchetta M, et al. Brain atrophy in Alzheimer's Disease and aging[J]. Ageing Res Rev, 2016, 30: 25-48. DOI: 10.1016/j.arr.2016.01.002.
[5]
Sun YT, Chen TL, He D, et al. Research Progress of Biological Markers for Depression Based on Psychoradiology and Artificial Intelligence[J]. Prog Biochem Biophys2019, 46(09): 879-899. DOI: 10.16476/j.pibb.2019.0025.
[6]
Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future[J]. Stroke Vasc Neurol, 2017, 2(4): 230-243. DOI: 10.1136/svn-2017-000101.
[7]
Tighe SK, Reading SA, Rivkin P, et al. Total white matter hyperintensity volume in bipolar disorder patients and their healthy relatives[J]. Bipolar Disord, 2012, 14(8): 888-893. DOI: 10.1111/bdi.12019.
[8]
Yang SJ, Shin H, Lee SH, et al. Functional linear regression model with randomly censored data: Predicting conversion time to Alzheimer's disease[J]. Comput Stat Data Anal, 2020, 150: 107009. DOI: 10.1016/j.csda.2020.107009.
[9]
Shen X, Finn ES, Scheinost D, et al. Using connectome-based predictive modeling to predict individual behavior from brain connectivity[J]. Nat Protoc, 2017, 12(3): 506-518. DOI: 10.1038/nprot.2016.178.
[10]
Dadi K, Rahim M, Abraham A, et al. Benchmarking functional connectome-based predictive models for resting-state fMRI[J]. Neuroimage, 2019, 192: 115-134. DOI: 10.1016/j.neuroimage.2019.02.062.
[11]
Ju Y, Horien C, Chen W, et al. Connectome-based models can predict early symptom improvement in major depressive disorder[J]. J Affect Disord, 2020, 273: 442-452. DOI: 10.1016/j.jad.2020.04.028.
[12]
Wang ZH, Goerlich KS, Ai H, et al. Connectome-Based Predictive Modeling of Individual Anxiety[J]. Cereb Cortex, 2021, 31(6): 3006-3020. DOI: 10.1093/CERCOR/BHAA407.
[13]
Rosenberg MD, Hsu WT, Scheinost D, et al. Connectome-based Models Predict Separable Components of Attention in Novel Individuals[J]. J Cogn Neurosci, 2018, 30(2): 160-173. DOI: 10.1162/jocn_a_01197.
[14]
Jiang R, Calhoun VD, Cui Y, et al. Multimodal data revealed different neurobiological correlates of intelligence between males and females[J]. Brain Imaging Behav, 2020, 14(5): 1979-1993. DOI: 10.1007/s11682-019-00146-z.
[15]
Cover T, Hart P. Nearest neighbor pattern classification[J]. IEEE Trans Inf Theory, 1967, 13(1): 21-27. DOI: 10.1109/TIT.1967.1053964.
[16]
Su YX, Guan SW. Density and Distance Based KNN Approach to Classification[J]. Int J Appl Evol Comput, 2016, 7(2): 45-60. DOI: 10.4018/IJAEC.2016040103.
[17]
Acharya UR, Fernandes SL, WeiKoh JE, et al. Automated Detection of Alzheimer's Disease Using Brain MRI Images-A Study with Various Feature Extraction Techniques[J]. J Med Syst, 2019, 43(9): 302. DOI: 10.1007/s10916-019-1428-9.
[18]
de Bresser J, Portegies MP, Leemans A, et al. A comparison of MR based segmentation methods for measuring brain atrophy progression[J]. Neuroimage, 2011, 54(2): 760-768. DOI: 10.1016/j.neuroimage.2010.09.060.
[19]
Geng XF, Xu JH, Liu BL, et al. Multivariate Classification of Major Depressive Disorder Using the Effective Connectivity and Functional Connectivity[J]. Front Neurosci, 2018, 12: 38. DOI: 10.3389/fnins.2018.00038.
[20]
Vrooman HA, Cocosco CA, van der Lijn F, et al. Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification[J]. Neuroimage, 2007, 37(1): 71-81. DOI: 10.1016/j.neuroimage.2007.05.018.
[21]
Cortes C, Vapnik V. Support-vector networks[J]. Mach Learn, 1995, 20(3): 273-297. DOI: 10.1007/BF00994018.
[22]
Noble WS. What is a support vector machine?[J]. Nat Biotechnol, 2006, 24(12): 1565-1567. DOI: 10.1038/nbt1206-1565.
[23]
Wang S, Zhang Y, Lv LX, et al. Abnormal regional homogeneity as a potential imaging biomarker for adolescent-onset schizophrenia: A resting-state fMRI study and support vector machine analysis[J]. Schizophr Res, 2018, 192: 179-184. DOI: 10.1016/j.schres.2017.05.038.
[24]
Wang LY, Zhao SJ, Shan BC, et al. Classification Study of Major Depressive Disorder and Subthreshold Depression Based on Radiomics[J]. Chin J Med Imaging, 2020, 28(07): 538-542. DOI: 10.3969/j.issn.1005-5185.2020.07.015.
[25]
Cao X, Wang X, Xue C, et al. A Radiomics Approach to Predicting Parkinson's Disease by Incorporating Whole-Brain Functional Activity and Gray Matter Structure[J]. Front Neurosci, 2020, 14: 751. DOI: 10.3389/fnins.2020.00751.
[26]
Rizk-Jackson A, Stoffers D, Sheldon S, et al. Evaluating imaging biomarkers for neurodegeneration in pre-symptomatic Huntington's disease using machine learning techniques[J]. Neuroimage, 2011, 56(2): 788-796. DOI: 10.1016/j.neuroimage.2010.04.273.
[27]
Breiman L. Random Forests[J]. Mach Learn, 2001, 45(1): 5-32. DOI: 10.1023/A:1010933404324.
[28]
Yang XB, Zhang J. Decision Tree and Its Key Techniques[J]. Comput Techno Dev, 2007, 17(1): 43-45. DOI: 10.3969/j.issn.1673-629X.2007.01.015.
[29]
Li CS, Wang Y, Xiao HB, et al. Medical image classification for Alzheimer's disease diagnosis based on random forest algorithm[J]. Chin J Med Phys2020, 37(08): 1005-1009. DOI: 10.3969/j.issn.1005-202X.2020.08.013.
[30]
Alessia S, Antonio C, Aldo Q. Random Forest Algorithm for the Classification of Neuroimaging Data in Alzheimer's Disease: A Systematic Review[J]. Front Aging Neurosci, 2017, 9: 329. DOI: 10.3389/fnagi.2017.00329.
[31]
Cordova M, Shada K, Demeter DV, et al. Heterogeneity of executive function revealed by a functional random forest approach across ADHD and ASD[J]. Neuroimage Clin. 2020, 26: 102245. DOI: 10.1016/j.nicl.2020.102245.
[32]
Liu D, Qiu BY, Fang F, et al. Medical Image Classification Method Based on Bag-of-Spatial-Symbiosis-Words Model and Convolution Neural Network[J]. J Xiangnan Univ, 2020, 41(02): 26-31. DOI: 10.3969/j.issn.1672-8173.2020.02.007.
[33]
Banerjee S, Mitra S, Masulli F, et al. Glioma Classification Using Deep Radiomics[J]. SN Comput Sci, 2020, 1(4): 1-14. DOI: 10.1007/s42979-020-00214-y.
[34]
Schelb P, Kohl S, Radtke JP, et al. Classification of Cancer at Prostate MRI: Deep Learning versus Clinical PI-RADS Assessment[J]. Radiology. 2019, 293(3): 607-617. DOI: 10.1148/radiol.2019190938.
[35]
Oh K, Kim W, Shen G, et al. Classification of schizophrenia and normal controls using 3D convolutional neural network and outcome visualization[J]. Schizophr Res, 2019, 212: 186-195. DOI: 10.1016/j.schres.2019.07.034.
[36]
Chakraborty S, Aich S, Kim HC. Detection of Parkinson's Disease from 3T T1 Weighted MRI Scans Using 3D Convolutional Neural Network[J]. Diagnostics (Basel), 2020, 10(6): 402. DOI: 10.3390/diagnostics10060402.
[37]
Basaia S, Agosta F, Wagner L, et al. Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks[J]. Neuroimage Clin, 2019, 21: 101645. DOI: 10.1016/j.nicl.2018.101645.
[38]
Shorten C, Khoshgoftaar TM. A survey on Image Data Augmentation for Deep Learning[J]. J Big Data, 2019, 6: 60. DOI: 10.1186/s40537-019-0197-0.
[39]
Chawla NV, Bowyer KW, Hall LO, et al. SMOTE: Synthetic Minority Over-sampling Technique[J]. J Artif Intell Res, 2002, 16: 321-357. DOI: 10.1613/jair.953.

PREV Research progress on the value of magnetic resonance imaging technique in evaluating the efficacy of repetitive transcranial magnetic stimulation in patients with obsessive-compulsive disorder
NEXT Research progress of resting-state brain functional network in T2DM patients with cognitive impairment
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn