[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81780-en":3,"doc-seo-81780-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},81780,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Stacked Ensemble Learning for Abdominal Aortic Aneurysm Segmentation in CT Angiography","Abdominal aortic aneurysm (AAA) rupture risk assessment increasingly depends on patient-specific biomechanical computations that require accurate three-dimensional aneurysm geometry from computed tomography angiography (CTA). Manual and semi-automated segmentation is slow and observer-dependent, hindering large-scale clinical use. This study builds a stacked ensemble for automated AAA segmentation, trained on reference labels from 32 cases and evaluated on 8 held-out scans using Dice and surface separation distance metrics.","Stacked Ensemble Learning for Abdominal Aortic Aneurysm Segmentation in CT Angiography  \nJoshua Fry 1[0009-0005-0002-6037], Sajjad Arzemanzadeh 1[0000-0001-7381-1777], Saeideh Sekhavat1[0009-0006-9280-2781], Mostafa Jamshidian 1[0000-0002-5166-171X], Adam Wittek 1[0000-0001- 9780-8361], Michael Bertolacci2[0000-0003-0317-5941], Elke R. Gizewski3[0000-0001-6859-8377], Eva Gassner3[0000-0002-8309-2638], Alexander Loizides3[0000-0001-5179-2309], Maximillian Lutz3[0009- 0009-8141-8006], Florian K. Enzmann4[0000-0002-7200-4145], Karol Miller1[0000-0002-6577-2082]  \n1 Intelligent Systems for Medicine Laboratory, The University of Western Australia, Perth, Western Australia, Australia  \n2 School of Physics, Mathematics and Computing, The University of Western Australia, Perth, Western Australia, Australia  \n3 Department of Radiology, Medical University of Innsbruck, Innsbruck, Austria  \n4 Department of Vascular Surgery, Medical University of Innsbruck, Innsbruck, Austria  \n[mostafa.jamshidian@uwa.edu.au](mostafa.jamshidian@uwa.edu.au)  \nAbstract. 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 timeconsuming and observer-dependent, limiting their use in large-scale clinical workflows. In this study, we developed a stacked ensemble framework for automated AAA segmentation 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 outputs were combined using an L2-regularised logistic regression meta-model trained from out-of-sample cross-validation predictions.  \nWe 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 biomechanical computations.  \nKeywords: Abdominal Aortic Aneurysm, Image Segmentation, Ensemble  \nLearning.  \n1 Introduction  \nAbdominal aortic aneurysm (AAA) is a typically asymptomatic vascular condition characterised by dilation of the abdominal aorta to a diameter exceeding 3.0 cm, approximately two standard deviations above the average aortic diameter of 1.8 cm [1, 2] . AAA develops due to structural weakening of the aortic wall and ruptures when blood pressure-induced wall stress exceeds wall strength. Although AAA may remain clinically silent, rupture is life-threatening, with mortality rates reaching up to 80% without immediate intervention [3] . Current clinical guidelines recommend surgical intervention when the maximum aneurysm diameter exceeds 5.5 cm in men and 5.0 cm in women, or when the annual growth rate exceeds 1 cm [1, 4] . However, aneurysm diameter alone is an unreliable predictor of rupture risk at the individual level. Many aneurysms exceeding clinical thresholds remain stable throughout a patient’s lifetime [1, 4, 5], while smaller aneurysms may still rupture [6] . Autopsy studies report that approximately 60% of AAAs larger than 5 cm do not rupture, whereas nearly 13% of ruptured AAAs measure 5 cm or less [7] .  \nTowards patient-specific AAA assessment, biomedical computational studies have investigated AAA wa","cbCaijj5GPrBN47M","https://ap.wps.com/l/cbCaijj5GPrBN47M","pdf",723557,3,1,14,"English","en",105,"# Introduction\n## Problem and clinical motivation\n## Deep learning and nnUNet background\n## Ensemble learning for improved performance","[{\"question\":\"Why is automated AAA segmentation needed in CT angiography workflows?\",\"answer\":\"Manual and semi-automated segmentation are time-consuming and depend on observers, limiting scalability and reproducibility for large-scale clinical biomechanical analysis.\"},{\"question\":\"How is the stacked ensemble constructed in the study?\",\"answer\":\"Three nnUNetv2 configurations (Default, DA5, ResEncL) act as base learners, and an L2-regularised logistic regression meta-model combines their voxel-wise probability outputs using out-of-sample cross-validation predictions.\"},{\"question\":\"What metrics are used to evaluate segmentation quality?\",\"answer\":\"Segmentation performance is assessed using the Dice Coefficient and a separation distance metric that quantifies mean boundary-to-boundary surface agreement introduced in the study.\"}]",1784176094,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"stacked-ensemble-learning-for-abdominal-aortic-aneurysm-segmentation-in-ct-angiography","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/stacked-ensemble-learning-for-abdominal-aortic-aneurysm-segmentation-in-ct-angiography/81780/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is automated AAA segmentation needed in CT angiography workflows?","Question",{"text":75,"@type":76},"Manual and semi-automated segmentation are time-consuming and depend on observers, limiting scalability and reproducibility for large-scale clinical biomechanical analysis.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the stacked ensemble constructed in the study?",{"text":80,"@type":76},"Three nnUNetv2 configurations (Default, DA5, ResEncL) act as base learners, and an L2-regularised logistic regression meta-model combines their voxel-wise probability outputs using out-of-sample cross-validation predictions.",{"name":82,"@type":73,"acceptedAnswer":83},"What metrics are used to evaluate segmentation quality?",{"text":84,"@type":76},"Segmentation performance is assessed using the Dice Coefficient and a separation distance metric that quantifies mean boundary-to-boundary surface agreement introduced in the study.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]