We propose an efficient sequence for the acquisition of multiple contrasts for MR-only radiotherapy. By including T2-weighted echoes to a gradient echo sequence, this sequence provides T1- and T2-weighted imaging and water-fat separation in a single 4 minute acquisition. A previously trained deep neural network for synthetic CT generation was successfully applied to this new sequence, demonstrating that synthetic CT-based dose calculations can be performed. Furthermore, increased contrast between the anatomies of interest shows promise for (automatic) segmentation.
This abstract and the presentation materials are available to members only; a login is required.