基于机器学习的脑小血管病认知障碍影像研究进展

doi:10.3969/j.issn.1673-5765.2020.12.005

摘要/Abstract

摘要：

脑小血管病（cerebral small vessel disease，CSVD）是认知障碍的主要原因。神经影像研究已在组水平层面发现许多与CSVD认知障碍相关的大脑结构与功能的改变，然而难以实现个体化评价和预测。近年来，机器学习逐渐应用于脑疾病中，如利用神经影像数据对疾病进展进行个体化预测，发掘潜在的生物学标志物等方面。

文章导读： 机器学习与神经影像相结合的方法，在CSVD辅助诊断、自动化影像负荷评定、临床症状和结局预测、疾病机制探索等方面均展现了良好的性能。

关键词: 脑小血管病; 认知障碍; 神经影像; 机器学习

Abstract:

Cerebral small vessel disease (CSVD) is the main cause of cognitive impairment. Some neuroimaging studies have found many changes in brain structure and function related to cognitive impairment due to CSVD at group level. However, it is hard to make individual evaluation for cognitive impairment and prognosis prediction according to these neuroimaging changes. In recent years, machine learning has been gradually applied to cerebrovascular disease field, and machine learning-based neuroimaging data analysis can be used to predict disease progression and find potential imaging biomarkers.

Key words: Cerebral small vessel disease; Cognitive impairment; Neuroimaging; Machine learning

陆佩文，徐群. 基于机器学习的脑小血管病认知障碍影像研究进展[J]. 中国卒中杂志, 2020, 15(12): 1281-1286.

LU Pei-Wen, XU Qun. Advances in Machine Learning-based Neuroimaging Studies on Cognitive Impairment due to Cerebral Small Vessel Disease[J]. Chinese Journal of Stroke, 2020, 15(12): 1281-1286.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.chinastroke.org.cn/CN/10.3969/j.issn.1673-5765.2020.12.005

https://www.chinastroke.org.cn/CN/Y2020/V15/I12/1281

参考文献

[1] WARDLAW J M，SMITH C，DICHGANS M.

Mechanisms of sporadic cerebral small vessel disease：

insights from neuroimaging[J]. Lancet Neurol，2013，

12（5）：483-497.

[2] WARDLAW J M，SMITH C，DICHGANS M.

Small vessel disease：mechanisms and clinical

implications[J]. Lancet Neurol，2019，18（7）：684-

696.

[3] PANTONI L，GORELICK P. Advances in vascular

cognitive impairment 2010[J]. Stroke，2011，42（2）：

291-293.

[4] GORELICK P B，SCUTERI A，BLACK S E，et al.

Vascular contributions to cognitive impairment and

dementia：a statement for healthcare professionals

from the American Heart Association/American

Stroke Association[J]. Stroke，2011，42（9）：2672-

2713.

[5] DICHGANS M，LEYS D. Vascular cognitive

impairment[J]. Circ Res，2017，120（3）：573-591.

[6] ROSENBERG G A，WALLIN A，WARDLAW J

M，et al. Consensus statement for diagnosis of

subcortical small vessel disease[J]. J Cereb Blood

Flow Metab，2016，36（1）：6-25.

[7] WARDLAW J M，SMITH E E，BIESSELS G J，et

al. Neuroimaging standards for research into small

vessel disease and its contribution to ageing and

neurodegeneration[J]. Lancet Neurol，2013，12（8）：

822-838.

[8] BIESBROEK J M，LEEMANS A，DEN BAKKER

H，et al. Microstructure of strategic white matter

tracts and cognition in memory clinic patients with

vascular brain injury[J]. Dement Geriatr Cogn

Disord，2017，44（5/6）：268-282.

[9] TULADHAR A M，VAN NORDEN A G，DE LAAT

K F，et al. White matter integrity in small vessel

disease is related to cognition[J/OL]. Neuroimage

Clin，2015，7：518-524[2020-06-20]. https：//doi.

org/10.1016/j.nicl.2015.02.003.

[10] VAN DER HOLST H M，TULADHAR A M，ZERBI

V，et al. White matter changes and gait decline in

cerebral small vessel disease[J/OL]. Neuroimage

Clin，2018，17：731-738[2020-06-20]. https：//doi.

org/10.1016/j.nicl.2017.12.007.

[11] VAN UDEN I W，TULADHAR A M，DE LAAT

K F，et al. White matter integrity and depressive

symptoms in cerebral small vessel disease：the RUN

DMC study[J]. Am J Geriatr Psychiatry，2015，23

（5）：525-535.

[12] YI L Y，WANG J H，JIA L F，et al. Structural and

functional changes in subcortical vascular mild

cognitive impairment：a combined voxel-based

morphometry and resting-state fMRI study[J/OL].

PLoS One，2012，7（9）：e44758[2020-06-20].

https：//doi.org/10.1371/journal.pone.0044758.

[13] SANG L Q，CHEN L，WANG L，et al. Progressively

disrupted brain functional connectivity network in

subcortical ischemic vascular cognitive impairment

patients[J/OL]. Front Neurol，2018，9：94[2020-06-

20]. https：//doi.org/10.3389/fneur.2018.00094.

[14] LI C M，ZHENG J，WANG J. An fMRI study of

prefrontal cortical function in subcortical ischemic

vascular cognitive impairment[J]. Am J Alzheimers

Dis Other Demen，2012，27（7）：490-495.

[15] SHI Y L，WARDLAW J M. Update on cerebral small

vessel disease：a dynamic whole-brain disease[J].

Stroke Vasc Neurol，2016，1（3）：83-92.

[16] LAWRENCE A J，CHUNG A W，MORRIS R G，et

al. Structural network efficiency is associated with

cognitive impairment in small-vessel disease[J].

Neurology，2014，83（4）：304-311.

[17] DU J，WANG Y，ZHI N，et al. Structural brain

network measures are superior to vascular burden

scores in predicting early cognitive impairment in

post stroke patients with small vessel disease[J/OL].

Neuroimage Clin，2019，22：101712[2020-06-20].

https：//doi.org/10.1016/j.nicl.2019.101712.

[18] TULADHAR A M，VAN UDEN I W，RUTTENJACOBS

L C，et al. Structural network efficiency

predicts conversion to dementia[J]. Neurology，2016，

86（12）：1112-1119.

[19] DEY A K，STAMENOVA V，TURNER G，et al.

Pathoconnectomics of cognitive impairment in small

vessel disease：a systematic review[J]. Alzheimers

Dement，2016，12（7）：831-845.

[20] LAWRENCE A J，TOZER D J，STAMATAKIS E A，

et al. A comparison of functional and tractography

based networks in cerebral small vessel disease[J/

OL]. Neuroimage Clin，2018，18：425-432[2020-06-

20]. https：//doi.org/10.1016/j.nicl.2018.02.013.

[21] LI X，LIANG Y，CHEN Y J，et al. Disrupted

frontoparietal network mediates white matter

structure dysfunction associated with cognitive

decline in hypertension patients[J]. J Neurosci，2015，

35（27）：10015-10024.

[22] LAVDAS I，GLOCKER B，RUECKERT D，et al.

Machine learning in whole-body MRI：experiences

and challenges from an applied study using

multicentre data[J]. Clin Radiol，2019，74（5）：346-

356.

[23] SAUR D，RONNEBERGER O，KUMMERER D，

et al. Early functional magnetic resonance imaging

activations predict language outcome after stroke[J].

Brain，2010，133（Pt 4）：1252-1264.

[24] KLOPPEL S，STONNINGTON C M，CHU C，et al.

Automatic classification of MR scans in Alzheimer's

disease[J]. Brain，2008，131（Pt 3）：681-689.

[25] ZACHARAKI E I，WANG S，CHAWLA S，et

al. Classification of brain tumor type and grade

using MRI texture and shape in a machine learning

scheme[J]. Magn Reson Med，2009，62（6）：1609-

1618.

[26] FRANKE K，ZIEGLER G，KLOPPEL S，et

al. Estimating the age of healthy subjects from

T1-weighted MRI scans using kernel methods：

exploring the influence of various parameters[J].

Neuroimage，2010，50（3）：883-892.

[27] STONNINGTON C M，CHU C，KLOPPEL S，et al.

Predicting clinical scores from magnetic resonance

scans in Alzheimer's disease[J]. Neuroimage，2010，

51（4）：1405-1413.

[28] HSIEH Y Z，LUO Y C，PAN C，et al. Cerebral small

vessel disease biomarkers detection on MRI-sensorbased

image and deep learning[J]. Sensors（Basel），

2019，19（11）：2573.

[29] GONZALEZ-CASTRO V，VALDES HERNANDEZ

M D C，CHAPPELL F M，et al. Reliability of an

automatic classifier for brain enlarged perivascular

spaces burden and comparison with human

performance[J]. Clin Sci（Lond），2017，131（13）：

1465-1481.

[30] DUBOST F，YILMAZ P，ADAMS H，et al. Enlarged

perivascular spaces in brain MRI：automated

quantification in four regions[J/OL]. Neuroimage，

2019，185：534-544[2020-06-20]. https：//doi.org/

10.1016/j.neuroimage.2018.10.026.

[31] MORRISON M A，PAYABVASH S，CHEN Y C，et

al. A user-guided tool for semi-automated cerebral

microbleed detection and volume segmentation：

evaluating vascular injury and data labelling for

machine learning[J/OL]. Neuroimage Clin，2018，

20：498-505[2020-06-20]. https：//doi.org/10.1016/

j.nicl.2018.08.002.

[32] DOU Q，CHEN H，YU L Q，et al. Automatic

detection of cerebral microbleeds from MR images

via 3D convolutional neural networks[J]. IEEE Trans

Med Imaging，2016，35（5）：1182-1195.

[33] SUNDARESAN V，ZAMBONI G，LE HERON C，

et al. Automated lesion segmentation with BIANCA：

impact of population-level features，classification

algorithm and locally adaptive thresholding[J/OL].

Neuroimage，2019，202：116056[2020-06-20].

https：//doi.org/10.1016/j.neuroimage.2019.116056.

[34] JIANG J Y，LIU T，ZHU W L，et al. UBO

Detector-A cluster-based，fully automated pipeline

for extracting white matter hyperintensities[J/OL].

Neuroimage，2018，174：539-549[2020-06-20].

https：//doi.org/10.1016/j.neuroimage.2018.03.050.

[35] ORTIZ-RAMÓN R，VALDÉS HERNÁNDEZ M D

C，GONZÁLEZ-CASTRO V，et al. Identification of

the presence of ischaemic stroke lesions by means

of texture analysis on brain magnetic resonance

images[J/OL]. Comput Med Imaging Graph，2019，

74：12-24[2020-06-20]. https：//doi.org/10.1016/

j.compmedimag.2019.02.006.

[36] WANG Y B，CATINDIG J A，HILAL S，et

al. Multi-stage segmentation of white matter

hyperintensity，cortical and lacunar infarcts[J].

Neuroimage，2012，60（4）：2379-2388.

[37] LAMBERT C，SAM NAREAN J，BENJAMIN P，

et al. Characterising the grey matter correlates of

leukoaraiosis in cerebral small vessel disease[J/OL].

Neuroimage Clin，2015，9：194-205[2020-06-20].

https：//doi.org/10.1016/j.nicl.2015.07.002.

[38] CIULLI S，CITI L，SALVADORI E，et al.

Prediction of impaired performance in trail making

test in MCI patients with small vessel disease using

DTI data[J]. IEEE J Biomed Health Inform，2016，20

（4）：1026-1033.

[39] CHEN H F，HUANG L L，LI H Y，et al.

Microstructural disruption of the right inferior

fronto-occipital and inferior longitudinal fasciculus

contributes to WMH-related cognitive impairment[J].

CNS Neurosci Ther，2020，26（5）：576-588.

[40] PANTONI L，MARZI C，POGGESI A，et al. Fractal

dimension of cerebral white matter：a consistent

feature for prediction of the cognitive performance

in patients with small vessel disease and mild

cognitive impairment[J/OL]. Neuroimage Clin，2019，

24：101990[2020-06-20]. https：//doi.org/10.1016/

j.nicl.2019.101990.