Anatomy-Informed Deep Learning for Abdominal Aortic Aneurysm Segmentation

2026-04-11

AI Summary

Abdominal aortic aneurysm (AAA) segmentation in CT angiography remains challenging due to substantial anatomical variability, ambiguous vessel boundaries, and interference from adjacent organs, often resulting in high false-positive rates. This work proposes a U-Net-based segmentation framework that explicitly integrates anatomical priors by incorporating organ exclusion masks generated by TotalSegmentator directly into the training process. These masks are leveraged within the loss function to suppress lesion predictions in non-vascular regions, thereby guiding the model to focus exclusively on anatomically plausible aortic structures and their dilated segments. Evaluated under limited-data conditions, the proposed method significantly enhances model robustness and generalization, effectively reducing false positives and improving boundary consistency compared to the standard U-Net, ultimately achieving high-precision AAA segmentation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

In CT angiography, the accurate segmentation of abdominal aortic aneurysms (AAAs) is difficult due to large anatomical variability, low-contrast vessel boundaries, and the close proximity of organs whose intensities resemble vascular structures, often leading to false positives. To address these challenges, we propose an anatomy-aware segmentation framework that integrates organ exclusion masks derived from TotalSegmentator into the training process. These masks encode explicit anatomical priors by identifying non-vascular organsand penalizing aneurysm predictions within these regions, thereby guiding the U-Net to focus on the aorta and its pathological dilation while suppressing anatomically implausible predictions. Despite being trained on a relatively small dataset, the anatomy-aware model achieves high accuracy, substantially reduces false positives, and improves boundary consistency compared to a standard U-Net baseline. The results demonstrate that incorporating anatomical knowledge through exclusion masks provides an efficient mechanism to enhance robustness and generalization, enabling reliable AAA segmentation even with limited training data.

Problem

• abdominal aortic aneurysm
• segmentation
• CT angiography
• anatomical variability
• false positives

Innovation

• anatomy-aware learning
• organ exclusion masks
• abdominal aortic aneurysm segmentation
• anatomical priors
• U-Net