Abstract: The present invention relates to image fusion of lower resolution images (32) and higher resolution reference images (50) of an object (30). Specific image scanning geometries used for acquiring the lower resolution images (32) are determined based on a machine learning algorithm that uses at least one feature in at least one region of interest in the respective lower resolution images (32) as input. Image scanning geometry matching oblique higher resolution images (54) are generated based on the higher resolution reference images (50) and the determined specific image scanning geometries used for acquiring the respective lower resolution images (32). The oblique higher resolution images (54) are registered with the lower resolution images (32) in order to generate registered higher resolution images. Current feature information is extracted from the lower resolution images and mapped on corresponding feature information in the registered higher resolution images in order to generate fusion images.

Abstract: A radiation therapy delivery device console (50) controls a radiation therapy delivery device (36) and an imaging device (40, 42), and further performs adaptive radiotherapy (ART) recommendation as follows. The imaging device is controlled to acquire a current image (44) of a patient. At least one perturbation of the current image is determined compared with a radiation therapy planning image (1) from which a radiation therapy plan (22) for the patient has been generated. An ART recommendation score is computed, indicating whether ART should be performed, based on the determined at least one perturbation. A recommendation is displayed as to whether ART should be performed based on the computed ART recommendation score, or an alarm is displayed conditional upon the computed ART recommendation score satisfying an ART recommendation criterion.