Titlebook: Biomedical Image Registration; 10th International W Alessa Hering,Julia Schnabel,Daniel Rueckert Conference proceedings 2022 The Editor(s)

Noisome

Distinct Structural Patterns of?the?Human Brain: A Caveat for?Registrationlinear registration to reduce the inter-individual variability. This assumption is challenged here. Regional anatomical and connection patterns cluster into statistically distinct types. An advanced analysis proposed here leads to a deeper understanding of the governing principles of cortical variab

Junction

overshadow

Voxelmorph++udes. The recent Learn2Reg medical registration benchmark has demonstrated that single-scale U-Net architectures, such as VoxelMorph that directly employ a spatial transformer loss, often do not generalise well beyond the cranial vault and fall short of state-of-the-art performance for abdominal or

Allege

Unsupervised Learning of?Diffeomorphic Image Registration via?TransMorphoposed network learns to produce and integrate time-dependent velocity fields in an LDDMM setting. The proposed method guarantees a diffeomorphic transformation and allows the transformation to be easily and accurately inverted. We also showed that, without explicitly imposing a diffeomorphism, the

cumber

SuperWarp: Supervised Learning and Warping on U-Net for Invariant Subvoxel-Precise Registrationng segmentations, producing promising results across several benchmarks. In this paper, we argue that the relative failure of supervised registration approaches can in part be blamed on the use of regular U-Nets, which are jointly tasked with feature extraction, feature matching, and estimation of d