Abstract <p>We introduce AortaExplorer, an open-source, fully automated AI-driven framework for end-to-end aortic analysis from computed tomography angiography (CTA) scans. AortaExplorer extracts established biomarkers, such as diameters across anatomical segments, and introduces novel metrics, including aortic tortuosity. Diameter measurements were validated against expert manual readings in more than 10,000 CTA scans from Danish population cohorts, demonstrating high accuracy. The computed descending aortic tortuosity index aligns with trends reported in previous studies, confirming its increase with age. By reducing analysis time from approximately 15 minutes per case to under five minutes, AortaExplorer enables efficient, reproducible assessment of aortic morphology at scale. This tool supports clinical research and large cohort studies by combining state-of-the-art segmentation performance with extensive visualization and quantitative reporting.</p> Graphical abstract <p></p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

AortaExplorer: AI-driven analysis of the aorta in CT images

  • Rasmus R. Paulsen,
  • Linnea Hjordt Juul,
  • Michael Huy Cuong Pham,
  • Jørgen Tobias Kühl,
  • Klaus Fuglsang Kofoed,
  • Kristine Aavild Sørensen,
  • Josefine Vilsbøll Sundgaard

摘要

Abstract

We introduce AortaExplorer, an open-source, fully automated AI-driven framework for end-to-end aortic analysis from computed tomography angiography (CTA) scans. AortaExplorer extracts established biomarkers, such as diameters across anatomical segments, and introduces novel metrics, including aortic tortuosity. Diameter measurements were validated against expert manual readings in more than 10,000 CTA scans from Danish population cohorts, demonstrating high accuracy. The computed descending aortic tortuosity index aligns with trends reported in previous studies, confirming its increase with age. By reducing analysis time from approximately 15 minutes per case to under five minutes, AortaExplorer enables efficient, reproducible assessment of aortic morphology at scale. This tool supports clinical research and large cohort studies by combining state-of-the-art segmentation performance with extensive visualization and quantitative reporting.

Graphical abstract