English

A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans

Image and Video Processing 2022-09-15 v4 Computer Vision and Pattern Recognition Machine Learning

Abstract

This is the technical report of the 9th place in the final result of PARSE2022 Challenge. We solve the segmentation problem of the pulmonary artery by using a two-stage method based on a 3D CNN network. The coarse model is used to locate the ROI, and the fine model is used to refine the segmentation result. In addition, in order to improve the segmentation performance, we adopt multi-view and multi-window level method, at the same time we employ a fine-tune strategy to mitigate the impact of inconsistent labeling.

Keywords

Cite

@article{arxiv.2209.03918,
  title  = {A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans},
  author = {ZeYu Liu and Yi Wang and Jing Wen and Yong Zhang and Hao Yin and Chao Guo and ZhongYu Wang},
  journal= {arXiv preprint arXiv:2209.03918},
  year   = {2022}
}
R2 v1 2026-06-28T00:58:21.900Z