Automatic Segmentation of Abdominal Aortic Aneurysms from CT Angiography Using a Context-aware Cascaded U-Net

Overview

Journal Comput Biol Med

Publisher Elsevier

Specialties Biology
General Medicine
Medical Informatics

Date 2023 Mar 29

PMID 36989747

Authors

Nan Mu

Zonghan Lyu

Mostafa Rezaeitaleshmahalleh

Xiaoming Zhang

Todd Rasmussen

Robert McBane

Jingfeng Jiang

Affiliations

Soon will be listed here.

Abstract

We delineate abdominal aortic aneurysms, including lumen and intraluminal thrombosis (ILT), from contrast-enhanced computed tomography angiography (CTA) data in 70 patients with complete automation. A novel context-aware cascaded U-Net configuration enables automated image segmentation. Notably, auto-context structure, in conjunction with dilated convolutions, anisotropic context module, hierarchical supervision, and a multi-class loss function, are proposed to improve the delineation of ILT in an unbalanced, low-contrast multi-class labeling problem. A quantitative analysis shows that the automated image segmentation produces comparable results with trained human users (e.g., DICE scores of 0.945 and 0.804 for lumen and ILT, respectively). Resultant morphological metrics (e.g., volume, surface area, etc.) are highly correlated to those parameters generated by trained human users. In conclusion, the proposed automated multi-class image segmentation tool has the potential to be further developed as a translational software tool that can be used to improve the clinical management of AAAs.

Citing Articles

Improving Prediction of Intracranial Aneurysm Rupture Status Using Temporal Velocity-Informatics.

Rezaeitaleshmahalleh M, Lyu Z, Mu N, Nainamalai V, Tang J, Gemmete J Ann Biomed Eng. 2025; .

PMID: 39904865 DOI: 10.1007/s10439-025-03686-2.

Automatic segmentation of intraluminal thrombosis of abdominal aortic aneurysms from CT angiography using a mixed-scale-driven multiview perception network (MNet) model.

Lyu Z, Mu N, Rezaeitaleshmahalleh M, Zhang X, McBane R, Jiang J Comput Biol Med. 2024; 179:108838.

PMID: 39033681 PMC: 11772087. DOI: 10.1016/j.compbiomed.2024.108838.

Computational Hemodynamics-Based Growth Prediction for Small Abdominal Aortic Aneurysms: Laminar Simulations Versus Large Eddy Simulations.

Rezaeitaleshmahalleh M, Lyu Z, Mu N, Wang M, Zhang X, Rasmussen T Ann Biomed Eng. 2024; 52(11):3078-3097.

PMID: 39020077 PMC: 11772086. DOI: 10.1007/s10439-024-03572-3.

Slimmable transformer with hybrid axial-attention for medical image segmentation.

Hu Y, Mu N, Liu L, Zhang L, Jiang J, Li X Comput Biol Med. 2024; 173:108370.

PMID: 38564854 PMC: 11772084. DOI: 10.1016/j.compbiomed.2024.108370.

USING CONVOLUTIONAL NEURAL NETWORK-BASED SEGMENTATION FOR IMAGE-BASED COMPUTATIONAL FLUID DYNAMICS SIMULATIONS OF BRAIN ANEURYSMS: INITIAL EXPERIENCE IN AUTOMATED MODEL CREATION.

Rezaeitaleshmahalleh M, Lyu Z, Mu N, Jiang J J Mech Med Biol. 2024; 23(4).

PMID: 38523806 PMC: 10956116. DOI: 10.1142/s0219519423400559.

References

Gloviczki P, Lawrence P, Forbes T . Update of the Society for Vascular Surgery abdominal aortic aneurysm guidelines. J Vasc Surg. 2017; 67(1):1. DOI: 10.1016/j.jvs.2017.11.022. View

Lopez-Linares K, Stephens M, Garcia I, Macia I, Gonzalez Ballester M, San Jose Estepar R . Abdominal Aortic Aneurysm Segmentation Using Convolutional Neural Networks Trained with Images Generated with a Synthetic Shape Model. Mach Learn Med Eng Cardiovasc Health Intravasc Imaging Comput Assist Stenting (2019). 2021; 11794:167-174. PMC: 8188890. DOI: 10.1007/978-3-030-33327-0_20. View

Chaikof E, Dalman R, Eskandari M, Jackson B, Lee W, Mansour M . The Society for Vascular Surgery practice guidelines on the care of patients with an abdominal aortic aneurysm. J Vasc Surg. 2017; 67(1):2-77.e2. DOI: 10.1016/j.jvs.2017.10.044. View

Wilmink A, Quick C, Hubbard C, Day N . Effectiveness and cost of screening for abdominal aortic aneurysm: results of a population screening program. J Vasc Surg. 2003; 38(1):72-7. DOI: 10.1016/s0741-5214(03)00135-6. View

Silverstein M, Pitts S, Chaikof E, Ballard D . Abdominal aortic aneurysm (AAA): cost-effectiveness of screening, surveillance of intermediate-sized AAA, and management of symptomatic AAA. Proc (Bayl Univ Med Cent). 2005; 18(4):345-67. PMC: 1255946. DOI: 10.1080/08998280.2005.11928095. View

Lalys F, Yan V, Kaladji A, Lucas A, Esneault S . Generic thrombus segmentation from pre- and post-operative CTA. Int J Comput Assist Radiol Surg. 2017; 12(9):1501-1510. DOI: 10.1007/s11548-017-1591-8. View

Mu N, Wang H, Zhang Y, Jiang J, Tang J . Progressive global perception and local polishing network for lung infection segmentation of COVID-19 CT images. Pattern Recognit. 2021; 120:108168. PMC: 8272691. DOI: 10.1016/j.patcog.2021.108168. View

Chung M, Lee J, Park S, Lee C, Lee J, Shin Y . Liver segmentation in abdominal CT images via auto-context neural network and self-supervised contour attention. Artif Intell Med. 2021; 113:102023. DOI: 10.1016/j.artmed.2021.102023. View

Tu Z, Bai X . Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans Pattern Anal Mach Intell. 2010; 32(10):1744-57. DOI: 10.1109/TPAMI.2009.186. View

10.

Lindquist Liljeqvist M, Bogdanovic M, Siika A, Gasser T, Hultgren R, Roy J . Geometric and biomechanical modeling aided by machine learning improves the prediction of growth and rupture of small abdominal aortic aneurysms. Sci Rep. 2021; 11(1):18040. PMC: 8433325. DOI: 10.1038/s41598-021-96512-3. View

11.

Olson S, Wijesinha M, Panthofer A, Blackwelder W, Upchurch Jr G, Terrin M . Evaluating Growth Patterns of Abdominal Aortic Aneurysm Diameter With Serial Computed Tomography Surveillance. JAMA Surg. 2021; 156(4):363-370. PMC: 7890454. DOI: 10.1001/jamasurg.2020.7190. View

12.

Lopez-Linares K, Aranjuelo N, Kabongo L, Maclair G, Lete N, Ceresa M . Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks. Med Image Anal. 2018; 46:202-214. DOI: 10.1016/j.media.2018.03.010. View

13.

Meyrignac O, Bal L, Zadro C, Vavasseur A, Sewonu A, Gaudry M . Combining Volumetric and Wall Shear Stress Analysis from CT to Assess Risk of Abdominal Aortic Aneurysm Progression. Radiology. 2020; 295(3):722-729. DOI: 10.1148/radiol.2020192112. View

14.

Stenbaek J, Kalin B, Swedenborg J . Growth of thrombus may be a better predictor of rupture than diameter in patients with abdominal aortic aneurysms. Eur J Vasc Endovasc Surg. 2000; 20(5):466-9. DOI: 10.1053/ejvs.2000.1217. View

15.

Ng E, Looi L . Numerical analysis of biothermal-fluids and cardiac thermal pulse of abdominal aortic aneurysm. Math Biosci Eng. 2022; 19(10):10213-10251. DOI: 10.3934/mbe.2022479. View

16.

Mohseni Salehi S, Erdogmus D, Gholipour A . Auto-Context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging. IEEE Trans Med Imaging. 2017; 36(11):2319-2330. PMC: 5715475. DOI: 10.1109/TMI.2017.2721362. View

17.

Mu N, Lyu Z, Rezaeitaleshmahalleh M, Tang J, Jiang J . An attention residual u-net with differential preprocessing and geometric postprocessing: Learning how to segment vasculature including intracranial aneurysms. Med Image Anal. 2022; 84:102697. PMC: 9830590. DOI: 10.1016/j.media.2022.102697. View

18.

Hoornweg L, Storm-Versloot M, Ubbink D, Koelemay M, Legemate D, Balm R . Meta analysis on mortality of ruptured abdominal aortic aneurysms. Eur J Vasc Endovasc Surg. 2008; 35(5):558-70. DOI: 10.1016/j.ejvs.2007.11.019. View

19.

Hwang B, Kim J, Lee S, Kim E, Kim J, Jung Y . Automatic Detection and Segmentation of Thrombi in Abdominal Aortic Aneurysms Using a Mask Region-Based Convolutional Neural Network with Optimized Loss Functions. Sensors (Basel). 2022; 22(10). PMC: 9145191. DOI: 10.3390/s22103643. View

20.

Lindholt J, Vammen S, Juul S, Henneberg E, Fasting H . The validity of ultrasonographic scanning as screening method for abdominal aortic aneurysm. Eur J Vasc Endovasc Surg. 1999; 17(6):472-5. DOI: 10.1053/ejvs.1999.0835. View