The aim of this study was to elucidate a multiple diffusion-model-based radiomics model in detecting radiation-induced brain injury (RI). We used diffusion features derived from DTI, DKI, NODDI and MAP-MRI models and chose LR as the classifier to construct a prediction model. The results showed that the most accurate prediction was achieved by incorporating the DKI-AD and RTPP into a nomogram, with AUC and accuracy reached 0.8356 and 0.8182.
This abstract and the presentation materials are available to members only; a login is required.