A new convolution layer uses persistent homology on feature maps to guide adaptive kernel offsets, improving topological consistency in medical image segmentation.
V oxelmorph: a learning framework for deformable medical image registration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Conformable Convolution for Topologically Aware Learning of Complex Anatomical Structures
A new convolution layer uses persistent homology on feature maps to guide adaptive kernel offsets, improving topological consistency in medical image segmentation.