GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs

📅 2025-02-17
📈 Citations: 0
Influential: 0
📄 PDF

career value

211K/year
🤖 AI Summary
To address the challenge of topological recovery in tubular structure extraction (e.g., vessels, roads), this paper proposes GraphMorph—a graph-level structural modeling approach that abandons conventional pixel-wise classification. Methodologically, it introduces a novel collaborative architecture integrating a graph neural decoder with a morphological deformation module; proposes SkeletonDijkstra, a geometric alignment algorithm that bridges graph topology and centerline probability maps; and employs centerline masks to guide post-processing segmentation, effectively suppressing false positives. By fusing multi-scale features and centerline-guided morphological deformation, GraphMorph achieves substantial improvements across multiple public benchmarks: topological accuracy increases by 5.2–9.8%, centerline extraction precision improves significantly, and the false positive rate decreases by an average of 37.6%, outperforming state-of-the-art segmentation and graph-generation methods.

Technology Category

Application Category

📝 Abstract
Accurately restoring topology is both challenging and crucial in tubular structure extraction tasks, such as blood vessel segmentation and road network extraction. Diverging from traditional approaches based on pixel-level classification, our proposed method, named GraphMorph, focuses on branch-level features of tubular structures to achieve more topologically accurate predictions. GraphMorph comprises two main components: a Graph Decoder and a Morph Module. Utilizing multi-scale features extracted from an image patch by the segmentation network, the Graph Decoder facilitates the learning of branch-level features and generates a graph that accurately represents the tubular structure in this patch. The Morph Module processes two primary inputs: the graph and the centerline probability map, provided by the Graph Decoder and the segmentation network, respectively. Employing a novel SkeletonDijkstra algorithm, the Morph Module produces a centerline mask that aligns with the predicted graph. Furthermore, we observe that employing centerline masks predicted by GraphMorph significantly reduces false positives in the segmentation task, which is achieved by a simple yet effective post-processing strategy. The efficacy of our method in the centerline extraction and segmentation tasks has been substantiated through experimental evaluations across various datasets. Source code will be released soon.
Problem

Research questions and friction points this paper is trying to address.

Accurate tubular structure topology restoration.
Branch-level feature extraction for predictions.
Reduction of segmentation false positives.
Innovation

Methods, ideas, or system contributions that make the work stand out.

Utilizes Graph Decoder for branch-level features
Employs Morph Module with SkeletonDijkstra algorithm
Reduces false positives via centerline masks
🔎 Similar Papers
No similar papers found.
Z
Zhao Zhang
Center for Data Science, Peking University; Pazhou Laboratory (Huangpu)
Z
Ziwei Zhao
Yizhun Medical AI Co., Ltd
D
Dong Wang
Yizhun Medical AI Co., Ltd
L
Liwei Wang
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University; Center for Machine Learning Research, Peking University