Aims and Scope

Submissions are invited in all areas of biomedical image registration. Topics of interest include, but are not limited to:
 

Novel registration methodology: Learning-based methods, combinations of learning and non-learning techniques and conventional approaches. 2D/3D/4D, spatiotemporal/dynamic, pairwise / groupwise, slice-to-volume, projective, single/multi-modal, intra/inter-subject, model-based, patch-based, multi-channel, tracking. 

Machine learning and deep learning techniques for registration: unsupervised / supervised / reinforcement learning, convolutional / recurrent / transformer networks, cost correlation, neural networks for feature extraction and matching, correspondence weighting and prediction, attention modeling, deformation learning, deep encoder-decoder networks

Optimisation and mathematical aspects of image registration: continuous/discrete optimization, real-time, similarity measures, diffeomorphisms, LDDMM, stationary velocity, inverse consistency, multi-scale, graphical models

Biomedical applications of registration: computer-assisted interventions, image-guided therapy, treatment planning/delivery, diagnosis/prognosis, atlas-based segmentation, label fusion, histopathology correlation, serial studies, pathology detection and localization, morphometry, biomechanics, image retrieval/restoration/fusion, imaging biomarkers for precision medicine, radiomics & radiogenomics, early proofs of concept

Validation of registration: quantitative and qualitative methods, benchmarking, comparison studies, phantom studies, correlation to outcome, validation protocols and performance metrics, uncertainty estimation

Motion modelling, simulations and motion reconstruction