Automated Aortic Quantification Based on Artificial Intelligence: Validation Using Contrast-Enhanced and Non-Contrast CT Scans from the Same Session
Authors:
- Jia-Sheng HongJia-Sheng Hong
- Yun-Hsuan TzengYTYun-Hsuan Tzeng
- Kuan-Ting WuKWKuan-Ting Wu
- Shih-Yu HuangSHShih-Yu Huang
- Ting-Wei WangTWTing-Wei Wang
- Guan-Yu LiGLGuan-Yu Li
- Chun-Yi LinCLChun-Yi Lin
- Ho-Ren LiuHLHo-Ren Liu
- Hai-Neng FuHFHai-Neng Fu
- Yung-Tsai LeeYLYung-Tsai Lee
- Wei-Hsian YinWYWei-Hsian Yin
- Yu-Te WuYWYu-Te Wu
Open Access
- 17 April 2026
- journal article
- research article
- Published by MDPI AG in Bioengineering
- Vol. 13 (4) , 471
Abstract
Early detection of aortic dilatation is clinically important for preventing progression to serious aortic disease and enabling timely intervention. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. A total of 190 patient cases were analyzed, each having paired contrast-enhanced and non-contrast CT scans acquired in the same session, resulting in 380 scans. Our approach, based on open-source tools, demonstrated strong agreement with manual annotations, particularly in the ascending aorta. For contrast-enhanced CT, the AI achieved a correlation coefficient of 0.987 and intraclass correlation coefficient (ICC) of 0.986; for non-contrast CT, both were 0.945. Compared with clinical records, the sensitivity of AI detection was 97% for contrast-enhanced CT and 94% for non-contrast CT. This AI-based workflow enables highly sensitive automated aortic quantification in both contrast-enhanced and non-contrast CT scans, supporting broader clinical applicability across different imaging conditions.Keywords
All Related Versions
Funding Information
- National Yang Ming Chiao Tung University (CY11102)
- National Yang Ming Chiao Tung University (CY113-CY11201-01)
- National Yang Ming Chiao Tung University (CY113-CY11201-02)
- National Yang Ming Chiao Tung University (CY113-CY11201-03)
- University System of Taiwan (115W084700)
This publication has 40 references indexed in Scilit:
- AortaExplorer: AI-driven analysis of the aorta in CT imagesMedical & Biological Engineering & Computing, 2026
- Radiomic Features Extracted from Magnetic Resonance Imaging to Identify Arteriopathy in a Humanized Mouse Model of Sickle Cell Anemia and Sickle Cell TraitAnnals of Biomedical Engineering, 2026
- Artificial Intelligence Detection and Segmentation Models: A Systematic Review and Meta-Analysis of Brain Tumors in Magnetic Resonance ImagingMayo Clinic Proceedings: Digital Health, 2024
- Validation of an AI-based algorithm for measurement of the thoracic aortic diameter in low-dose chest CTEuropean Journal of Radiology, 2023
- Health Economic Research Assessing the Value of Early Detection of Cardiovascular Disease: A Systematic ReviewPharmacoEconomics, 2023
- Population-Based Risk Factors for Ascending, Arch, Descending, and Abdominal Aortic Dilations for 60-74–Year-Old IndividualsJACC, 2021
- Automated segmentation and quantification of the healthy and diseased aorta in CT angiographies using a dedicated deep learning approachEuropean Radiology, 2021
- Deep learning algorithm for detection of aortic dissection on non-contrast-enhanced CTEuropean Radiology, 2020
- Automated 3D segmentation and diameter measurement of the thoracic aorta on non-contrast enhanced CTEuropean Radiology, 2019
- Proximal thoracic aortic diameter measurements at CT: repeatability and reproducibility according to measurement methodThe International Journal of Cardiovascular Imaging, 2012