![]() Our results indicate that the incorporation of diffusion- and perfusion-weighted MR imaging into an MR radiomics model to improve prognostication in glioblastoma patients improved its performance over that achievable using clinical predictors alone. The multiparametric MR prognostic model also showed robustness in external validation (C-index, 0.70). The results showed that the multiparametric MR prognostic model (radiomics score + clinical predictors) exhibited good discrimination (C-index, 0.74) and performed better than a conventional MR radiomics model (C-index, 0.65, P < 0.0001) or clinical predictors (C-index, 0.66 P < 0.0001). A multiparametric MR prognostic model was built using the radiomic score and clinical predictors. After radiomic feature selection using LASSO regression, an individualized radiomic score was calculated. Radiomic features were extracted from contrast-enhanced T1-weighted imaging, fluid-attenuated inversion recovery, diffusion-weighted imaging, and dynamic susceptibility contrast imaging. A total of 216 patients with newly diagnosed glioblastoma were enrolled from two tertiary medical centers and divided into training (n = 158) and external validation sets (n = 58). We aimed to develop and validate a multiparametric MR radiomics model using conventional, diffusion-, and perfusion-weighted MR imaging for better prognostication in patients with newly diagnosed glioblastoma.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |