Deep Learning for Ultrasound Guided Radiotherapy

This repository contains experimental research code for the task of using Deep Learning methods to track motion in ultrasound image sequences. At the moment, the repository only contains initial image pre-processing work on the CAMUS database (https://www.creatis.insa-lyon.fr/Challenge/camus/). It may be updated in the future to include an experimental GAN architecture design for image registration, estimating deformation vector fields (DVFs) between consecutive frames, to shift the landmarks from thestart to end frame.