Purpose: Aortic dissections are life-threatening cardiovascular conditions requiring accurate segmentation of true lumen (TL), false lumen (FL), and false lumen thrombosis (FLT) from CTA images for effective management. Manual segmentation is time-consuming and variable, necessitating automated solutions. Materials and Methods: We developed four deep learning-based pipelines for Type B aortic dissection segmentation: a single-step model, a sequential model, a sequential multi-task model, and an ensemble model, utilizing 3D U-Net and Swin-UnetR architectures. A dataset of 100 retrospective CTA images was split into training (n=80), validation (n=10), and testing (n=10). Performance was assessed using the Dice Coefficient and Hausdorff Distance. Results: Our approach achieved superior segmentation accuracy, with Dice Coefficients of 0.91 ± 0.07 for TL, 0.88 ± 0.18 for FL, and 0.47 ± 0.25 for FLT, outperforming Yao et al. (1), who reported 0.78 ± 0.20, 0.68 ± 0.18, and 0.25 ± 0.31, respectively. Conclusion: The proposed pipelines provide accurate segmentation of TBAD features, enabling derivation of morphological parameters for surveillance and treatment planning
@article{arxiv.2506.22222,
title = {Advanced Deep Learning Techniques for Automated Segmentation of Type B Aortic Dissections},
author = {Hao Xu and Ruth Lim and Brian E. Chapman},
journal= {arXiv preprint arXiv:2506.22222},
year = {2025}
}