High-order radiomics features based on T2 FLAIR MRI predict multiple glioma immunohistochemical features: A more precise and personalized gliomas management

Abstract

Objective To investigate the performance of high-order radiomics features and models based on T2weighted fluid-attenuated inversion recovery (T2 FLAIR) in predicting the immunohistochemical biomarkers of glioma, in order to execute a non-invasive, more precise and personalized glioma disease management. Methods 51 pathologically confirmed gliomas patients committed in our hospital from March 2015 to June 2018 were retrospective analysis, and Ki-67, vimentin, S-100 and CD34 immunohistochemical data were collected. The volumes of interest (VOIs) were manually sketched and the radiomics features were extracted. Feature reduction was performed by ANOVA+ Mann-Whiney, spearman correlation analysis, least absolute shrinkage and selection operator (LASSO) and Gradient descent algorithm (GBDT). SMOTE technique was used to solve the data bias between two groups. Comprehensive binary logistic regression models were established. Area under the ROC curves (AUC), sensitivity, specificity and accuracy were used to evaluate the predict performance of models. Models reliability were decided according to the standard net benefit of the decision curves. Results Four clusters of significant features were screened out and four predicting models were constructed. AUC of Ki-67, S-100, vimentin and CD34 models were 0.

Unraveling response to temozolomide in preclinical GL261 glioblastoma with MRI/MRSI using radiomics and signal source extraction

“…This agrees with the available literature, for example, Ref. 37 describes features such as GLRLM correlating with histopathological features such as Ki67 in high-grade glioma. Recent work 38 also described the value of GLRLM and GLSZM for evaluating response to therapy in GB, being able to distinguish pseudoprogression from true progression.…”

Interpreting response to TMZ therapy in murine GL261 glioblastoma by combining Radiomics, Convex-NMF and feature selection in MRI/MRSI data analysis

“…The local effects of these cells against the GB mass, may also cause local changes that could be spotted by MRI. This is supported by results described by others [26], in which radiomics features such as GLRLM correlate with histopathological features such as Ki67 in high grade glioma. Recent work [27] also described the value of GLRLM and GLSZM for evaluating response to therapy in GB, being able to distinguish pseudoprogression from true progression.…”

Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma

“…As artificial intelligence develops at an extraordinarily pace, countless applications have been created in the past decade (28)(29)(30). Recently, AI has been increasingly adopted to diagnose and predict some diseases, while the medical image analysis community has paid particular attention to the success of machine learning in computer vision (31,32). Some researchers have been initiated into applying AI techniques to the quantification of early rheumatoid arthritis using Magnetic Resonance Imaging (MRI) data (33).…”