Multimodal fusion of structural and functional brain imaging in depression using linked independent component analysis

Abstract

Previous structural and functional neuroimaging studies have implicated distributed brain regions and networks in depression. However, there are no robust imaging biomarkers that are specific to depression, which may be due to clinical heterogeneity and neurobiological complexity. A dimensional approach and fusion of imaging modalities may yield a more coherent view of the neuronal correlates of depression. We used linked independent component analysis to fuse cortical macrostructure (thickness, area, gray matter density), white matter diffusion properties and resting‐state functional magnetic resonance imaging default mode network amplitude in patients with a history of depression (n = 170) and controls (n = 71). We used univariate and machine learning approaches to assess the relationship between age, sex, case–control status, and symptom loads for depression and anxiety with the resulting brain components. Univariate analyses revealed strong associations between age and sex with mainly global but also regional specific brain components, with varying degrees of multimodal involvement. In contrast, there were no significant associations with case–control status, nor symptom loads for depression and anxiety with the brain components, nor any interaction effects with age and sex. Machine learning revealed low model performance for classifying patients from controls and predicting symptom loads for depression and anxiety, but high age prediction accuracy. Multimodal fusion of brain imaging data alone may not be sufficient for dissecting the clinical and neurobiological heterogeneity of depression. Precise clinical stratification and methods for brain phenotyping at the individual level based on large training samples may be needed to parse the neuroanatomy of depression.

From genetics to systems biology of stress-related mental disorders

“…However, even with this potential drawback, they have shown promise in analyzing genomic datasets ( Arloth et al, 2020 ; Chen et al, 2019 ; Min et al, 2017 ; Tranchevent et al, 2019 ). Deep learning has enabled efficient multimodal neuroimaging fusion, capitalizing on the strength of each modality ( Maglanoc et al, 2020 ; Plis et al, 2014 ; Sui et al, 2012 ; Zhang et al, 2020 ). A convolutional neural network for co-expression was able to predict transcription factor targets, identify disease-related genes and perform causality inference in one framework ( Yuan and Bar-Joseph, 2019 ).…”

Structural and Functional Abnormities of Amygdala and Prefrontal Cortex in Major Depressive Disorder With Suicide Attempts

“…The MRI literatures on suicide attempt in MDD suggested alterations of both structure and function in the amygdala-PFC neural circuitry. Compared with single neuroimaging analysis, the multiple neuroimaging analyses such as combining functional connectivity, regional gray matter volume, as well as combining amplitude of low-frequency fluctuations and white matter connectivity, could be used not only to explore the local functional and structural abnormalities, but also to identify more precisely the key neural circuitry in the mental disorders, providing the evidence to better understand the the mechanism of mental disorders in-depth (29,(31)(32)(33). Additionally, the latest studies suggested that data from multimodal fusion of structural and functional brain imaging analyses may be helpful to specifically predict symptoms and treatment effects in mental diseases (34,35).…”

Differences in directed functional brain connectivity related to age, sex and mental health

“…Although the rates and trajectories vary substantially between individuals and cognitive domains (Ardila, 2007), normal aging is primarily associated with a decline in most cognitive functions, including executive functions, attention, memory and perception (Riddle, 2007). Numerous studies have established pronounced age-related differences in brain network connections (Betzel et al, 2014; Cassady et al, 2019; Dørum et al, 2017; Geerligs, Renken, Saliasi, Maurits, & Lorist, 2015; Grady, Springer, Hongwanishkul, McIntosh, & Winocur, 2006; Maglanoc, Kaufmann, van der Meer, et al, 2019; Meunier, Achard, Morcom, & Bullmore, 2009; Wang, Su, Shen, & Hu, 2012). However, so far mostly age-related network changes have been studied using static functional connectivity, where connectivity strengths are estimated from stationary coefficients and assumed not to change short-term during the period of scan.…”