•Machine learning methods enable individual treatment response prediction.•Deep learning methods predict treatment response in depression with high accuracy.•The definition of response biomarkers may ...help towards personalized psychiatry.
Mood disorders are characterized by heterogeneity in severity, symptoms and treatment response. The possibility of selecting the correct therapy on the basis of patient-specific biomarker may be a considerable step towards personalized psychiatry. Machine learning methods are gaining increasing popularity in the medical field. Once trained, the possibility to consider single patients in the analyses instead of whole groups makes them particularly appealing to investigate treatment response. Deep learning, a branch of machine learning, lately gained attention, due to its effectiveness in dealing with large neuroimaging data and to integrate them with clinical, molecular or -omics biomarkers.
In this mini-review, we summarize studies that use deep learning methods to predict response to treatment in depression. We performed a bibliographic search on PUBMED, Google Scholar and Web of Science using the terms “psychiatry”, “mood disorder”, “depression”, “treatment”, “deep learning”, “neural networks”. Only studies considering patients’ datasets are considered.
Eight studies met the inclusion criteria. Accuracies in prediction of response to therapy were considerably high in all studies, but results may be not easy to interpret.
The major limitation for the current studies is the small sample size, which constitutes an issue for machine learning methods.
Deep learning shows promising results in terms of prediction of treatment response, often outperforming regression methods and reaching accuracies of around 80%. This could be of great help towards personalized medicine. However, more efforts are needed in terms of increasing datasets size and improved interpretability of results.
The recent widespread use of diffusion tensor imaging (DTI) tractography allowed researchers to investigate the diffusivity modifications and neuroanatomical changes of white matter (WM) fascicles in ...major psychiatric disorders, including bipolar disorder (BD). In BD, corpus callosum (CC) seems to have a crucial role in explaining the pathophysiology and cognitive impairment of this psychiatric disorder. This review aims to provide an overview on the latest results emerging from studies that investigated neuroanatomical changes of CC in BD using DTI tractography.
Bibliographic research was conducted on PubMed, Scopus and Web of Science datasets until March 2022. Ten studies fulfilled our inclusion criteria.
From the reviewed DTI tractography studies a significant decrease of fractional anisotropy emerged in the genu, body and splenium of CC of BD patients compared to controls. This finding is coupled with reduction of fiber density and modification in fiber tract length. Finally, an increase of radial and mean diffusivity in forceps minor and in the entire CC was also reported.
Small sample size, heterogeneity in terms of methodological (diffusion gradient) and clinical (lifetime comorbidity, BD status, pharmacological treatments) characteristics.
Overall, these findings suggest the presence of structural modifications in CC in BD patients, which may in turn explain the cognitive impairments often observed in this psychiatric disorder, especially in executive processing, motor control and visual memory. Finally, structural modifications may suggest an impairment in the amount of functional information and a morphological impact within those brain regions connected by CC.
•This review summarizes the results of DTI tractography studies investigating the CC in BD patients.•Decreased FA and fiber density were found in genu, body and splenium of CC in BD patients.•Deficits in CC in BD patients may explain impairments in executive functions, motor codification and visual memory processes.•Further studies in larger and more homogeneous BD samples are warranted.
•Studies on twins may increase our knowledge of how gene and environment interaction.•Brain characteristics are highly heritable from early childhood to young adulthood.•Environment has a key role in ...mediating brain network differentiation.
Neurodevelopment represents a period of increased opportunity and vulnerability, during which a complex confluence of genetic and environmental factors influences brain growth trajectories, cognitive and mental health outcomes. Recently, magnetic resonance imaging (MRI) studies on twins have increased our knowledge of the extent to which genes, the environment and their interactions shape inter-individual brain variability.
The present review draws from highly salient MRI studies in young twin samples to provide a robust assessment of the heritability of structural and functional brain changes during development.
The available studies suggest that (as with many other traits), global brain morphology and network organization are highly heritable from early childhood to young adulthood. Conversely, genetic correlations among brain regions exhibit heterogeneous trajectories, and this heterogeneity reflects the progressive, experience-related increase in brain network complexity. Studies also support the key role of environment in mediating brain network differentiation via changes of genetic expression and hormonal levels. Thus, rest- and task-related functional brain circuits seem to result from a contextual and dynamic expression of heritability.
Brain segmentation is often the first and most critical step in quantitative analysis of the brain for many clinical applications, including fetal imaging. Different aspects challenge the ...segmentation of the fetal brain in magnetic resonance imaging (MRI), such as the non-standard position of the fetus owing to his/her movements during the examination, rapid brain development, and the limited availability of imaging data. In recent years, several segmentation methods have been proposed for automatically partitioning the fetal brain from MR images. These algorithms aim to define regions of interest with different shapes and intensities, encompassing the entire brain, or isolating specific structures. Deep learning techniques, particularly convolutional neural networks (CNNs), have become a state-of-the-art approach in the field because they can provide reliable segmentation results over heterogeneous datasets. Here, we review the deep learning algorithms developed in the field of fetal brain segmentation and categorize them according to their target structures. Finally, we discuss the perceived research gaps in the literature of the fetal domain, suggesting possible future research directions that could impact the management of fetal MR images.
•We reviewed 39 DL studies for fetal brain segmentation from MR images•U-Net backbone is the dominant method for automatic fetal brain segmentation•There is a segmentation performances convergence for the currently available datasets•Heterogeneous datasets, including pathologies and broader GAs, are required•Super hi-res reconstructed images became standard for fetal brain tissue annotation
BACKGROUNDGrowing evidence suggests the presence of white matter (WM) alterations in bipolar disorder (BD). In this study we aimed to investigate the state of WM structures, in terms of tissue ...integrity and morphological complexity, in BD patients compared to healthy controls (HC), in an attempt to better elucidate the microstructural changes associated with BD.METHODSWe collected a dataset of 399 Diffusion Tensor Magnetic Resonance Imaging (167 BD and 232 healthy controls) images, acquired at five different sites, which was processed with Tract-Based Spatial Statistics (TBSS) and fractal analysis.RESULTSThe TBSS analysis demonstrated significantly lower FA values in the BD group. Diffusion abnormalities were primarily located in the temporo-parietal network. The Fractal Dimension (FD) analysis did not reveal consistent significant differences in the morphological complexity of WM structures between the groups. When the FD values of patients were considered individually, it is possible to notice some localized significant deviations from the healthy population.LIMITATIONSDTI sequences have not been harmonized before acquisition, samples' sizes are heterogeneous.CONCLUSIONSThis study, by applying both TBSS and FD analyses, allows to evaluate diffusion and structural alterations of WM at the same time. The evaluation of WM integrity from these two different perspectives could be useful to better understand the pathophysiological and morphological changes underpinning bipolar disorder.
•Gender differences have been found in depression and anxiety disorders.•The neural basis of gender differences in depression/anxiety disorders are unclear.•Male with PD and GAD had lower GPC+PC and ...glutamate levels compared to controls.•An association between gender and brain metabolites was shown in anxiety spectrum.
Gender differences in mood and anxiety disorders are well-established. However, the neural basis of these differences is not clear yet, especially in terms of brain metabolism. Indeed, although several proton Magnetic Resonance Spectroscopy (¹H MRS) investigations reported different metabolic levels in both depression and anxiety disorders, which have been also linked to symptoms severity and response to treatment, the role of gender on these differences have not been explored yet. Therefore, this study aims at investigating the role of sex in neurometabolic alterations associated with both mood and anxiety disorders. A 3T single-voxel ¹H MRS acquisition of the dorsolateral prefrontal cortex was acquired from 14 Major Depressive Disorder, 10 Generalized Anxiety Disorder (GAD), 11 Panic Disorder (PD), patients and 16 healthy controls (HC). Among males, PD patients showed significantly lower GPC+PC (also observed in GAD+PD) and Glu levels compared to HC. Finally, a significant group x sex interaction effect was observed in the GPC+PC and Glu levels. We proved the presence of an association between sex and brain metabolites in anxiety spectrum.
Fetal Magnetic Resonance Imaging (MRI) is an important noninvasive diagnostic tool to characterize the central nervous system (CNS) development, significantly contributing to pregnancy management. In ...clinical practice, fetal MRI of the brain includes the acquisition of fast anatomical sequences over different planes on which several biometric measurements are manually extracted. Recently, modern toolkits use the acquired two-dimensional (2D) images to reconstruct a Super-Resolution (SR) isotropic volume of the brain, enabling three-dimensional (3D) analysis of the fetal CNS.
We analyzed 17 fetal MR exams performed in the second trimester, including orthogonal T2-weighted (T2w) Turbo Spin Echo (TSE) and balanced Fast Field Echo (b-FFE) sequences. For each subject and type of sequence, three distinct high-resolution volumes were reconstructed via NiftyMIC, MIALSRTK, and SVRTK toolkits. Fifteen biometric measurements were assessed both on the acquired 2D images and SR reconstructed volumes, and compared using Passing-Bablok regression, Bland-Altman plot analysis, and statistical tests.
Results indicate that NiftyMIC and MIALSRTK provide reliable SR reconstructed volumes, suitable for biometric assessments. NiftyMIC also improves the operator intraclass correlation coefficient on the quantitative biometric measures with respect to the acquired 2D images. In addition, TSE sequences lead to more robust fetal brain reconstructions against intensity artifacts compared to b-FFE sequences, despite the latter exhibiting more defined anatomical details.
Our findings strengthen the adoption of automatic toolkits for fetal brain reconstructions to perform biometry evaluations of fetal brain development over common clinical MR at an early pregnancy stage.