A large number of morphology-based studies have previously reported a variety of regional abnormalities in hemispheric asymmetry in Alzheimer’s disease (AD). Recently, neuroimaging studies have revealed changes in the topological organization of the structural network in AD. However, little is known about the alterations in topological asymmetries. In the present study, we used diffusion tensor image tractography to construct the hemispheric brain white matter networks of 25 AD patients, 95 mild cognitive impairment (MCI) patients, and 48 normal control (NC) subjects. Graph theoretical approaches were then employed to estimate hemispheric topological properties. Rightward asymmetry in both global and local network efficiencies were observed between the two hemispheres only in AD patients. The brain regions/nodes exhibiting increased rightward asymmetry in both AD and MCI patients were primarily located in the parahippocampal gyrus and cuneus. The observed rightward asymmetry was attributed to changes in the topological properties of the left hemisphere in AD patients. Finally, we found that the abnormal hemispheric asymmetries of brain network properties were significantly correlated with memory performance (Rey’s Auditory Verbal Learning Test). Our findings provide new insights into the lateralized nature of hemispheric disconnectivity and highlight the potential for using hemispheric asymmetry of brain network measures as biomarkers for AD.

No abstract

This study aims to develop a CT-based radiomic features analysis approach for diagnosis of ground-glass opacity (GGO) pulmonary nodules, and also assess whether computer-aided diagnosis (CADx) performance changes in classifying between benign and malignant nodules associated with histopathological subtypes namely, adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC), respectively. The study involves 182 histopathology-confirmed GGO nodules collected from two cancer centers. Among them, 59 are benign, 50 are AIS, 32 are MIA, and 41 are IAC nodules. Four training/testing data sets—(1) all nodules, (2) benign and AIS nodules, (3) benign and MIA nodules, (4) benign and IAC nodules—are assembled based on their histopathological subtypes. We first segment pulmonary nodules depicted in CT images by using a 3D region growing and geodesic active contour level set algorithm. Then, we computed and extracted 1117 quantitative imaging features based on the 3D segmented nodules. After conducting radiomic features normalization process, we apply a leave-one-out cross-validation (LOOCV) method to build models by embedding with a Relief feature selection, synthetic minority oversampling technique (SMOTE) and three machine-learning classifiers namely, support vector machine classifier, logistic regression classifier and Gaussian Naïve Bayes classifier. When separately using four data sets to train and test three classifiers, the average areas under receiver operating characteristic curves (AUC) are 0.75, 0.55, 0.77 and 0.93, respectively. When testing on an independent data set, our scheme yields higher accuracy than two radiologists (61.3% versus radiologist 1: 53.1% and radiologist 2: 56.3%). This study demonstrates that: (1) the feasibility of using CT-based radiomic features analysis approach to distinguish between benign and malignant GGO nodules, (2) higher performance of CADx scheme in diagnosing GGO nodules comparing with radiologist, and (3) a consistently positive trend between classification performance and invasive grade of GGO nodules. Thus, to improve the CADx performance in diagnosing of GGO nodules, one should assemble an optimal training data set dominated with more nodules associated with non-invasive lung adenocarcinoma (i.e. AIS and MIA).

The thalamus is a relay center between various subcortical brain areas and the cerebral cortex with delineation of its constituent nuclei being of particular interest in many applications. While previous studies have demonstrated efficacy of connectivity-based thalamus segmentation, they used approaches that do not consider the dynamic nature of thalamo-cortical interactions. In this study, we explicitly exploited the dynamic variation of thalamo-cortical connections to identify different states of functional connectivity and performed state-specific thalamus parcellation. With normalized spectral clustering successively applied in temporal and spatial domains, nine thalamo-cortical connectivity states were identified and the dynamic thalamus parcellation revealed finer thalamic structures with improved atlas correspondence. The present results extend our understanding of thalamo-cortical connectivity and provide a more comprehensive view of the thalamo-cortical interaction.

No abstract