Fracture interactive geodesic active contours for bone segmentation

2025-09-18

AI Summary

Traditional geodesic active contour (GAC) models suffer from indiscriminate feature extraction, susceptibility to edge occlusion/leakage, and interference from fractures in skeletal segmentation. To address these limitations, this paper proposes a fracture-aware geodesic active contour algorithm. Methodologically: (1) we design an orthopedic prior-driven edge detection function that jointly incorporates image intensity and gradient information; (2) we embed fracture cues into a distance-field-guided adaptive step-size mechanism, enabling responsive contour evolution tailored to fracture regions. Experiments on pelvic and ankle CT datasets demonstrate that the proposed method significantly improves edge localization accuracy and segmentation stability in fracture-affected regions. Quantitative evaluation shows superior performance over baseline GAC models in terms of accuracy, robustness, and inter-scan consistency. Moreover, the framework exhibits promising generalizability to other skeletal structures.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

For bone segmentation, the classical geodesic active contour model is usually limited by its indiscriminate feature extraction, and then struggles to handle the phenomena of edge obstruction, edge leakage and bone fracture. Thus, we propose a fracture interactive geodesic active contour algorithm tailored for bone segmentation, which can better capture bone features and perform robustly to the presence of bone fractures and soft tissues. Inspired by orthopedic knowledge, we construct a novel edge-detector function that combines the intensity and gradient norm, which guides the contour towards bone edges without being obstructed by other soft tissues and therefore reduces mis-segmentation. Furthermore, distance information, where fracture prompts can be embedded, is introduced into the contour evolution as an adaptive step size to stabilize the evolution and help the contour stop at bone edges and fractures. This embedding provides a way to interact with bone fractures and improves the accuracy in the fracture regions. Experiments in pelvic and ankle segmentation demonstrate the effectiveness on addressing the aforementioned problems and show an accurate, stable and consistent performance, indicating a broader application in other bone anatomies. Our algorithm also provides insights into combining the domain knowledge and deep neural networks.

Problem

• Addresses bone segmentation challenges with edge obstruction and leakage
• Proposes geodesic contour method robust to fractures and soft tissues
• Improves fracture region accuracy through interactive distance information embedding

Innovation

• Novel edge-detector combining intensity and gradient
• Distance information with embedded fracture prompts
• Adaptive step size stabilizing contour evolution