Shape-aware Sampling Matters in the Modeling of Multi-Class Tubular Structures
Journal:
arXiv
Published Date:
Jun 14, 2025
Abstract
Accurate multi-class tubular modeling is critical for precise lesion
localization and optimal treatment planning. Deep learning methods enable
automated shape modeling by prioritizing volumetric overlap accuracy. However,
the inherent complexity of fine-grained semantic tubular shapes is not fully
emphasized by overlap accuracy, resulting in reduced topological preservation.
To address this, we propose the Shapeaware Sampling (SAS), which optimizes
patchsize allocation for online sampling and extracts a topology-preserved
skeletal representation for the objective function. Fractal Dimension-based
Patchsize (FDPS) is first introduced to quantify semantic tubular shape
complexity through axis-specific fractal dimension analysis. Axes with higher
fractal complexity are then sampled with smaller patchsizes to capture
fine-grained features and resolve structural intricacies. In addition, Minimum
Path-Cost Skeletonization (MPC-Skel) is employed to sample topologically
consistent skeletal representations of semantic tubular shapes for
skeleton-weighted objective functions. MPC-Skel reduces artifacts from
conventional skeletonization methods and directs the focus to critical
topological regions, enhancing tubular topology preservation. SAS is
computationally efficient and easily integrable into optimization pipelines.
Evaluation on two semantic tubular datasets showed consistent improvements in
both volumetric overlap and topological integrity metrics.
