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

TL;DR

This paper presents a multi-view, multi-stage, and multi-window 3D CNN framework for pulmonary artery segmentation from CT scans, achieving 9th place in the PARSE2022 Challenge.

Contribution

It introduces a novel multi-view, multi-window, and two-stage CNN approach with fine-tuning to enhance pulmonary artery segmentation accuracy.

Findings

Achieved 9th place in PARSE2022 Challenge

Improved segmentation performance with multi-view and multi-window methods

Effective fine-tuning strategy to reduce label inconsistency impact

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.