Abstract 1116
Background
The purpose of current study is to discriminate primary central nervous system lymphoma from metastatic brain tumors with 3D texture features.
Methods
A total number of 120 patients involved this study, 58 with PCNSL and 62 with MBTs. Texture features were retrieved from histogram matrix and GLCM matrix. Mann Whitney U tests were performed to detect if texture feature were significantly different between two type of tumors. Binary logistic regressions were conducted to detect if they could be taken as independent predictors, based on which integrated model was built. ROC curves of each parameter were generated to evaluate the ability in discrimination.
Results
Three texture features (histo-Kurtosis, GLCM-Contrast and GLCM-Dissimilarity from post contrast T1WI) were independent predictors in discrimination, whose AUC were 0.632, 0.742 and 0.706 respectively. The integrated model represented better diagnostic value than any single features. ROC curve suggested the AUC of model was 0.832, representing practical clinical value.
Conclusions
Texture analysis has potential in the differentiation between primary central nervous system lymphoma from metastatic brain tumors. Moreover, combination of single texture shows more promising and effective ability in discrimination.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
Xuelei Ma.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.