OncoReg-Challenge: Evaluation for the integration of anatomical expert knowledge from retrospective data in oncological computed tomographic image registration with artificial intelligence

Modern cancer research is generating ever more extensive data sets (big data). The data originates from molecular and biochemical analyses, modern imaging procedures, clinical studies or depicts the course of a patient's disease. These data treasures need to be exploited in the future. New computer-aided approaches to data use, state-of-the-art methods of artificial intelligence, machine learning and statistics are of great importance for the improved analysis and extraction of research-relevant information. With this funding guideline as part of the National Decade Against Cancer, the BMBF intends to provide research groups from the field of data analysis with low-threshold access to high-quality data from translational, biomedical cancer research and routine oncological care. At the same time, researchers from the fields of data acquisition and data analysis work closely together to address clinically relevant oncological questions. In addition, the culture of data sharing for research purposes is to be promoted. The OncoReg project aims to prepare and implement a data challenge for the registration of oncological image data of the lung. The aim is to promote data sharing and the curation of existing data for automatic analysis. The quality-checked data from routine oncological care will be made available to scientists in the field of data analysis. The planned challenge aims to develop 3D registration procedures for oncological image data. The results of the project will make a significant contribution to methodological development in the field of image registration, which is important for numerous healthcare applications in the prevention, diagnosis and treatment of oncological diseases.