Search

Abstract We investigated the potential of machine learning for diagnostic classification in late-life major depression based on an advanced whole brain white matter segmentation framework. Twenty-six late-life depression and 12 never depressed individuals aged > 55 years, matched for age, MMSE, and education underwent brain diffusion tensor imaging and a multi-contrast, multi-atlas segmentation in MRIcloud. Fractional anisotropy volume, mean fractional anisotropy, trace, axial and radial diffusivity (RD) extracted from 146 white matter parcels for each subject were used to train and test the AdaBoost classifier using stratified 12-fold cross validation. Performance was evaluated using various measures. The statistical power of the classifier was assessed using label permutation test. Statistical analysis did not yield significant differences in DTI measures between the groups. The classifier achieved a balanced accuracy of 71% and an Area Under the Receiver Operator Characteristic Curve (ROC-AUC) of 0.81 by trace, and a balanced accuracy of 70% and a ROC-AUC of 0.80 by RD, in limbic, cortico-basal ganglia-thalamo-cortical loop, brainstem, external and internal capsules, callosal and cerebellar structures. Both indices shared important structures for classification, while fornix was the most important structure for classification by both indices. The classifier proved statistically significant, as trace and RD ROC-AUC scores after permutation were lower than those obtained with the actual data (P = 0.022 and P = 0.024, respectively). Similar results were obtained with the Gradient Boosting classifier, whereas the RBF-kernel Support Vector Machine with k-best feature selection did not exceed the chance level. Finally, AdaBoost significantly predicted the class using all features together. Limitations are discussed. The results encourage further investigation of the implemented methods for computer aided diagnostics and anatomically informed therapeutics.

Neuropsychological profiling and clinical DTI of three stroke patients highlight the importance of the ventral language system in normal language comprehension and cognition.

Abstract Chronic cannabis use and schizophrenia are both thought to affect reward processing. While behavioural and neural effects on reward processing have been investigated in both conditions, their interaction has not been studied, although chronic cannabis use is common among these patients. In the present study eighty-nine participants divided into four groups (control chronic cannabis users and non-users; schizophrenia patient cannabis users and non-users) performed a two-choice decision task, preceded by monetary cues (high/low reward/punishment or neutral), while being scanned using functional magnetic resonance imaging. Reward and punishment anticipation resulted in activation of regions of interest including the thalamus, striatum, amygdala and insula. Chronic cannabis use and schizophrenia had opposing effects on reward anticipation sensitivity. More specifically control users and patient non-users showed faster behavioural responses and increased activity in anterior/posterior insula for high magnitude cues compared to control non-users and patient users. The same interaction pattern was observed in the activation of the right thalamus for reward versus punishment cues. This study provided evidence for interaction of chronic cannabis use and schizophrenia on reward processing and highlights the need for future research addressing the significance of this interaction for the pathophysiology of these conditions and its clinical consequences.