Abstract: Systems and methods for providing a novel framework for unsupervised coregistration using convolutional neural network (CNN) models. The CNN models may perform image coregistration using fully unsupervised learning. Advantageously, the CNN models may also explicitly stabilizes images or transfers contour masks across images. Global alignment may be learned via affine deformations in addition to a dense deformation field, and an unsupervised loss function may be maintained. The CNN models may apply an additional spatial transformation layer at the end of a transformation step, which provides the ability to fine-tune previously predicted transformation so that the CNN models may correct previous transformation errors.

Abstract: Described is an assistance device for providing imaging support to an operating surgeon during a surgical procedure involving at least one medical instrument. The assistance device comprises a camera, a display unit, a manipulator coupled to the camera, a manipulator controller and an image processing unit. The image processing unit includes an instrument detection module for detecting at least one target structure that represents the instrument being used in the frame in question by identifying a predetermined distinguishing feature, and for extracting position information that indicates the position of the target structure in the frame. The instrument detection module identifies an image segment as the predetermined distinguishing feature, said image segment being characterized by a color saturation that is equal to or less than a predefined color saturation and by a contour line that delimits the image segment and has at least one rectilinear section.