Abstract
Leukoaraiosis (LA) is strongly associated with impaired cognition and increased dementia risk. Determining effective and robust methods of identifying LA patients with mild cognitive impairment (LA-MCI) is important for clinical intervention and disease monitoring. In this study, an ensemble learning method that combines multiple magnetic resonance imaging (MRI) morphological features is proposed to distinguish LA-MCI patients from LA patients lacking cognitive impairment (LA-nCI). Multiple comprehensive morphological measures (including gray matter volume (GMV), cortical thickness (CT), surface area (SA), cortical volume (CV), sulcus depth (SD), fractal dimension (FD), and gyrification index (GI)) are extracted from MRI to enrich model training on disease characterization information. Then, based on the general extreme gradient boosting (XGBoost) classifier, we leverage a weighted soft-voting ensemble framework to ensemble a data-level resampling method (Fusion + XGBoost) and an algorithm-level focal loss (FL)-improved XGBoost model (FL-XGBoost) to overcome class-imbalance learning problems and provide superior classification performance and stability. The baseline XGBoost model trained on an original imbalanced dataset had a balanced accuracy (Bacc) of 78.20%. The separate Fusion + XGBoost and FL-XGBoost models achieved Bacc scores of 80.53 and 81.25%, respectively, which are clear improvements (i.e., 2.33% and 3.05%, respectively). The fused model distinguishes LA-MCI from LA-nCI with an overall accuracy of 84.82%. Sensitivity and specificity were also well improved (85.50 and 84.14%, respectively). This improved model has the potential to facilitate the clinical diagnosis of LA-MCI.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
Moran C, Phan TG, Srikanth VK: Cerebral small vessel disease: a review of clinical, radiological, and histopathological phenotypes. Int J Stroke 7:36-46, 2012
Debette S, Markus HS: The clinical importance of white matter hyperintensities on brain magnetic resonance imaging: systematic review and meta-analysis. Brit Med J 341, 2010
Mortamais M, Artero S, Ritchie K: Cerebral white matter hyperintensities in the prediction of cognitive decline and incident dementia. Int Rev Psychiatr 25:686-698, 2013
Lee HK, Lee YM, Park JM, Lee BD, Moon ES, Chung YI: Amnestic multiple cognitive domains impairment and periventricular white matter hyperintensities are independently predictive factors progression to dementia in mild cognitive impairment. Int J Geriatr Psych 29:526-532, 2014
Kynast J, et al.: White matter hyperintensities associated with small vessel disease impair social cognition beside attention and memory. J Cerebr Blood F Met 38:996-1009, 2018
de Havenon A, Sheth KN, Yeatts SD, Turan TN, Prabhakaran S. White matter hyperintensity progression is associated with incident probable dementia or mild cognitive impairment. Stroke Vasc Neurol. 2022 Apr 29;7(4):364–6. https://doi.org/10.1136/svn-2021-001357. Epub ahead of print. PMID: 35487617
Seo SW, et al.: Cortical thinning related to periventricular and deep white matter hyperintensities. Neurobiol Aging 33:1156-1167, 2012
Dey AK, Stamenova V, Turner G, Black SE, Levine B: Pathoconnectomics of cognitive impairment in small vessel disease: A systematic review. Alzheimers Dement 12:831-845, 2016
Nitkunan A, Lanfranconi S, Charlton RA, Barrick TR, Markus HS: Brain atrophy and cerebral small vessel disease: a prospective follow-up study. Stroke 42:133-138, 2011
Appelman AP, Exalto LG, van der Graaf Y, Biessels GJ, Mali WP, Geerlings MI: White matter lesions and brain atrophy: more than shared risk factors? A systematic review. Cerebrovasc Dis 28:227-242, 2009
Yuan JL, Feng L, Hu WL, Zhang YM: Use of Multimodal Magnetic Resonance Imaging Techniques to Explore Cognitive Impairment in Leukoaraiosis. Med Sci Monitor 24:8910-8915, 2018
Mok VCT, et al.: Neuroimaging predictors of cognitive impairment in confluent white matter lesion: Volumetric analyses of 99 brain regions. Dement Geriatr Cogn 25:67-73, 2008
Peng Y, et al.: Density abnormalities in normal-appearing gray matter in the middle-aged brain with white matter hyperintense lesions: a DARTEL-enhanced voxel-based morphometry study. Clin Interv Aging 11:615-622, 2016
Tuladhar AM, et al.: Relationship Between White Matter Hyperintensities, Cortical Thickness, and Cognition. Stroke 46:425-432, 2015
Rizvi B, et al.: The effect of white matter hyperintensities on cognition is mediated by cortical atrophy. Neurobiol Aging 64:25-32, 2018
Zhuang Y, Zeng X, Wang B, Huang M, Gong H, Zhou F: Cortical Surface Thickness in the Middle-Aged Brain with White Matter Hyperintense Lesions. Front Aging Neurosci 9:225, 2017
Iniesta R, Stahl D, McGuffin P: Machine learning, statistical learning and the future of biological research in psychiatry. Psychol Med 46:2455-2465, 2016
Lemm S, Blankertz B, Dickhaus T, Muller KR: Introduction to machine learning for brain imaging. Neuroimage 56:387-399, 2011
Morra JH, Tu ZW, Apostolova LG, Green AE, Toga AW, Thompson PM: Comparison of AdaBoost and Support Vector Machines for Detecting Alzheimer’s Disease Through Automated Hippocampal Segmentation. Ieee T Med Imaging 29:30-43, 2010
Chen HF, et al.: Microstructural disruption of the right inferior fronto-occipital and inferior longitudinal fasciculus contributes to WMH-related cognitive impairment. Cns Neurosci Ther 26:576-588, 2020
Zhu WH, et al.: Cortical and Subcortical Grey Matter Abnormalities in White Matter Hyperintensities and Subsequent Cognitive Impairment. Neurosci Bull 37:789-803, 2021
Hopkins WD, Li X, Crow T, Roberts N: Vertex- and atlas-based comparisons in measures of cortical thickness, gyrification and white matter volume between humans and chimpanzees. Brain Struct Funct 222:229-245, 2017
Yushkevich PA, et al.: Automated Volumetry and Regional Thickness Analysis of Hippocampal Subfields and Medial Temporal Cortical Structures in Mild Cognitive Impairment. Hum Brain Mapp 36:258-287, 2015
Ma Z, et al.: Identifying Mild Cognitive Impairment with Random Forest by Integrating Multiple MRI Morphological Metrics. J Alzheimers Dis 73:991-1002, 2020
Dimitriadis SI, Liparas D, Tsolaki MN, Initia ADN: Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and Alzheimer’s disease patients: From the Alzheimer’s disease neuroimaging initiative (ADNI) database. J Neurosci Meth 302:14-23, 2018
Fazekas F, Chawluk JB, Alavi A, Hurtig HI, Zimmerman RA: MR signal abnormalities at 1.5 T in Alzheimer’s dementia and normal aging. AJR American journal of roentgenology 149:351–356, 1987
Ribaldi F, et al.: Accuracy and reproducibility of automated white matter hyperintensities segmentation with lesion segmentation tool: A European multi-site 3T study. Magn Reson Imaging 76:108-115, 2021
Seiger R, Ganger S, Kranz GS, Hahn A, Lanzenberger R: Cortical Thickness Estimations of FreeSurfer and the CAT12 Toolbox in Patients with Alzheimer’s Disease and Healthy Controls. J Neuroimaging 28:515-523, 2018
Dahnke R, Yotter RA, Gaser C: Cortical thickness and central surface estimation. Neuroimage 65:336-348, 2013
Luders E, Thompson PM, Narr KL, Toga AW, Jancke L, Gaser C: A curvature-based approach to estimate local gyrification on the cortical surface. Neuroimage 29:1224-1230, 2006
Mascalchi M, et al.: The burden of microstructural damage modulates cortical activation in elderly subjects with MCI and leuko-araiosis. A DTI and fMRI study. Hum Brain Mapp 35:819–830, 2014
Fan LZ, et al.: The Human Brainnetome Atlas: A New Brain Atlas Based on Connectional Architecture. Cereb Cortex 26:3508-3526, 2016
Glasser MF, et al.: A multi-modal parcellation of human cerebral cortex. Nature 536:171-+, 2016
Han H, Wang WY, Mao BH: Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. Lect Notes Comput Sc 3644:878-887, 2005
Lin WC, Tsai CF, Hu YH, Jhang JS: Clustering-based undersampling in class-imbalanced data. Inform Sciences 409:17-26, 2017
Batista GE, Prati RC, Monard MCJASen: A study of the behavior of several methods for balancing machine learning training data6:20–29, 2004
Lin TY, Goyal P, Girshick R, He KM, Dollar P: Focal loss for dense object detection. Ieee T Pattern Anal 42:318-327, 2020
Wang C, Deng CY, Wang SZ: Imbalance-XGBoost: leveraging weighted and focal losses for binary label-imbalanced classification with XGBoost. Pattern Recogn Lett 136:190-197, 2020
Lundberg SM, Lee SI: A unified approach to interpreting model predictions. Adv Neur In 30, 2017
Wang, L et al.: Alterations in cortical thickness and white matter integrity in mild cognitive impairment measured by whole-brain cortical thickness mapping and diffusion tensor imaging. American journal of neuroradiology vol. 30,5 (2009): 893-9.
Seo, Sang Won et al.: Cortical thinning related to periventricular and deep white matter hyperintensities. Neurobiology of aging vol. 33,7 (2012): 1156–67.
Guo, Shengwen et al.: Conversion discriminative analysis on mild cognitive impairment using multiple cortical features from MR images. Frontiers in aging neuroscience vol. 9 146. 18 May. 2017.
Lin, Sung-Han et al.: Increased water diffusion in the parcellated cortical regions from the patients with amnestic mild cognitive impairment and Alzheimer’s disease. Frontiers in aging neuroscience vol. 8 325. 11 Jan. 2017.
Burge, Wesley K et al.: Cortical thickness in human V1 associated with central vision loss. Scientific reports vol. 6 23268. 24 Mar. 2016.
Won, Yu Deok et al.: The frontal skull Hounsfield unit value can predict ventricular enlargement in patients with subarachnoid haemorrhage. Scientific reports vol. 8,1 10178. 5 Jul. 2018.
Du AT, et al.: White matter lesions are associated with cortical atrophy more than entorhinal and hippocampal atrophy. Neurobiol Aging 26:553-559, 2005
Gouw AA, et al.: Heterogeneity of small vessel disease: a systematic review of MRI and histopathology correlations. J Neurol Neurosur Ps 82:126-135, 2011
Ma, Zhe et al.: Identifying mild cognitive impairment with random forest by integrating multiple MRI morphological metrics. Journal of Alzheimer’s disease : JAD vol. 73,3 (2020): 991–1002.
Wee, Chong-Yaw et al.: Cortical graph neural network for AD and MCI diagnosis and transfer learning across populations. NeuroImage. Clinical vol. 23 (2019): 101929.
Funding
This study has received funding by grant from the National Natural Science Foundation of China (Grant No. 82271286), the Key Program of National Natural Science Foundation of China (Grant No.81830052); the Science and Technology Innovation Action Plan of Shanghai (Grant No.18441900500), and the Natural Science Foundation of Shanghai (Grant 20ZR1438300).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of Interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yang, Y., Hu, Y., Chen, Y. et al. Identifying Leukoaraiosis with Mild Cognitive Impairment by Fusing Multiple MRI Morphological Metrics and Ensemble Machine Learning. J Digit Imaging. Inform. med. 37, 666–678 (2024). https://doi.org/10.1007/s10278-023-00958-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-023-00958-y