Artificial intelligence, especially deep learning technology, achieves remarkable success in healthcare. In such a way, deep learning technology is effectively applied for radiotherapy applications to enhance the radiotherapy patient workflow. Image fusion, delineation of Clinical Target Volume (CTV), Organ-At-Risk (OAR), Automatic Planning (AP), dose distribution prediction, image phenotyping, radiomic signature discovery, image dose quantification, dose-response modeling, radiation adaption, and image generation are the deep learning enabled clinical radiotherapy works of radiation oncology.

In radiotherapy, deep learning-based medical imaging conducts a high-throughput and quantitative analysis of extensive features in medical images such as computed tomography, magnetic resonance imaging, fluoroscopic X-ray, ultrasound, dermoscopic images, positron emission tomography, mammography, 3D camera images, and motion capture camera images. Radiotherapy planning and treatment setup, image segmentation, computer-aided detection and diagnosis, image registration, treatment planning, motion management, patient setup during treatment, and medical data extraction and outcome prediction in radiotherapy are the different deep-learning-based implementation areas in radiotherapy.

Various surveys and reviews on radiotherapy using deep learning have been published that describe deep learning methods, applications, challenges, comparison methods, evaluation metrics, and future scopes.