NeuroVascU-Net: A Unified Multi-Scale and Cross-Domain Adaptive Feature Fusion U-Net for Precise 3D Segmentation of Brain Vessels in Contrast-Enhanced T1 MRI

2025-11-23

AI Summary

To address low accuracy, high computational cost, and poor generalizability in 3D cerebral vasculature segmentation from clinical routine T1-weighted contrast-enhanced (T1CE) MRI, this paper proposes a lightweight, enhanced dilated U-Net architecture. Methodologically, it innovatively incorporates a Multi-Scale Context and Cross-Domain Adaptive Feature Fusion module (MSC²F and CDA²F), which jointly enhances fine vessel delineation and inter-domain feature robustness without significant computational overhead. To our knowledge, this is the first network specifically designed for brain vascular segmentation on standard clinical T1CE MRI. Evaluated on 137 patient scans, it achieves a Dice score of 0.8609 and precision of 0.8841 using only 12.4 million parameters—outperforming comparable transformer-based models in both efficiency and segmentation performance. The proposed method demonstrates strong clinical deployment potential due to its lightweight design, high accuracy, and domain adaptability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Precise 3D segmentation of cerebral vasculature from T1-weighted contrast-enhanced (T1CE) MRI is crucial for safe neurosurgical planning. Manual delineation is time-consuming and prone to inter-observer variability, while current automated methods often trade accuracy for computational cost, limiting clinical use. We present NeuroVascU-Net, the first deep learning architecture specifically designed to segment cerebrovascular structures directly from clinically standard T1CE MRI in neuro-oncology patients, addressing a gap in prior work dominated by TOF-MRA-based approaches. NeuroVascU-Net builds on a dilated U-Net and integrates two specialized modules: a Multi-Scale Contextual Feature Fusion ($MSC^2F$) module at the bottleneck and a Cross-Domain Adaptive Feature Fusion ($CDA^2F$) module at deeper hierarchical layers. $MSC^2F$ captures both local and global information via multi-scale dilated convolutions, while $CDA^2F$ dynamically integrates domain-specific features, enhancing representation while keeping computation low. The model was trained and validated on a curated dataset of T1CE scans from 137 brain tumor biopsy patients, annotated by a board-certified functional neurosurgeon. NeuroVascU-Net achieved a Dice score of 0.8609 and precision of 0.8841, accurately segmenting both major and fine vascular structures. Notably, it requires only 12.4M parameters, significantly fewer than transformer-based models such as Swin U-NetR. This balance of accuracy and efficiency positions NeuroVascU-Net as a practical solution for computer-assisted neurosurgical planning.

Problem

• Automated 3D brain vessel segmentation from T1CE MRI for neurosurgery
• Addressing accuracy-computation tradeoff in current vessel segmentation methods
• Bridging domain gap between TOF-MRA and clinical T1CE MRI approaches

Innovation

• Uses dilated U-Net with multi-scale feature fusion
• Integrates cross-domain adaptive feature fusion module
• Achieves high accuracy with only 12.4M parameters