Continuous benchmarking in medical image registration-review of the current state of the Learn2Reg challenge

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks, in part because of the lack of availability of such diverse data. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration benchmark for comprehensive characterisation of deformable registration algorithms. We established an easily accessible framework for training and validation of 3D registration methods, which so far enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. In this abstract for the MIDL community we want to 1) give a shortest (graphical) overview of the Learn2Reg Challenge, 2) present key results and outcomes of past editions and 3) outline limitations and resulting ongoing work.