Review article on automated tumor segmentation in radiotherapy

Our review article “Automated Tumor Segmentation in Radiotherapy“, by Ricky Savjani et al. has been published in Seminars in Radiation Oncology. In this work, we present advances in gross tumor volume automatic segmentation made in multiple key sites: brain, head and neck, thorax, abdomen, and pelvis.

Automatic tumor segmentation can decrease clinical demand, provide consistency across clinicians and institutions for radiation treatment planning. Additionally, automatic segmentation can enable imaging analyses such as radiomics to construct and deploy large studies with thousands of patients.

(A) In this review, we highlight major advances in tumor autosegmentation for 5 major clinical sites: brain, head and neck, thorax, abdomen, and pelvis. (B) Successful autosegmentation models rely on several steps including: data collection and curation, pre-processing and data ingestion, splitting datasets into train/validate/test sets, hyper-parameter optimization and tuning, architecting networks, post-processing and visualization, and aggregating outputs from ensembles of networks.