MorVess: Morphology-Aware Pulmonary Vessel Segmentation Network

2026-06-23

AI Summary

This work addresses the challenges of losing fine vascular branches and preserving topological integrity in pulmonary vessel segmentation by proposing the MorVess framework. MorVess jointly predicts vessel masks, distance maps, and thickness maps, incorporating differentiable geometric priors to explicitly constrain vascular morphology. The method innovatively embeds these geometric priors into a pretrained vision model and introduces a lightweight 2.5D adapter to bridge 3D contextual information with 2D SAM representations. A global–local feature fusion module further enhances reconstruction fidelity. Evaluated on two pulmonary CT datasets, the approach significantly improves Dice, clDice, and HD95 metrics, demonstrating superior recovery of small vessels and enhanced topological connectivity.

Abstract

Accurate pulmonary vessel segmentation remains challenging due to the sparse, tortuous, and multi-scale nature of vascular structures, where small branches are easily lost and topology integrity is difficult to preserve under voxel-wise supervision. Existing deep segmentation models primarily optimize binary masks, lacking explicit geometric constraints, thus struggling to recover continuous tubular morphology and fine vascular connectivity. In this study, we introduce MorVess, a morphology-aware segmentation framework that integrates differentiable geometric priors with large-scale foundation model adaptation to achieve fine-grained vascular parsing. MorVess jointly predicts vessel masks, distance maps, and thickness maps, providing explicit supervision for vascular boundaries, centerline consistency, and smooth diameter transitions. A lightweight 2.5D adapter bridges 3D spatial context and 2D SAM representations, while a global-local fusion block aggregates multi-level semantics and geometric cues for high-fidelity topology reconstruction. Across two challenging pulmonary CT benchmarks, MorVess delivers superior Dice, clDice, and HD95 scores, substantially improving small-vessel recovery and global connectivity. These results demonstrate that embedding geometric intelligence into pretrained vision models offers a principled and scalable pathway toward precise vessel analysis and clinically reliable structural quantification. Our source code is available at https://github.com/MaoFuyou/MorVess.

Problem

• pulmonary vessel segmentation
• tubular morphology
• topology integrity
• geometric constraints
• small-vessel recovery

Innovation

• morphology-aware segmentation
• geometric priors
• foundation model adaptation
• vascular topology
• distance and thickness maps