Other Open Access
Adrian Dalca; Yipeng Hu; Tom Vercauteren; Mattias Heinrich; Lasse Hansen; Marc Modat; Bob de Vos; Yiming Xiao; Hassan Rivaz; Matthieu Chabanas; Ingerid Reinertsen; Bennett Landman; Jorge Cardoso; Bram van Ginneken; Alessa Hering; Keelin Murphy
This is the challenge design document for "Learn2Reg - The Challenge", accepted for MICCAI 2020.
Medical image registration plays a very important role in improving clinical workflows, computer-assisted interventions and diagnosis as well as for research studies involving e.g. morphological analysis. Besides ongoing research into new concepts for optimisation, similarity metrics and deformation models, deep learning for medical registration is currently starting to show promising advances that could improve the robustness, computation speed and accuracy of conventional algorithms to enable better practical translation. Nevertheless, there exists no commonly used benchmark dataset to compare state-of-the-art learning based registration among another and with their conventional (not trained) counterparts. With few exceptions (CuRIOUS at MICCAI 2018/2019 and the Continuous Registration Challenge at WBIR 2018) there has also been no comprehensive registration challenge covering different anatomical structures and evaluation metrics. We also believe that the entry barrier for new teams to contribute to this emerging field are higher than e.g. for segmentation, where standardised datasets (e.g. Medical Decathlon, BraTS) are easily available. In contrast, many registration tasks, require resampling from different voxel spacings, affine pre-registration and can lead to ambiguous and error-prone evaluation of whole deformation fields.
We propose a simplified challenge design that removes many of the common pitfalls for learning and applying transformations. We will provide pre-preprocessed data (resample, crop, pre-align, etc.) that can be directly employed by most conventional and learning frameworks. Only displacement fields in voxel dimensions in a standard orientation will have to be provided by participants and python code to test their application to training data will be provided as open-source along with all evaluation metrics. Our challenge will consist of 4 clinically relevant sub-tasks (datasets) that are complementary in nature. They can either be individually or comprehensively addressed by participants and cover both intra- and inter-patient alignment, CT, ultrasound and MRI modalities, neuro-, thorax and abdominal anatomies and the four of the imminent challenges of medical image registration:
An important aspect of challenges are comprehensive and fair evaluation criteria. Since, medical image registration is not limited to accurately and robustly transferring anatomical annotations but should also provide plausible deformations, we will incorporate a measure of transformation complexity (the standard deviation of local volume change defined by the Jacobian determinant of the deformation). To encourage the submission of learning based approaches that reduce the computational burden of image registration, the run-time computation time will also be included into the ranking by awarding extra points. Due to differences in hardware, the computation time (including all steps of the employed pipeline) will be measured by running algorithms on the grand-challenge.org evaluation platform (where the whole challenge will be hosted) with the potential of using Nvidia GPU backends (this will not be a strict requirement for participants).