Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge

TL;DR

This work introduces PARSE, the first public MICCAI challenge to jointly segment main and branch pulmonary arteries in CTPA while explicitly balancing segmentation accuracy with inference efficiency. It provides a large-scale dataset, a multi-level evaluation framework (DSC/HD95) augmented with efficiency metrics (RT and GPU memory) and a weighted scheme that prioritizes branch PA, reflecting clinical needs. The paper analyzes the top-10 methods, detailing diverse strategies such as lightweight U-Net variants, ROI-focused preprocessing, skeleton or skeleton-inspired losses, coarse-to-fine localization, and selective postprocessing, and discusses how preprocessing, augmentation, and inference choices drive performance. Key findings show that branch PA remains more challenging than main PA, that accuracy and efficiency must be balanced, and that robust multi-level evaluation is essential for meaningful comparisons and future algorithm development in pulmonary vessel segmentation.

Abstract

Efficient automatic segmentation of multi-level (i.e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications. However, most existing methods concentrate only on main PA or branch PA segmentation separately and ignore segmentation efficiency. Besides, there is no public large-scale dataset focused on PA segmentation, which makes it highly challenging to compare the different methods. To benchmark multi-level PA segmentation algorithms, we organized the first \textbf{P}ulmonary \textbf{AR}tery \textbf{SE}gmentation (PARSE) challenge. On the one hand, we focus on both the main PA and the branch PA segmentation. On the other hand, for better clinical application, we assign the same score weight to segmentation efficiency (mainly running time and GPU memory consumption during inference) while ensuring PA segmentation accuracy. We present a summary of the top algorithms and offer some suggestions for efficient and accurate multi-level PA automatic segmentation. We provide the PARSE challenge as open-access for the community to benchmark future algorithm developments at \url{https://parse2022.grand-challenge.org/Parse2022/}.

Figures (10)

• Figure 1: Complex pulmonary artery topology structures: (a) the pulmonary arteries (blue); (b) the pulmonary arteries and pulmonary veins (red) are intertwined, while the pulmonary airways (grey) increasing the complex; (c) the pulmonary arteries, pulmonary veins and pulmonary airways with lungs (shade); (d) the pulmonary arteries are divided into two levels: main PA (outside the lungs) and branch PA (inside the lungs).
• Figure 2: Summary of PARSE challenge participants and submissions. There were 469 teams registering on the official grand-challenge webpage and 111 of them were approved before the end of the training phase. Finally, 49 teams submitted validation results and 28 teams submitted Docker containers with 25 qualified results.
• Figure 3: Framework pipeline for the Top 1 team. A lightweight model called Tiny Res-U-Net was designed.
• Figure 4: Framework overview of the T4 team. The model consists of a U-Net architecture to perform segmentation and a skeleton decoder used in the training stage to predict vessel skeletons.
• Figure 5: Dot- and boxplot visualization (the first row) and statistical significance maps (the second row) for the DSC metric of the top 20 teams. (a) and (d), (b) and (e), and (c) and (f) are the results for main PA, branch PA and weighted PA, respectively. In each sub-figure, the teams are arranged from left to right in accordance with the corresponding mean score. In the statistical significance maps, light red shading indicates that the DSC scores of the teams on the x-axis are significantly superior to the scores of the teams on the y-axis based on one-sided Wilcoxon signed rank test (p-value < 5%) and dark red shading indicates they are not significantly superior.