Abstract: Systems and methods for acquiring an ultrasound volume comprising acquiring sequential bi-plane ultrasound images in a first direction using an ultrasound probe of an ultrasound system, the sequential bi-plane ultrasound images comprising first ultrasound image planes or first ultrasound image volumes along a first plane and second ultrasound image planes or second ultrasound image volumes along a second plane, the first plane corresponding to the first direction and the second plane corresponding to a second direction, calculating one or more first displacements in the first direction of the sequential bi-plane ultrasound images during the acquisition, positioning the second ultrasound image planes or the second ultrasound image volumes sequentially, wherein the second ultrasound image planes or the second ultrasound image volumes are positioned according to the one or more first displacements, and generating the ultrasound volume by combining the second ultrasound image planes or the second ultrasound image

Abstract: A system for image inpainting of in-vivo images includes at least one processor and at least one memory storing instructions. The instructions, when executed by the processor(s), cause the system to access an in-vivo image of a portion of a gastrointestinal tract where the in-vivo image includes image regions to be reconstructed, process the in-vivo image by a trained image inpainting deep learning model to provide a reconstructed in-vivo image, and provide the reconstructed in-vivo image to a device for viewing by a medical professional.

Abstract: A method for image classification includes accessing a plurality of images of at least a portion of a gastrointestinal tract (GIT) captured by a capsule endoscopy device and for each image of the plurality of images: providing a classification score for each segment of a plurality of consecutive segments of the GIT by a deep learning neural network, and providing a classification probability for each segment of the plurality of consecutive segments of the GIT based on the classification scores by a classical machine learning classifier. The method further includes determining a classification for each image to one segment of the plurality of consecutive segments of the GIT based on processing a signal corresponding to the classification probabilities of the plurality of images.