.png){kind=icon}
.png){kind=icon}
Return
Interpretable wavelet transformer-enhanced framework for unsupervised deformable image registration
.png){kind=icon}
PRE
AI
DOI：10.1002/mp.70056.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deformable image registration (DIR) underpins quantitative analysis in clinical image-based diagnosis and intervention. Nevertheless, prevailing techniques falter due to their inadequate capacity to encapsulate high-frequency multi-scale data. Additionally, they lack explicit constraints on the deformation learning process, leading to poor interpretability.
Keywords:
high-frequency multi-scale representation
information-preserving encoding
interpretable registration
wavelet-based Transformer