A topology-constrained 8-bit quantized nnUNet with connected-component, adjacency, and hole penalties reduces topological errors in tooth segmentation compared to standard quantization.
The topological metrics were evaluated on both instance -level and whole -dentition levels to capture local and global anatomical consistency
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation
A topology-constrained 8-bit quantized nnUNet with connected-component, adjacency, and hole penalties reduces topological errors in tooth segmentation compared to standard quantization.