Automatic deep learning based quality assessment of transperineal ultrasound guided prostate radiotherapy

Ultrasound (US) is one of the imaging modalities that can be used for image‐guided radiotherapy (RT) workflows of prostate cancer patients. It allows real‐time volumetric tracking during the course of the RT treatment, which could potentially improve the precision of radiation dose delivery. However, intra‐fraction motion management using US image guidance is not yet widespread. This can be partially attributed to the need for image interpretation by a trained operator during or after US image acquisition.