Distinguishing brain inflammation from grade II glioma in population without contrast enhancement: a radiomics analysis based on conventional MRI.

PURPOSE: In populations without contrast enhancement, the imaging features of atypical brain parenchyma inflammations can mimic those of grade II gliomas. The aim of this study was to assess the value of the conventional MR-based radiomics signature in differentiating brain inflammation from grade II glioma. METHODS: Fifty-seven patients (39 patients with grade II glioma and 18 patients with inflammation) were divided into primary (n = 44) and validation cohorts (n = 13). Radiomics features were extracted from T1-weighted images (T1WI) and T2-weighted images (T2WI). Two-sample t-test and least absolute shrinkage and selection operator (LASSO) regression were adopted to select features and build radiomics signature models for discriminating inflammation from glioma. The predictive performance of the models was evaluated via area under the receiver operating characteristic curve (AUC) and compared with the radiologists' assessments. RESULTS: Based on the primary cohort, we developed T1WI, T2WI and combination (T1WI + T2WI) models for differentiating inflammation from glioma with 4, 8, and 5 radiomics features, respectively. Among these models, T2WI and combination models achieved better diagnostic efficacy, with AUC of 0.980, 0.988 in primary cohort and that of 0.950, 0.925 in validation cohort, respectively. The AUCs of radiologist 1's and 2's assessments were 0.661 and 0.722, respectively. CONCLUSION: The signature based on radiomics features helps to differentiate inflammation from grade II glioma and improved performance compared with experienced radiologists, which could potentially be useful in clinical practice.

Increased resting state functional irregularity of T2DM brains with high HbA1c: sign for impaired verbal memory function?

Glycosylated hemoglobin A1c (HbA1c) has been considered as a key contributor to impaired cognition in type 2 diabetes mellitus (T2DM) brains. However, how does it affect the brain and whether the glucose controlling can slow down the process are still unknown. In the current study, T2DM patients with high glycosylated hemoglobin level (HGL) and controls with normal glycosylated hemoglobin level (NGL) were enrolled to investigate the relationships between HbA1c, brain imaging characteristics and cognitive function. First, a series of cognitive tests including California Verbal Learning Test (CVLT) were conducted. Then, the functional irregularity based on resting state functional magnetic resonance imaging data was evaluated via a new data-driven brain entropy (BEN) mapping analysis method. We found that the HGLs exhibited significantly increased BEN in the right precentral gyrus (PreCG.R), the right middle frontal gyrus (MFG.R), the triangular and opercular parts of the right inferior frontal gyrus (IFGtriang.R and IFGoperc.R). The strengths of the functional connections of PreCG.R with the brainstem/cerebellum were decreased. Partial correlation analysis showed that HbA1c had a strong positive correlation to regional BEN and negatively correlated with some CVLT scores. Negative correlations also existed between the BEN of PreCG.R/IFGoperc.R and some CVLT scores, suggesting the correspondence between higher HbA1c, increased BEN and decreased verbal memory function. This study demonstrated the potential of BEN in exploring the functional alterations affected by HbA1c and interpreting the verbal memory function decline. It will help understanding the neurophysiological mechanism of T2DM-induced cognitive decline and taking effective prevention or treatment measures.