https://www.selleckchem.com/
97mm). In the 2D validation, the median estimation error on anatomical landmarks' position resulted below 4mm in every scenario, whereas in the 3D validation it was 1.33mm and 4.21mm when testing intra- and inter-fraction motion, respectively. The range of motion described in the cine-MRI was comparable to the motion of the building 4DMRI, being always above the estimation error. Overall, the model performance was dependent on DIR error, presenting reduced accuracy when inter-fraction baseline variations occurred. Results suggest the potential of the propos