PointScatter: Point Set Representation for Tubular Structure Extraction
This work addresses tubular structure extraction for medical or biological imaging, offering a flexible alternative to mask-based methods, though it appears incremental as it builds on existing point set ideas.
The paper tackles tubular structure extraction by proposing PointScatter, a point set representation method that splits images into scatter regions and predicts points in parallel, achieving effectiveness in segmentation and centerline extraction across four public datasets.
This paper explores the point set representation for tubular structure extraction tasks. Compared with the traditional mask representation, the point set representation enjoys its flexibility and representation ability, which would not be restricted by the fixed grid as the mask. Inspired by this, we propose PointScatter, an alternative to the segmentation models for the tubular structure extraction task. PointScatter splits the image into scatter regions and parallelly predicts points for each scatter region. We further propose the greedy-based region-wise bipartite matching algorithm to train the network end-to-end and efficiently. We benchmark the PointScatter on four public tubular datasets, and the extensive experiments on tubular structure segmentation and centerline extraction task demonstrate the effectiveness of our approach. Code is available at https://github.com/zhangzhao2022/pointscatter.