High Accuracy Pulmonary Vessel Segmentation for Contrast and Non-contrast CT Images and Its Clinical Evaluation

2025-03-21

AI Summary

Clinical pulmonary vascular segmentation on non-contrast-enhanced CT (NCCT) suffers from low accuracy and poor robustness. To address this, we propose a unified 3D deep learning framework adaptable to both contrast-enhanced CT pulmonary angiography (CTPA) and NCCT. Our method introduces the novel Vessel Lumen Structure Optimization Module (VLSOM), integrating centerline-guided weighting with a customized Cl-Dice loss; designs a cross-modal ground-truth transfer strategy to generalize knowledge from CTPA annotations to NCCT models; and employs multi-center, multi-vendor data for joint training. Evaluated on 427 high-quality annotated cases, our method achieves Cl-Recall of 0.879 (CTPA) and 0.928 (NCCT), and Cl-Dice of 0.909 (CTPA) and 0.936 (NCCT), significantly outperforming state-of-the-art approaches. Clinical validation confirms strong robustness across diverse pulmonary diseases. This work establishes a new paradigm for precise pulmonary vascular assessment without contrast enhancement.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• 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

Accurate segmentation of pulmonary vessels plays a very critical role in diagnosing and assessing various lung diseases. In clinical practice, diagnosis is typically carried out using CTPA images. However, there is a lack of high-precision pulmonary vessel segmentation algorithms for CTPA, and pulmonary vessel segmentation for NCCT poses an even greater challenge. In this study, we propose a 3D image segmentation algorithm for automated pulmonary vessel segmentation from both contrast and non-contrast CT images. In the network, we designed a Vessel Lumen Structure Optimization Module (VLSOM), which extracts the centerline of vessels and adjusts the weights based on the positional information and adds a Cl-Dice-Loss to supervise the stability of the vessels structure. In addition, we designed a method for generating vessel GT from CTPA to NCCT for training models that support both CTPA and NCCT. In this work, we used 427 sets of high-precision annotated CT data from multiple vendors and countries. Finally, our experimental model achieved Cl-Recall, Cl-DICE and Recall values of 0.879, 0.909, 0.934 (CTPA) and 0.928, 0.936, 0.955 (NCCT) respectively. This shows that our model has achieved good performance in both accuracy and completeness of pulmonary vessel segmentation. In clinical visual evaluation, our model also had good segmentation performance on various disease types and can assist doctors in medical diagnosis, verifying the great potential of this method in clinical application.

Problem

• Lack of high-precision pulmonary vessel segmentation algorithms for CTPA.
• Challenges in pulmonary vessel segmentation for non-contrast CT (NCCT).
• Need for accurate segmentation to diagnose and assess lung diseases.

Innovation

• 3D segmentation algorithm for CT images
• Vessel Lumen Structure Optimization Module
• Generates vessel GT for CTPA and NCCT