Prediction of 1p/19q codeletion status in diffuse lower-grade glioma using multimodal MRI radiomics / 南方医科大学学报

OBJECTIVE@#To develop a noninvasive method for prediction of 1p/19q codeletion in diffuse lower-grade glioma (DLGG) based on multimodal magnetic resonance imaging (MRI) radiomics.@*METHODS@#We collected MRI data from 104 patients with pathologically confirmed DLGG between October, 2015 and September, 2022. A total of 535 radiomics features were extracted from T2WI, T1WI, FLAIR, CE-T1WI and DWI, including 70 morphological features, 90 first order features, and 375 texture features. We constructed logistic regression (LR), logistic regression least absolute shrinkage and selection operator (LRlasso), support vector machine (SVM) and Linear Discriminant Analysis (LDA) radiomics models and compared their predictive performance after 10-fold cross validation. The MRI images were reviewed by two radiologists independently for predicting the 1p/19q status. Receiver operating characteristic curves were used to evaluate classification performance of the radiomics models and the radiologists.@*RESULTS@#The 4 radiomics models (LR, LRlasso, SVM and LDA) achieved similar area under the curve (AUC) in the validation dataset (0.833, 0.819, 0.824 and 0.819, respectively; P>0.1), and their predictive performance was all superior to that of resident physicians of radiology (AUC=0.645, P=0.011, 0.022, 0.016, 0.030, respectively) and similar to that of attending physicians of radiology (AUC=0.838, P>0.05).@*CONCLUSION@#Multiparametric MRI radiomics models show good performance for noninvasive prediction of 1p/19q codeletion status in patients with in diffuse lower-grade glioma.

The value of wholeGtumor texture analysis of contrastGenhanced T1 WI in differentiating cystic glioma from brain abscess / 实用放射学杂志

Objective To evaluate the feasibility of wholeGtumor texture analysis of contrastGenhanced T1 WI (T1 Ce)in differentiating cystic glioma (CG)from brain abscess (BA).Methods MRI data of 25 cases of ringGenhanced CG and 24 cases of BA proven pathologically were retrospectively studied.All the patients underwent preGsurgery MRI plain and contrastGenhanced scans.FireVoxel software was used to outline the ROI of the wholeGtumor.The signal intensity histogram and related texture parameters of the 3D ROI were obtained,including mean, median,standard deviation,inhomogeneity,skewness,kurtosis and entropy.The data were first tested for normality and the differences in wholeG tumor texture analysis parameters of T1 Ce between CGs and BAs were compared using the independentGsample t test(normal distribution)and MannGWhitney rank sum test (skewed distribution).ROC curve was used to evaluate the efficacy of the parameter in differentiating CG from BA.Results There were statistical significances in the parameters of mean,median,standard deviation,inhomogeneity and skewness between CGs and BAs(P＜0.05),and there were no any statistical significances in kurtosis and entropy between CGs and BAs(P＞0.05).In all the texture parameters,the AUC of inhomogeneity was the largest(0.988),and when the threshold was 0.314, the sensitivity and the specificity were 92.60% and 9 7.1 0%,respectively.Conclusion Some of the quantitative parameters of the wholeGtumor texture analysis of T1 Ce(mean,median,standard deviation,inhomogeneity and skewness)could provide reliable and objective evidences for imaging differential diagnosis of CG and BA preGsurgery.

Comparative study of clinical and MRI features between intracranial solitary fibrous tumor/hemangiopericytoma and meningioma / 中国医学影像技术

Objective To investigate the MRI features of intracranial solitary fibrous tumors/hemangiopericytomas (SFT/HPC),and to compare these findings with those of intracranial meningiomas.Methods The clinical features and MRI findings in 28 patients of intracranial SFT/HPC (SFT/HPC group)and 68 patients of meningiomas (meningiomas group) confirmed by operation and pathology were retrospectively analyzed.The indicators of two groups were compared.Results Shape of tumor,signal homogeneous,signal voids of vessel in tumor,hypointense signal nodules on T2WI and enhanded,cystic or necrosis in tumor,meningeal tail sign,changes of the nearby bone,sex,Ki-67％ level,blood lose in surgery had significant differences between SFT/HPC group and meningiomas group (all P＜0.05).Conclusion There are some differences between intracranial SFT/HPC and meningiomas.It is helpful in diagnosis and differential diagnosis through the comparative analysis of the imaging signs.