Background: A large number of Alzheimer’s disease (AD) studies have focused on medial temporal and cortical atrophy, while changes in the basal ganglia or thalamus have received less attention. Objective: The aim of this study was to investigate the

In a clinical setting, an individual subject classification model rather than a group analysis would be more informative. Specifically, the subtlety of cortical atrophy in some frontotemporal dementia (FTD) patients and overlapping patterns of atrophy among three FTD clinical syndromes including behavioral variant FTD (bvFTD), non-fluent/agrammatic variant primary progressive aphasia (nfvPPA), and semantic variant PPA (svPPA) give rise to the need for classification models at the individual level. In this study, we aimed to classify each individual subject into one of the diagnostic categories in a hierarchical manner by employing a machine learning-based classification method. We recruited 143 patients with FTD, 50 patients with Alzheimer's disease (AD) dementia, and 146 cognitively normal subjects. All subjects underwent a three-dimensional volumetric brain magnetic resonance imaging (MRI) scan, and cortical thickness was measured using FreeSurfer. We applied the Laplace Beltrami operator to reduce noise in the cortical thickness data and to reduce the dimension of the feature vector. Classifiers were constructed by applying both principal component analysis and linear discriminant analysis to the cortical thickness data. For the hierarchical classification, we trained four classifiers using different pairs of groups: Step 1 - CN vs. FTD + AD, Step 2 - FTD vs. AD, Step 3 - bvFTD vs. PPA, Step 4 - svPPA vs. nfvPPA. To evaluate the classification performance for each step, we used a10-fold cross-validation approach, performed 1000 times for reliability. The classification accuracy of the entire hierarchical classification tree was 75.8%, which was higher than that of the non-hierarchical classifier (73.0%). The classification accuracies of steps 1-4 were 86.1%, 90.8%, 86.9%, and 92.1%, respectively. Changes in the right frontotemporal area were critical for discriminating behavioral variant FTD from PPA. The left frontal lobe discriminated nfvPPA from svPPA, while the bilateral anterior temporal regions were critical for identifying svPPA. In the present study, our automated classifier successfully classified FTD clinical subtypes with good to excellent accuracy. Our classifier may help clinicians diagnose FTD subtypes with subtle cortical atrophy and facilitate appropriate specific interventions.

Major depressive disorder (MDD) and suicidal behavior have been associated with structural and functional changes in the brain. However, little is known regarding alterations of brain networks in MDD patients with suicidal ideation. We investigated whether or not MDD patients with suicidal ideation have different topological organizations of white matter networks compared with MDD patients without suicidal ideation. Participants consisted of 24 patients with MDD and suicidal ideation, 25 age- and gender-matched MDD patients without suicidal ideation and 31 healthy subjects. A network-based statistics (NBS) and a graph theoretical analysis were performed to assess differences in the inter-regional connectivity. Diffusion tensor imaging (DTI) was performed to assess topological changes according to suicidal ideation in MDD patients. The Scale for Suicide Ideation (SSI) and the Korean version of the Barrett Impulsiveness Scale (BIS) were used to assess the severity of suicidal ideation and impulsivity, respectively. Reduced structural connectivity in a characterized subnetwork was found in patients with MDD and suicidal ideation by utilizing NBS analysis. The subnetwork included the regions of the frontosubcortical circuits and the regions involved in executive function in the left hemisphere (rostral middle frontal, pallidum, superior parietal, frontal pole, caudate, putamen and thalamus). The graph theoretical analysis demonstrated that network measures of the left rostral middle frontal had a significant positive correlation with severity of SSI (r=0.59,P=0.02) and BIS (r=0.59,P=0.01). The total edge strength that was significantly associated with suicidal ideation did not differ between MDD patients without suicidal ideation and healthy subjects. Our findings suggest that the reduced frontosubcortical circuit of structural connectivity, which includes regions associated with executive function and impulsivity, appears to have a role in the emergence of suicidal ideation in MDD patients.

Accumulating evidence suggests that Alzheimer’s disease (AD) is heterogenous and can be classified into several subtypes. Here, we propose a robust subtyping method for AD based on cortical atrophy patterns and graph theory. We calculated similarities between subjects in their atrophy patterns throughout the whole brain, and clustered subjects with similar atrophy patterns using the Louvain method for modular organization extraction. We applied our method to AD patients recruited at Samsung Medical Center and externally validated our method by using the AD Neuroimaging Initiative (ADNI) dataset. Our method categorized very mild AD into three clinically distinct subtypes with high reproducibility (>90%); the parietal-predominant (P), medial temporal-predominant (MT), and diffuse (D) atrophy subtype. The P subtype showed the worst clinical presentation throughout the cognitive domains, while the MT and D subtypes exhibited relatively mild presentation. The MT subtype revealed more impaired language and executive function compared to the D subtype.

Despite recent developments in neuroimaging, alterations of brain functional connectivity in major depressive disorder (MDD) patients with suicidal ideation are poorly understood. This study investigated specific changes of suicidal ideation in functional connectivity of MDD patients. Whole brain functional connectivity in 46 patients with MDD (23 with suicidal ideation and 23 without) and 36 age- and gender- matched healthy controls were compared using resting-state functional Magnetic Resonance Imaging (fMRI) analyzed with network-based statistics (NBS) and graph-theoretical methods. Decreased functional connectivity in a characterized sub-network was observed in patients with MDD and suicidal ideation (FDR-adjusted p < 0.05). The sub-network included the regions of the fronto-thalamic circuits in the left hemisphere. The network measures of the left superior frontal gyrus, pars orbitalis (r = −0.40, p = 0.009), left thalamus (r = −0.41, p = 0.009), and right thalamus (r = −0.51, p = −0.002) were shown, through graph theoretical analysis, to be significantly negatively correlated with severity of suicidal ideation. The reduced functional connectivity in left orbitofrontal-both thalamic regions with suicidal ideation in MDD were inversely proportional to the severity of suicidality independent from depression severity. These findings suggest problems with decision-making and information integration in MDD patients with suicidal ideation.