Saved in:
Bibliographic Details
Main Authors: Sufyan, Osamah, Brückmann, Martin, Wickenhöfer, Ralph, Dellen, Babette, Jaekel, Uwe
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10312
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917401153503232
author Sufyan, Osamah
Brückmann, Martin
Wickenhöfer, Ralph
Dellen, Babette
Jaekel, Uwe
author_facet Sufyan, Osamah
Brückmann, Martin
Wickenhöfer, Ralph
Dellen, Babette
Jaekel, Uwe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10312
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Anatomy-Informed Deep Learning for Abdominal Aortic Aneurysm Segmentation
Sufyan, Osamah
Brückmann, Martin
Wickenhöfer, Ralph
Dellen, Babette
Jaekel, Uwe
Computer Vision and Pattern Recognition
Machine Learning
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.
title Anatomy-Informed Deep Learning for Abdominal Aortic Aneurysm Segmentation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2604.10312