Robust automatic brain vessel segmentation in 3D CTA scans using dynamic 4D-CTA data

TL;DR

This paper introduces a dynamic 4D-CTA based method for automatic brain vessel segmentation, leveraging multiple phases to improve accuracy and robustness of deep learning models in vascular imaging.

Contribution

The study presents a novel dynamic 4D-CTA dataset and a segmentation approach that significantly enhances accuracy and robustness over existing methods.

Findings

Achieved high segmentation accuracy with mDC of 0.846 for arteries and 0.957 for veins.

Demonstrated robustness across contrast phases with low adHD and high tSens metrics.

Enlarged dataset via multi-phase training improves model performance.

Abstract

In this study, we develop a novel methodology for annotating the brain vasculature using dynamic 4D-CTA head scans. By using multiple time points from dynamic CTA acquisitions, we subtract bone and soft tissue to enhance the visualization of arteries and veins, reducing the effort required to obtain manual annotations of brain vessels. We then train deep learning models on our ground truth annotations by using the same segmentation for multiple phases from the dynamic 4D-CTA collection, effectively enlarging our dataset by 4 to 5 times and inducing robustness to contrast phases. In total, our dataset comprises 110 training images from 25 patients and 165 test images from 14 patients. In comparison with two similarly-sized datasets for CTA-based brain vessel segmentation, a nnUNet model trained on our dataset can achieve significantly better segmentations across all vascular regions, with an average mDC of 0.846 for arteries and 0.957 for veins in the TopBrain dataset. Furthermore, metrics such as average directed Hausdorff distance (adHD) and topology sensitivity (tSens) reflected similar trends: using our dataset resulted in low error margins (adHD of 0.304 mm for arteries and 0.078 for veins) and high sensitivity (tSens of 0.877 for arteries and 0.974 for veins), indicating excellent accuracy in capturing vessel morphology. Our code and model weights are available online at https://github.com/alceballosa/robust-vessel-segmentation