Multi-label brain segmentation from brain magnetic resonance imaging (MRI) provides valuable structural information for most neurological analyses. Due to the complexity of the brain segmentation algorithm, it could delay the delivery of neuroimaging findings. Therefore, we introduce Split-Attention U-Net (SAU-Net), a convolutional neural network with skip pathways and a split-attention module that segments brain MRI scans. The proposed architecture employs split-attention blocks, skip pathways with pyramid levels, and evolving normalization layers. For efficient training, we performed pre-training and fine-tuning with the original and manually modified FreeSurfer labels, respectively. This learning strategy enables involvement of heterogeneous neuroimaging data in the training without the need for many manual annotations. Using nine evaluation datasets, we demonstrated that SAU-Net achieved better segmentation accuracy with better reliability that surpasses those of state-of-the-art methods. We believe that SAU-Net has excellent potential due to its robustness to neuroanatomical variability that would enable almost instantaneous access to accurate neuroimaging biomarkers and its swift processing runtime compared to other methods investigated.
Objective Despite multiple drugs available, a large proportion of patients with generalized anxiety disorder (GAD) do not show adequate response and remission. Thus, additional novel pharmacological agents are needed to increase treatment option for GAD. We aimed to investigate efficacy and safety of agomelatine in the treatment of GAD by conducting a meta-analysis. Methods An extensive search of multiple databases and clinical trial registries were conducted. Mean change in total scores on Hamilton Anxiety Rating Scale (HAM-A) from baseline to endpoint was our primary outcome measure. Secondary efficacy measures included response and remission rates, as defined by a 50% or greater reduction in HAM-A total scores and a score of 7 or less in HAM-A total scores at study endpoint respectively. Results Four published double blinded, randomized, placebo-controlled trials were included in this meta-analysis. Agomelatine more significantly (standardized mean difference = −0.56, p = 0.004) improved HAM-A total scores than placebo. The odds ratios (ORs) of agomelatine over placebo for response and remission rates were 3.75 ( p < 0.00001) and 2.74 ( p < 0.00001), respectively. Agomelatine was generally well tolerated with insignificance in dropout rate, somnolence, headache, nasopharyngitis, and dizziness compared with placebo. However, agomelatine showed significantly higher incidence of liver function increment (OR = 3.13, p = 0.01) and nausea (OR = 3.27, p = 0.02). Conclusion We showed that agomelatine may be another treatment option in patients with GAD. However, the results should be interpreted and translated into clinical practice with caution because the meta-analysis was based on limited numbers of clinical trials.
Objective Previous studies investigating association of alcohol intake and fracture risk in elderly yielded conflicting results. We first examined the association between alcohol intake and total fracture risk in elderly subjects and further analyzed whether the association varied by fracture locations.Methods This is a nationwide population-based cohort study which included all people aged 66 (n=1,431,539) receiving the National Screening Program during 2009–2014. Time-to-event were defined as duration from study recruitment, the day they received health screening, to the occurrence of fracture.Results Total fracture was significantly lower in mild drinkers [adjusted hazard ratio (aHR)=0.952; 95% confidence interval (95% CI) =0.931–0.973] and higher in heavy drinkers (aHR=1.246; 95% CI=1.201–1.294) than non-drinkers. Risk pattern of alcohol consumption and fracture differed according to affected bones. Similar J-shaped trends were observed for vertebra fractures, but risk of limb fracture showed a linear relationship with alcohol intake. For hip fracture, risk decrement was more pronounced in mild and moderate drinkers, and significant increment was noted only in very severe drinkers [≥60 g/day; (aHR)=1.446; 1.162–1.801].Conclusion Light to moderate drinking generally lowered risk of fractures, but association between alcohol and fracture risk varied depending on the affected bone lesions.
Objective Alzheimer’s disease (AD) is the most common type of dementia and the prevalence rapidly increased as the elderly population increased worldwide. In the contemporary model of AD, it is regarded as a disease continuum involving preclinical stage to severe dementia. For accurate diagnosis and disease monitoring, objective index reflecting structural change of brain is needed to correctly assess a patient’s severity of neurodegeneration independent from the patient’s clinical symptoms. The main aim of this paper is to develop a random forest (RF) algorithm-based prediction model of AD using structural magnetic resonance imaging (MRI).Methods We evaluated diagnostic accuracy and performance of our RF based prediction model using newly developed brain segmentation method compared with the Freesurfer’s which is a commonly used segmentation software.Results Our RF model showed high diagnostic accuracy for differentiating healthy controls from AD and mild cognitive impairment (MCI) using structural MRI, patient characteristics, and cognitive function (HC vs. AD 93.5%, AUC 0.99; HC vs. MCI 80.8%, AUC 0.88). Moreover, segmentation processing time of our algorithm (<5 minutes) was much shorter than of Freesurfer’s (6–8 hours).Conclusion Our RF model might be an effective automatic brain segmentation tool which can be easily applied in real clinical practice.
Studies investigating association of depression with overall survival (OS) after allogeneic hematopoietic stem cell transplantation (allo-HSCT) yielded conflicting results. A nationwide cohort study, which included all adult patients [n = 7,170; depression group, 13.3% (N = 956); non-depression group, 86.7% (N = 6,214)] who received allo-HSCT from 2002 to 2018 in South Korea, analyzed risk of pre-transplant depression in OS of allo-HSCT. Subjects were followed from the day they received allo-HSCT, to occurrence of death, or last follow-up day (December 31, 2018). Median age at allo-HSCT for depression and non-depression groups were 50 and 45 (p < 0.0001), respectively. Two groups also differed in rate of females (depression group, 55.8%; non-depression group, 43.8%; p < 0.0001) and leukemia (depression group, 61.4%; non-depression group, 49.7%; p < 0.0001). After a median follow-up of 29.1 months, 5-year OS rate was 63.1%. Cox proportional-hazard regression evaluated an adjusted risk of post-transplant mortality related to depression: OS decreased sequentially from no depression (adjusted hazard ratio [aHR] = 1) to pre-transplant depression only (aHR = 1.167, CI: 1.007–1.352, p = 0.04), and to having both depression and anxiety disorder (aHR = 1.202, CI: 1.038–1.393, p = 0.014) groups. Pre-transplant anxiety (anxiety only) did not have significant influence in OS. Additional medical and psychiatric care might be necessary in patients who experienced depression, especially with anxiety, before allo-HSCT.
Normative brain magnetic resonance imaging (MRI) is essential to interpret the state of an individual’s brain health. However, a normative study is often expensive for small research groups. Although several attempts have been made to establish brain MRI norms, the focus has been limited to certain age ranges. This study aimed to establish East Asian normative brain data using multi-site MRI and determine the robustness of these data for clinical research. Normative MRI was gathered covering a wide range of cognitively normal East Asian populations (age: 18–96 years) from two open sources and three research sites. Eight sub-regional volumes were extracted in the left and right hemispheres using an in-house deep learning-based tool. Repeated measure consistency and multicenter reliability were determined using intraclass correlation coefficients and compared to a widely used tool, FreeSurfer. Our results showed highly consistent outcomes with high reliability across sites. Our method outperformed FreeSurfer in repeated measure consistency for most structures and multicenter reliability for all structures. The normative MRI we constructed was able to identify sub-regional differences in mild cognitive impairments and dementia after covariate adjustments. Our investigation suggests it is possible to provide a sound normative reference for neurodegenerative or aging research.
Objective Despite a high prevalence of dementia in older adults hospitalized with severe acute respiratory syndrome coronavirus 2 infection (SARS-CoV-2), or so called COVID-19, research investigating association between preexisting diagnoses of dementia and prognosis of COVID-19 is scarce. We aimed to investigate treatment outcome of patients with dementia after COVID-19. Methods We explored a nationwide cohort with a total of 2,800 subjects older than 50 years who were diagnosed with COVID-19 between January and April 2020. Among them, 223 patients had underlying dementia (dementia group). We matched 1:1 for each dementia- non-dementia group pair yielding 223 patients without dementia (no dementia group) using propensity score matching. Results Mortality rate after COVID-19 was higher in dementia group than in no dementia group (33.6% vs. 20.2%, p=0.002). Dementia group had higher proportion of patients requiring invasive ventilatory support than no dementia group (34.1% vs. 22.0%, p=0.006). Multivariable analysis showed that dementia group had a higher risk of mortality than no dementia group (odds ratio=3.05, p<0.001). We also found that patients in dementia group had a higher risk of needing invasive ventilatory support than those in no dementia group. Conclusion Our results suggest that system including strengthen quarantines are required for patients with dementia during the COVID- 19 pandemic.
Objective: Diverse resting-state functional magnetic resonance imaging (rs-fMRI) studies showed that rs-fMRI might be able to reflect the earliest detrimental effect of cerebral beta-amyloid (Aβ) pathology. However, no previous studies specifically compared the predictive value of different rs-fMRI parameters in preclinical AD.Methods: A total of 106 cognitively normal adults (Aβ+ group = 66 and Aβ− group = 40) were included. Three different rs-fMRI parameter maps including functional connectivity (FC), fractional amplitude of low-frequency fluctuations (fALFF), and regional homogeneity (ReHo) were calculated. Receiver operating characteristic (ROC) curve analyses were utilized to compare classification performance of the three rs-fMRI parameters.Results: FC maps showed the best classifying performance in ROC curve analysis (AUC, 0.915, p < 0.001). Good but weaker performance was achieved by using ReHo maps (AUC, 0.836, p < 0.001) and fALFF maps (AUC, 0.804, p < 0.001). The brain regions showing the greatest discriminative power included the left angular gyrus for FC, left anterior cingulate for ReHo, and left middle frontal gyrus for fALFF. However, among the three measurements, ROI-based FC was the only measure showing group difference in voxel-wise analysis.Conclusion: Our results strengthen the idea that rs-fMRI might be sensitive to earlier changes in spontaneous brain activity and FC in response to cerebral Aβ retention. However, further longitudinal studies with larger sample sizes are needed to confirm their utility in predicting the risk of AD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.