Anatomy-Informed Deep Learning for Abdominal Aortic Aneurysm Segmentation

TL;DR

This paper introduces an anatomy-aware deep learning framework for abdominal aortic aneurysm segmentation in CT scans, improving accuracy and reducing false positives by integrating anatomical priors.

Contribution

The novel integration of organ exclusion masks into the training process guides the model to focus on relevant anatomy, enhancing segmentation robustness with limited data.

Findings

High segmentation accuracy achieved with small dataset

Significant reduction in false positives

Improved boundary consistency over baseline

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.