Deep-learning-based Image Segmentation for Image-based Computational Hemodynamic Analysis of Abdominal Aortic Aneurysms: A Comparison Study

Authors

Zonghan Lyu, Michigan Technological UniversityFollow
Kristin King, Michigan Technological University
Mostafa Rezaeitaleshmahalleh, Michigan Technological UniversityFollow
Drew Pienta, Michigan Technological UniversityFollow
Nan Mu, Michigan Technological UniversityFollow
Chen Zhao, Michigan Technological UniversityFollow
Weihua Zhou, Michigan Technological UniversityFollow
Jingfeng Jiang, Michigan Technological UniversityFollow

Document Type

Article

Publication Date

8-25-2023

Department

Department of Biomedical Engineering; Health Research Institute; Department of Applied Computing

Abstract

Computational hemodynamics is increasingly used to quantify hemodynamic characteristics in and around abdominal aortic aneurysms (AAA) in a patient-specific fashion. However, the time-consuming manual annotation hinders the clinical translation of computational hemodynamic analysis. Thus, we investigate the feasibility of using deep-learning-based image segmentation methods to reduce the time required for manual segmentation. Two of the latest deep-learning-based image segmentation methods, ARU-Net and CACU-Net, were used to test the feasibility of automated computer model creation for computational hemodynamic analysis. Morphological features and hemodynamic metrics of 30 computed tomography angiography (CTA) scans were compared between pre-dictions and manual models. The DICE score for both networks was 0.916, and the correlation value was above 0.95, indicating their ability to generate models comparable to human segmentation. The Bland-Altman analysis shows a good agreement between deep learning and manual segmentation results. Compared with manual (computational hemodynamics) model recreation, the time for automated computer model generation was significantly reduced (from ~ 2hr to ~ 10min). Automated image segmentation can significantly reduce time expenses on the recreation of patient-specific AAA models. Moreover, our study showed that both CACU-Net and ARU-Net could accomplish AAA segmentation, and CACU-Net outperformed ARU-Net in terms of accuracy and time-saving.

Publisher's Statement

© 2023 The Author(s). Published by IOP Publishing Ltd. Publisher’s version of record: https://doi.org/10.1088/2057-1976/acf3ed

Publication Title

Biomedical physics & engineering express

Recommended Citation

Lyu, Z., King, K., Rezaeitaleshmahalleh, M., Pienta, D., Mu, N., Zhao, C., Zhou, W., & Jiang, J. (2023). Deep-learning-based Image Segmentation for Image-based Computational Hemodynamic Analysis of Abdominal Aortic Aneurysms: A Comparison Study. Biomedical physics & engineering express, 9(6). http://doi.org/10.1088/2057-1976/acf3ed
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p2/87

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Version

Publisher's PDF