Computer-aided target volume delineation for postoperative radiation therapy in brain glioma patients with the use of the hybrid artificial intelligence model

Abstract Radiotherapy is an important element of the multimodal treatment of gliomas. Proper target volume delineation after the surgery is essential. The goal of the research presented is to provide a computer application, which would automate the contouring process and reduce the burden required by radiation oncologists. Thanks to pre-made contours delivered by the application, radiation oncologists would only need to supervise, improve, and make necessary adjustments, rather than starting from scratch. The model of the application is described in the paper as well as its implementation and first experimental results. The application, called HAICS (hybrid artificial intelligence-based contouring system), uses machine learning tools combined with the authors’ contouring algorithm enabling user interaction. Additionally, syntactic pattern recognition methods can serve as a post-contouring enhancement.