RibPull: Implicit Occupancy Fields and Medial Axis Extraction for CT Ribcage Scans

2025-09-01

AI Summary

Traditional voxel grids for CT rib modeling suffer from limited resolution, topological distortions, and poor robustness to sparse and noisy data. This paper proposes a neural implicit occupancy field for continuous 3D rib representation, integrating coordinate encoding with geometric priors to achieve high-fidelity, topology-preserving modeling from sparse CT scans. We innovatively introduce a differentiable Laplacian contraction algorithm—the first end-to-end differentiable method for extracting rib centerlines. Evaluated on the RibSeg dataset (20 CT scans), our approach significantly outperforms voxel-based baselines: occupancy prediction accuracy improves by +4.2% in Dice score, centerline localization error decreases by 31%, and the method enables arbitrary-resolution reconstruction and morphological analysis. The code will be publicly released.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Learning with Manifolds
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We present RibPull, a methodology that utilizes implicit occupancy fields to bridge computational geometry and medical imaging. Implicit 3D representations use continuous functions that handle sparse and noisy data more effectively than discrete methods. While voxel grids are standard for medical imaging, they suffer from resolution limitations, topological information loss, and inefficient handling of sparsity. Coordinate functions preserve complex geometrical information and represent a better solution for sparse data representation, while allowing for further morphological operations. Implicit scene representations enable neural networks to encode entire 3D scenes within their weights. The result is a continuous function that can implicitly compesate for sparse signals and infer further information about the 3D scene by passing any combination of 3D coordinates as input to the model. In this work, we use neural occupancy fields that predict whether a 3D point lies inside or outside an object to represent CT-scanned ribcages. We also apply a Laplacian-based contraction to extract the medial axis of the ribcage, thus demonstrating a geometrical operation that benefits greatly from continuous coordinate-based 3D scene representations versus voxel-based representations. We evaluate our methodology on 20 medical scans from the RibSeg dataset, which is itself an extension of the RibFrac dataset. We will release our code upon publication.

Problem

• Extracting medial axis from CT ribcage scans
• Handling sparse noisy data in medical imaging
• Overcoming resolution limitations of voxel grids

Innovation

• Implicit occupancy fields for 3D representation
• Neural networks encoding scenes in weights
• Laplacian-based medial axis extraction