Automated Labeling of Intracranial Arteries with Uncertainty Quantification Using Deep Learning

2025-09-22

AI Summary

Precise anatomical labeling of intracranial arteries is critical for cerebrovascular diagnosis and hemodynamic analysis, yet current manual or semi-automatic approaches are time-consuming and suffer from substantial inter-observer variability. To address this, we propose an automated anatomical labeling framework for 3D time-of-flight magnetic resonance angiography (TOF-MRA). Our method incorporates coordinate-guided test-time augmentation to mitigate interpolation artifacts, integrates uncertainty quantification to generate confidence maps reflecting both anatomical ambiguity and pathological variation, and ensembles three complementary architectures—nnUNet, ResUNet, and CS-Net—enhanced with attention mechanisms to improve vascular structure recognition robustness. Among them, nnUNet achieves the best performance (mean Dice score: 0.922; mean surface distance: 0.387 mm). Its automated labels yield velocity measurements in 4D Flow MRI statistically indistinguishable from expert annotations, significantly enhancing model interpretability, reliability, and clinical applicability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Accurate anatomical labeling of intracranial arteries is essential for cerebrovascular diagnosis and hemodynamic analysis but remains time-consuming and subject to interoperator variability. We present a deep learning-based framework for automated artery labeling from 3D Time-of-Flight Magnetic Resonance Angiography (3D ToF-MRA) segmentations (n=35), incorporating uncertainty quantification to enhance interpretability and reliability. We evaluated three convolutional neural network architectures: (1) a UNet with residual encoder blocks, reflecting commonly used baselines in vascular labeling; (2) CS-Net, an attention-augmented UNet incorporating channel and spatial attention mechanisms for enhanced curvilinear structure recognition; and (3) nnUNet, a self-configuring framework that automates preprocessing, training, and architectural adaptation based on dataset characteristics. Among these, nnUNet achieved the highest labeling performance (average Dice score: 0.922; average surface distance: 0.387 mm), with improved robustness in anatomically complex vessels. To assess predictive confidence, we implemented test-time augmentation (TTA) and introduced a novel coordinate-guided strategy to reduce interpolation errors during augmented inference. The resulting uncertainty maps reliably indicated regions of anatomical ambiguity, pathological variation, or manual labeling inconsistency. We further validated clinical utility by comparing flow velocities derived from automated and manual labels in co-registered 4D Flow MRI datasets, observing close agreement with no statistically significant differences. Our framework offers a scalable, accurate, and uncertainty-aware solution for automated cerebrovascular labeling, supporting downstream hemodynamic analysis and facilitating clinical integration.

Problem

• Automating intracranial artery labeling from 3D ToF-MRA to reduce manual effort
• Quantifying prediction uncertainty to enhance reliability of automated labeling
• Improving labeling accuracy for anatomically complex cerebrovascular structures

Innovation

• nnUNet framework for automated artery labeling
• Coordinate-guided test-time augmentation for uncertainty
• Uncertainty maps indicating anatomical ambiguity regions