A comprehensive hierarchical comparison of structural connectomes in Major Depressive Disorder cases v. controls in two large population samples.

BACKGROUND: The brain can be represented as a network, with nodes as brain regions and edges as region-to-region connections. Nodes with the most connections (hubs) are central to efficient brain function. Current findings on structural differences in Major Depressive Disorder (MDD) identified using network approaches remain inconsistent, potentially due to small sample sizes. It is still uncertain at what level of the connectome hierarchy differences may exist, and whether they are concentrated in hubs, disrupting fundamental brain connectivity. METHODS: We utilized two large cohorts, UK Biobank (UKB, N = 5104) and Generation Scotland (GS, N = 725), to investigate MDD case-control differences in brain network properties. Network analysis was done across four hierarchical levels: (1) global, (2) tier (nodes grouped into four tiers based on degree) and rich club (between-hub connections), (3) nodal, and (4) connection. RESULTS: In UKB, reductions in network efficiency were observed in MDD cases globally (d = -0.076, pFDR = 0.033), across all tiers (d = -0.069 to -0.079, pFDR = 0.020), and in hubs (d = -0.080 to -0.113, pFDR = 0.013-0.035). No differences in rich club organization and region-to-region connections were identified. The effect sizes and direction for these associations were generally consistent in GS, albeit not significant in our lower-N replication sample. CONCLUSION: Our results suggest that the brain's fundamental rich club structure is similar in MDD cases and controls, but subtle topological differences exist across the brain. Consistent with recent large-scale neuroimaging findings, our findings offer a connectomic perspective on a similar scale and support the idea that minimal differences exist between MDD cases and controls.

Predicting sex, age, general cognition and mental health with machine learning on brain structural connectomes.

There is an increasing expectation that advanced, computationally expensive machine learning (ML) techniques, when applied to large population-wide neuroimaging datasets, will help to uncover key differences in the human brain in health and disease. We take a comprehensive approach to explore how multiple aspects of brain structural connectivity can predict sex, age, general cognitive function and general psychopathology, testing different ML algorithms from deep learning (DL) model (BrainNetCNN) to classical ML methods. We modelled N = 8183 structural connectomes from UK Biobank using six different structural network weightings obtained from diffusion MRI. Streamline count generally provided the highest prediction accuracies in all prediction tasks. DL did not improve on prediction accuracies from simpler linear models. Further, high correlations between gradient attribution coefficients from DL and model coefficients from linear models suggested the models ranked the importance of features in similar ways, which indirectly suggested the similarity in models' strategies for making predictive decision to some extent. This highlights that model complexity is unlikely to improve detection of associations between structural connectomes and complex phenotypes with the current sample size.

Spectral clustering based on structural magnetic resonance imaging and its relationship with major depressive disorder and cognitive ability.

There is increasing interest in using data-driven unsupervised methods to identify structural underpinnings of common mental illnesses, including major depressive disorder (MDD) and associated traits such as cognition. However, studies are often limited to severe clinical cases with small sample sizes and most do not include replication. Here, we examine two relatively large samples with structural magnetic resonance imaging (MRI), measures of lifetime MDD and cognitive variables: Generation Scotland (GS subsample, N = 980) and UK Biobank (UKB, N = 8,900), for discovery and replication, using an exploratory approach. Regional measures of FreeSurfer derived cortical thickness (CT), cortical surface area (CSA), cortical volume (CV) and subcortical volume (subCV) were input into a clustering process, controlling for common covariates. The main analysis steps involved constructing participant K-nearest neighbour graphs and graph partitioning with Markov stability to determine optimal clustering of participants. Resultant clusters were (1) checked whether they were replicated in an independent cohort and (2) tested for associations with depression status and cognitive measures. Participants separated into two clusters based on structural brain measurements in GS subsample, with large Cohen's d effect sizes between clusters in higher order cortical regions, commonly associated with executive function and decision making. Clustering was replicated in the UKB sample, with high correlations of cluster effect sizes for CT, CSA, CV and subCV between cohorts across regions. The identified clusters were not significantly different with respect to MDD case-control status in either cohort (GS subsample: pFDR = .2239-.6585; UKB: pFDR = .2003-.7690). Significant differences in general cognitive ability were, however, found between the clusters for both datasets, for CSA, CV and subCV (GS subsample: d = 0.2529-.3490, pFDR  < .005; UKB: d = 0.0868-0.1070, pFDR  < .005). Our results suggest that there are replicable natural groupings of participants based on cortical and subcortical brain measures, which may be related to differences in cognitive performance, but not to the MDD case-control status.

Automated classification of depression from structural brain measures across two independent community-based cohorts.

Major depressive disorder (MDD) has been the subject of many neuroimaging case-control classification studies. Although some studies report accuracies ≥80%, most have investigated relatively small samples of clinically-ascertained, currently symptomatic cases, and did not attempt replication in larger samples. We here first aimed to replicate previously reported classification accuracies in a small, well-phenotyped community-based group of current MDD cases with clinical interview-based diagnoses (from STratifying Resilience and Depression Longitudinally cohort, 'STRADL'). We performed a set of exploratory predictive classification analyses with measures related to brain morphometry and white matter integrity. We applied three classifier types-SVM, penalised logistic regression or decision tree-either with or without optimisation, and with or without feature selection. We then determined whether similar accuracies could be replicated in a larger independent population-based sample with self-reported current depression (UK Biobank cohort). Additional analyses extended to lifetime MDD diagnoses-remitted MDD in STRADL, and lifetime-experienced MDD in UK Biobank. The highest cross-validation accuracy (75%) was achieved in the initial current MDD sample with a decision tree classifier and cortical surface area features. The most frequently selected decision tree split variables included surface areas of bilateral caudal anterior cingulate, left lingual gyrus, left superior frontal, right precentral and paracentral regions. High accuracy was not achieved in the larger samples with self-reported current depression (53.73%), with remitted MDD (57.48%), or with lifetime-experienced MDD (52.68-60.29%). Our results indicate that high predictive classification accuracies may not immediately translate to larger samples with broader criteria for depression, and may not be robust across different classification approaches.

Pipeline comparisons of convolutional neural networks for structural connectomes: predicting sex across 3,152 participants.

With several initiatives well underway towards amassing large and high-quality population-based neuroimaging datasets, deep learning is set to push the boundaries of what is possible in classification and prediction in neuroimaging studies. This includes those that derive increasingly popular structural connectomes, which map out the connections (and their relative strengths) between brain regions. Here, we test different Convolutional Neural Network (CNN) models in a benchmark sex prediction task in a large sample of N=3,152 structural connectomes acquired from the UK Biobank, and compare results across different connectome processing choices. The best results (76.5% test accuracy) were achieved using Fractional Anisotropy (FA) weighted connectomes, without sparsification, and with a simple weight normalisation through division by the maximum FA value. We also confirm that for structural connectomes, a Graph CNN approach, the recently proposed BrainNetCNN, outperforms an image-based CNN.