Stacked Ensemble Learning for Abdominal Aortic Aneurysm Segmentation in CT Angiography

2026-07-01

AI Summary

This study addresses the critical need for accurate and efficient three-dimensional geometric modeling in abdominal aortic aneurysm (AAA) rupture risk assessment, where existing segmentation methods suffer from low efficiency and high subjectivity. The authors propose an automated segmentation framework based on stacked ensemble learning, integrating three nnUNetv2 variants—Default, DA5, and ResEncL—as base learners. Their voxel-wise probability outputs are fused via L2-regularized logistic regression, and a novel metric termed “separation distance” is introduced to quantify boundary consistency. Evaluated on an independent test set, the method achieves a Dice coefficient of 0.9752 and a mean separation distance of 0.4598 mm, significantly outperforming individual models and delivering marked improvements in both volumetric overlap and boundary precision—advancements particularly beneficial for subsequent biomechanical analysis.

Abstract

Abdominal aortic aneurysm (AAA) rupture risk assessment increasingly relies on patient-specific biomechanical computations, which require accurate three-dimensional aneurysm geometry from computed tomography angiography (CTA). Manual and semi-automated segmentation remain time-consuming and observer-dependent, limiting their use in large-scale clinical workflows. In this study, we developed a stacked ensemble framework for automated AAA seg-mentation from CTA images. We used 40 anonymised contrast-enhanced CTA scans from AAA patients and generated reference segmentations using the nnInteractive extension in 3D Slicer. We partitioned the dataset into 32 training cases and 8 held-out test cases. Three nnUNetv2 configurations, Default, DA5, and ResEncL, were trained as base learners, and their voxel-wise probability out-puts were combined using an L2-regularised logistic regression meta-model trained from out-of-sample cross-validation predictions. We evaluated segmentation performance using Dice Coefficient and Separation Distance, a mean boundary-to-boundary distance measure introduced in this study to quantify average surface agreement. On the held-out test set, the ensemble achieved the highest mean Dice Coefficient of 0.9752 and the lowest mean Separation Distance of 0.4598 mm, indicating improved volumetric overlap and average boundary agreement compared with the individual base learners. Overall, stacked ensemble learning provided small but meaningful improvements in AAA segmentation, particularly for boundary accuracy relevant to downstream patient-specific bio-mechanical computations.

Problem

• Abdominal aortic aneurysm
• CT angiography
• Image segmentation
• Clinical workflow
• Biomechanical computation

Innovation

• stacked ensemble learning
• abdominal aortic aneurysm segmentation
• nnUNetv2
• Separation Distance
• CT angiography