Multimodal Neuroimaging: Basic Concepts and Classification of Neuropsychiatric Diseases

Abstract

Neuroimaging techniques are widely used in neuroscience to visualize neural activity, to improve our understanding of brain mechanisms, and to identify biomarkers-especially for psychiatric diseases; however, each neuroimaging technique has several limitations. These limitations led to the development of multimodal neuroimaging (MN), which combines data obtained from multiple neuroimaging techniques, such as electroencephalography, functional magnetic resonance imaging, and yields more detailed information about brain dynamics. There are several types of MN, including visual inspection, data integration, and data fusion. This literature review aimed to provide a brief summary and basic information about MN techniques (data fusion approaches in particular) and classification approaches. Data fusion approaches are generally categorized as asymmetric and symmetric. The present review focused exclusively on studies based on symmetric data fusion methods (data-driven methods), such as independent component analysis and principal component analysis. Machine learning techniques have recently been introduced for use in identifying diseases and biomarkers of disease. The machine learning technique most widely used by neuroscientists is classification-especially support vector machine classification. Several studies differentiated patients with psychiatric diseases and healthy controls with using combined datasets. The common conclusion among these studies is that the prediction of diseases increases when combining data via MN techniques; however, there remain a few challenges associated with MN, such as sample size. Perhaps in the future N-way fusion can be used to combine multiple neuroimaging techniques or nonimaging predictors (eg, cognitive ability) to overcome the limitations of MN.

Predictive Value of Slow and Fast EEG Oscillations for Methylphenidate Response in ADHD

“…Future studies should aim to find more accurate predictors that can be used solely to estimate response to stimulants. These predictors could involve use of multiple imaging methods at the same time (ie, multimodal neuroimaging 43 ). In addition, studies using complexity measures such as entropy revealed that this index might be useful for predicting treatment response in depression 44 and obsessive-compulsive disorder (unpublished results from our studies).…”

Regional gene expression patterns are associated with task-specific brain activation during reward and emotion processing measured with functional MRI

“…Different methods offer designated benefits and disadvantages, e.g. the precise temporal resolution of electroencephalography contrasts to its low spatial resolution 8 . In case of positron emission tomography, molecular specificity allows quantification of protein distributions in vivo, but availability of specific radioligands is limited 9 .…”

Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation

“…This practice offers the advantages of large and diverse datasets. However, it also comes with challenges of sophisticated models, complicated data normalization (that includes correction of errors and variations imbedded in data from different institutions), data fusion, and data integration [8, 9] .…”