A Self-training Framework for Semi-supervised Pulmonary Vessel Segmentation and Its Application in COPD

2025-07-25

AI Summary

Accurate segmentation of small pulmonary arteries in CT images of COPD patients remains challenging due to their low contrast and fine anatomical scale. Method: We propose a teacher-student semi-supervised self-training framework that integrates interactive high-quality annotation with confidence-driven pseudo-label filtering, enabling joint optimization using only 25 annotated and 100 unlabeled non-contrast CT scans. Contribution/Results: Our method achieves a Dice score of 90.3% for small-vessel segmentation across 125 cases—improving upon the fully supervised baseline by 2.3%. Notably, this is the first study to correlate semi-supervised pulmonary vascular quantification metrics with GOLD staging, revealing statistically significant differences in peripheral vessel density and caliber across severity grades. The approach offers a generalizable, low-annotation-dependency pipeline for developing imaging biomarkers in COPD.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Background: It is fundamental for accurate segmentation and quantification of the pulmonary vessel, particularly smaller vessels, from computed tomography (CT) images in chronic obstructive pulmonary disease (COPD) patients. Objective: The aim of this study was to segment the pulmonary vasculature using a semi-supervised method. Methods: In this study, a self-training framework is proposed by leveraging a teacher-student model for the segmentation of pulmonary vessels. First, the high-quality annotations are acquired in the in-house data by an interactive way. Then, the model is trained in the semi-supervised way. A fully supervised model is trained on a small set of labeled CT images, yielding the teacher model. Following this, the teacher model is used to generate pseudo-labels for the unlabeled CT images, from which reliable ones are selected based on a certain strategy. The training of the student model involves these reliable pseudo-labels. This training process is iteratively repeated until an optimal performance is achieved. Results: Extensive experiments are performed on non-enhanced CT scans of 125 COPD patients. Quantitative and qualitative analyses demonstrate that the proposed method, Semi2, significantly improves the precision of vessel segmentation by 2.3%, achieving a precision of 90.3%. Further, quantitative analysis is conducted in the pulmonary vessel of COPD, providing insights into the differences in the pulmonary vessel across different severity of the disease. Conclusion: The proposed method can not only improve the performance of pulmonary vascular segmentation, but can also be applied in COPD analysis. The code will be made available at https://github.com/wuyanan513/semi-supervised-learning-for-vessel-segmentation.

Problem

• Segment pulmonary vessels in COPD patients using CT images
• Improve vessel segmentation precision with semi-supervised learning
• Analyze pulmonary vessel differences across COPD severity levels

Innovation

• Self-training framework with teacher-student model
• Semi-supervised learning with pseudo-labeling strategy
• Interactive high-quality annotation for initial training