GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs

TL;DR

GraphMorph introduces a novel approach for tubular structure extraction that leverages branch-level graph predictions and a Morph Module to improve topological accuracy and reduce false positives in segmentation tasks.

Contribution

The paper presents GraphMorph, a new method combining a Graph Decoder and Morph Module with a SkeletonDijkstra algorithm for topologically accurate tubular structure extraction.

Findings

Improves topological accuracy in tubular structure segmentation.

Reduces false positives through centerline mask post-processing.

Validated across multiple datasets with strong results.

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.