Gender differences in functional connectivities between insular subdivisions and selective pain-related brain structures.

BACKGROUND: The incidence of pain disorders in women is higher than in men, making gender differences in pain a research focus. The human insular cortex is an important brain hub structure for pain processing and is divided into several subdivisions, serving different functions in pain perception. Here we aimed to examine the gender differences of the functional connectivities (FCs) between the twelve insular subdivisions and selected pain-related brain structures in healthy adults. METHODS: Twenty-six healthy males and 11 age-matched healthy females were recruited in this cross-sectional study. FCs between the 12 insular subdivisions (as 12 regions of interest (ROIs)) and the whole brain (ROI-whole brain level) or 64 selected pain-related brain regions (64 ROIs, ROI-ROI level) were measured between the males and females. RESULTS: Significant gender differences in the FCs of the insular subdivisions were revealed: (1) The FCs between the dorsal dysgranular insula (dId) and other brain regions were significantly increased in males using two different techniques (ROI-whole brain and ROI-ROI analyses); (2) Based on the ROI-whole brain analysis, the FC increases in 4 FC-pairs were observed in males, including the left dId - the right median cingulate and paracingulate/ right posterior cingulate gyrus/ right precuneus, the left dId - the right median cingulate and paracingulate, the left dId - the left angular as well as the left dId - the left middle frontal gyrus; (3) According to the ROI-ROI analysis, increased FC between the left dId and the right rostral anterior cingulate cortex was investigated in males. CONCLUSION: In summary, the gender differences in the FCs of the insular subdivisions with pain-related brain regions were revealed in the current study, offering neuroimaging evidence for gender differences in pain processing. TRIAL REGISTRATION: ClinicalTrials.gov, NCT02820974 . Registered 28 June 2016.

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features.

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.