Machine Learning-Based Framework for Differential Diagnosis Between Vascular Dementia and Alzheimer's Disease Using Structural MRI Features

Background and Objective: Vascular dementia (VaD) and Alzheimer's disease (AD) could be characterized by the same syndrome of dementia. This study aims to assess whether multi-parameter features derived from structural MRI can serve as the informative biomarker for differential diagnosis between VaD and AD using machine learning. Methods: A total of 93 patients imaged with brain MRI including 58 AD and 35 VaD confirmed by two chief physicians were recruited in this study from June 2013 to July 2019. Automated brain tissue segmentation was performed by the AccuBrain tool to extract multi-parameter volumetric measurements from different brain regions. Firstly, a total of 62 structural MRI biomarkers were addressed to select significantly different features between VaD and AD for dimensionality reduction. Then, the least absolute shrinkage and selection operator (LASSO) was further used to construct a feature set that is fed into a support vector machine (SVM) classifier. To ensure the unbiased evaluation of model performance, a comparative study of classification models was implemented by using different machine learning algorithms in order to determine which performs best in the application of differential diagnosis between VaD and AD. The diagnostic performance of the classification models was evaluated by the quantitative metrics derived from the receiver operating characteristic curve (ROC). Results: The experimental results demonstrate that the SVM with RBF achieved an encouraging performance with sensitivity (SEN), specificity (SPE), and accuracy (ACC) values of 82.65%, 87.17%, and 84.35%, respectively (AUC = 0.861, 95% CI = 0.820–0.902), for the differential diagnosis between VaD and AD. Conclusions: The proposed computer-aided diagnosis method highlights the potential of combining structural MRI and machine learning to support clinical decision making in distinction of VaD vs. AD.

[1]  K. Jellinger,et al.  The enigma of vascular cognitive disorder and vascular dementia , 2007, Acta Neuropathologica.

[2]  Johannes Kornhuber,et al.  Blood‐based neurochemical diagnosis of vascular dementia: a pilot study , 2007, Journal of neurochemistry.

[3]  Simon Cervenka,et al.  In vivo tau PET imaging in dementia: Pathophysiology, radiotracer quantification, and a systematic review of clinical findings , 2017, Ageing Research Reviews.

[4]  Karl J. Friston,et al.  Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation , 2011, NeuroImage.

[5]  Mark Jenkinson,et al.  Structural MRI changes detectable up to ten years before clinical Alzheimer's disease , 2012, Neurobiology of Aging.

[6]  Abbas Babajani-Feremi,et al.  Classification of patients with MCI and AD from healthy controls using directed graph measures of resting-state fMRI , 2017, Behavioural Brain Research.

[7]  Hasan Demirel,et al.  Classification of Alzheimer's disease and prediction of mild cognitive impairment-to-Alzheimer's conversion from structural magnetic resource imaging using feature ranking and a genetic algorithm , 2017, Comput. Biol. Medicine.

[8]  C. Baird,et al.  The pilot study. , 2000, Orthopedic nursing.

[9]  Taehong Sohn,et al.  The Differences of Behavioral and Psychological Symptoms in the Patients of Alzheimer's Disease and Vascular Dementia , 2006 .

[10]  Annachiara Cagnin,et al.  Vascular Cognitive Disorder. A Biological and Clinical Overview , 2010, Neurochemical Research.

[11]  Lin Shi,et al.  Standardization of hippocampus volumetry using automated brain structure volumetry tool for an initial Alzheimer’s disease imaging biomarker , 2018, Acta radiologica.

[12]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[13]  Kun Hu,et al.  Multi-scale features extraction from baseline structure MRI for MCI patient classification and AD early diagnosis , 2016, Neurocomputing.

[14]  Christos Davatzikos,et al.  A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages , 2017, NeuroImage.

[15]  M N Rossor,et al.  A Systematic Review and Meta-Analysis of CSF Neurofilament Protein Levels as Biomarkers in Dementia , 2007, Neurodegenerative Diseases.

[16]  C. Igel,et al.  Differential diagnosis of mild cognitive impairment and Alzheimer's disease using structural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry* , 2016, NeuroImage: Clinical.

[17]  H. Braak,et al.  Neuropathological stageing of Alzheimer-related changes , 2004, Acta Neuropathologica.

[18]  Antonio Lobo,et al.  Dementia in western Europe: epidemiological evidence and implications for policy making , 2016, The Lancet Neurology.

[19]  A. Simmons,et al.  Different multivariate techniques for automated classification of MRI data in Alzheimer’s disease and mild cognitive impairment , 2013, Psychiatry Research: Neuroimaging.

[20]  W. Snow,et al.  The NINCDS‐ADRDA Work Group criteria for the clinical diagnosis of probable Alzheimer's disease , 1988, Neurology.

[21]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[22]  Serhat Ozkan,et al.  Apraxia for differentiating Alzheimer’s disease from subcortical vascular dementia and mild cognitive impairment , 2013, Neuropsychiatric disease and treatment.

[23]  Marie Chupin,et al.  Automatic classi fi cation of patients with Alzheimer ' s disease from structural MRI : A comparison of ten methods using the ADNI database , 2010 .

[24]  C. Jack,et al.  Tracking pathophysiological processes in Alzheimer's disease: an updated hypothetical model of dynamic biomarkers , 2013, The Lancet Neurology.

[25]  M Asgari,et al.  Clinical and Paraclinical Parameters Correlation with Histopathologic Classification in IgA Nephropathy: A Clinicopathologic Study of 57 Cases , 2005 .

[26]  O L Lopez,et al.  Reliability of NINDS‐AIREN clinical criteria for the diagnosis of vascular dementia , 1994, Neurology.

[27]  Andrew Lockhart,et al.  Imaging as a biomarker in drug discovery for Alzheimer’s disease: is MRI a suitable technology? , 2014, Alzheimer's Research & Therapy.

[28]  Lois Beech,et al.  Dementia in Western Europe: epidemiological evidence and implications for policy making , 2015 .

[29]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[30]  A. Simmons,et al.  Entorhinal cortex thickness predicts cognitive decline in Alzheimer's disease. , 2013, Journal of Alzheimer's disease : JAD.

[31]  C. Benedict,et al.  Insulin Resistance as a Therapeutic Target in the Treatment of Alzheimer's Disease: A State-of-the-Art Review , 2018, Front. Neurosci..

[32]  Jussi Tohka,et al.  Comparison of feature representations in MRI-based MCI-to-AD conversion prediction , 2017, bioRxiv.

[33]  David A Wolk,et al.  Cerebrovascular atherosclerosis correlates with Alzheimer pathology in neurodegenerative dementias. , 2012, Brain : a journal of neurology.

[34]  J. Langhoff‐Roos.  State‐of‐the‐art review , 2016, Acta obstetricia et gynecologica Scandinavica.

[35]  Ying Cheng,et al.  The Association of Tau With Mitochondrial Dysfunction in Alzheimer's Disease , 2018, Front. Neurosci..

[36]  Bengt Winblad,et al.  Biomarkers for Alzheimer’s disease and other forms of dementia: Clinical needs, limitations and future aspects , 2010, Experimental Gerontology.

[37]  Constantino Carlos Reyes-Aldasoro,et al.  Quantitative MRI Brain Studies in Mild Cognitive Impairment and Alzheimer's Disease: A Methodological Review , 2018, IEEE Reviews in Biomedical Engineering.

[38]  Lei Wang,et al.  Correlations Between Antemortem Hippocampal Volume and Postmortem Neuropathology in AD Subjects , 2004, Alzheimer disease and associated disorders.

[39]  Zdenko Sonicki,et al.  Evaluation of cerebrospinal fluid phosphorylated tau231 as a biomarker in the differential diagnosis of Alzheimer's disease and vascular dementia , 2018, CNS neuroscience & therapeutics.

[40]  Soo Jin Yoon,et al.  P2-095 The differences of behavioral and psychological symptoms in the patients of Alzheimer’s disease and vascular dementia , 2006, Alzheimer's & Dementia.

[41]  G. Ruxton.  The unequal variance t-test is an underused alternative to Student's t-test and the Mann–Whitney U test , 2006 .