SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI

arXiv:2312.13534v2 Announce Type: replace-cross
Abstract: Rigid motion tracking is paramount in many medical imaging applications where movements need to be detected, corrected, or accounted for. Modern strategies rely on convolutional neural networks (CNN) and pose this problem as rigid registration. Yet, CNNs do not exploit natural symmetries in this task, as they are equivariant to translations (their outputs shift with their inputs) but not to rotations. Here we propose EquiTrack, the first method that uses recent steerable SE(3)-equivariant CNNs (E-CNN) …

arxiv brain cs.cv eess.iv mri noise tracking type