Identification of MCI individuals using structural and functional connectivity networks

Abstract

Different imaging modalities provide essential complementary information that can be used to enhance our understanding of brain disorders. This study focuses on integrating multiple imaging modalities to identify individuals at risk for mild cognitive impairment (MCI). MCI, often an early stage of Alzheimer’s disease (AD), is difficult to diagnose due to its very mild or insignificant symptoms of cognitive impairment. Recent emergence of brain network analysis has made characterization of neurological disorders at a whole-brain connectivity level possible, thus providing new avenues for brain diseases classification. Employing multiple-kernel Support Vector Machines (SVMs), we attempt to integrate information from diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) for improving classification performance. Our results indicate that the multimodality classification approach yields statistically significant improvement in accuracy over using each modality independently. The classification accuracy obtained by the proposed method is 96.3%, which is an increase of at least 7.4% from the single modality-based methods and the direct data fusion method. A cross-validation estimation of the generalization performance gives an area of 0.953 under the receiver operating characteristic (ROC) curve, indicating excellent diagnostic power. The multimodality classification approach hence allows more accurate early detection of brain abnormalities with greater sensitivity.

On the early diagnosis of Alzheimer's Disease from multimodal signals: A survey

“…O'Dwyer et al [19] made use of DTI images and an SVM algorithm with an RBF kernel and achieved 92.9% accuracy in distinguishing MCI from control healthy subjects, and a very similar result of 92.785% considering a three class classification problem with aMCI, non-amnesic MCI and control subjects. Wee et al [173] combined both DTI and fMRI images in order to obtain complementary features related to the white matter (WM) and to the GM respectively. The combination of the two techniques and the SVM algorithm with a linear kernel gave significantly higher classification accuracies distinguishing MCI from healthy control subjects than using each one of the techniques alone.…”

Multivariate Pattern Recognition for Diagnosis and Prognosis in Clinical Neuroimaging: State of the Art, Current Challenges and Future Trends

“…It is further possible to combine for example DTI and resting state fMRI to identify MCI individuals (Wee et al 2012), to predict MCI to AD conversion using multimodal measures also in combination with neuropsychological scores or cerebrospinal fluid biomarkers (Cui et al 2011(Cui et al , 2012 or by the combination of structural MRI and FDG-PET (Zhang and Shen 2012a, b;Zhang et al 2011). Finally, it is possible to classify MCI subtypes, who have different risk of disease progression and who might benefit from different types of treatment, for example, based on DTI (Haller et al 2013b).…”

Multivariate Classification of Blood Oxygen Level-Dependent fMRI Data with Diagnostic Intention: A Clinical Perspective

“…For example, Du et al 55 combined both task-and task-free fMRI in schizophrenia in a small study. Additionally, combinations of fMRI measures with volumetric data, 41,[48][49][50]63,76,[78][79][80][81]86,89 DTI, 46,49,92 as well as genetics 42 and behavioral data, 40,41,50,76 have been used as features in MVPA analyses. However, results reported so far do not allow verified statements about the benefit of such multimodal acquisitions.…”