Automated Screening for Abdominal Aortic Aneurysm in CT Scans Under Clinical Conditions Using Deep Learning

Overview

Journal Diagnostics (Basel)

Specialty Radiology

Date 2021 Nov 27

PMID 34829478

Citations 7

Authors

Alena-K Golla

Christian Tonnes

Tom Russ

Dominik F Bauer

Matthias F Froelich

Steffen J Diehl

Stefan O Schoenberg

Michael Keese

Lothar R Schad

Frank G Zollner

Johann S Rink

Affiliations

Soon will be listed here.

Abstract

Abdominal aortic aneurysms (AAA) may remain clinically silent until they enlarge and patients present with a potentially lethal rupture. This necessitates early detection and elective treatment. The goal of this study was to develop an easy-to-train algorithm which is capable of automated AAA screening in CT scans and can be applied to an intra-hospital environment. Three deep convolutional neural networks (ResNet, VGG-16 and AlexNet) were adapted for 3D classification and applied to a dataset consisting of 187 heterogenous CT scans. The 3D ResNet outperformed both other networks. Across the five folds of the first training dataset it achieved an accuracy of 0.856 and an area under the curve (AUC) of 0.926. Subsequently, the algorithms performance was verified on a second data set containing 106 scans, where it ran fully automated and resulted in an accuracy of 0.953 and an AUC of 0.971. A layer-wise relevance propagation (LRP) made the decision process interpretable and showed that the network correctly focused on the aortic lumen. In conclusion, the deep learning-based screening proved to be robust and showed high performance even on a heterogeneous multi-center data set. Integration into hospital workflow and its effect on aneurysm management would be an exciting topic of future research.

Citing Articles

A Comprehensive Review of Cardiovascular Disease Management: Cardiac Biomarkers, Imaging Modalities, Pharmacotherapy, Surgical Interventions, and Herbal Remedies.

Netala V, Teertam S, Li H, Zhang Z Cells. 2024; 13(17.

PMID: 39273041 PMC: 11394358. DOI: 10.3390/cells13171471.

Streamlining Acute Abdominal Aortic Dissection Management-An AI-based CT Imaging Workflow.

Raj A, Allababidi A, Kayed H, Gerken A, Muller J, Schoenberg S J Imaging Inform Med. 2024; 37(6):2729-2739.

PMID: 38864947 PMC: 11612133. DOI: 10.1007/s10278-024-01164-0.

Deep learning techniques for imaging diagnosis and treatment of aortic aneurysm.

Huang L, Lu J, Xiao Y, Zhang X, Li C, Yang G Front Cardiovasc Med. 2024; 11:1354517.

PMID: 38481955 PMC: 10933089. DOI: 10.3389/fcvm.2024.1354517.

Artificial intelligence in clinical workflow processes in vascular surgery and beyond.

Dossabhoy S, Ho V, Ross E, Rodriguez F, Arya S Semin Vasc Surg. 2023; 36(3):401-412.

PMID: 37863612 PMC: 10956485. DOI: 10.1053/j.semvascsurg.2023.07.002.

Artificial Intelligence Application to Screen Abdominal Aortic Aneurysm Using Computed tomography Angiography.

Spinella G, Fantazzini A, Finotello A, Vincenzi E, Boschetti G, Brutti F J Digit Imaging. 2023; 36(5):2125-2137.

PMID: 37407843 PMC: 10501994. DOI: 10.1007/s10278-023-00866-1.

References

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

Claridge R, Arnold S, Morrison N, van Rij A . Measuring abdominal aortic diameters in routine abdominal computed tomography scans and implications for abdominal aortic aneurysm screening. J Vasc Surg. 2017; 65(6):1637-1642. DOI: 10.1016/j.jvs.2016.11.044. View

Bains P, Oliffe J, Mackay M, Kelly M . Screening Older Adult Men for Abdominal Aortic Aneurysm: A Scoping Review. Am J Mens Health. 2021; 15(2):15579883211001204. PMC: 7970195. DOI: 10.1177/15579883211001204. View

Cao L, Shi R, Ge Y, Xing L, Zuo P, Jia Y . Fully automatic segmentation of type B aortic dissection from CTA images enabled by deep learning. Eur J Radiol. 2019; 121:108713. DOI: 10.1016/j.ejrad.2019.108713. View

Singh D, Kumar V, Vaishali , Kaur M . Classification of COVID-19 patients from chest CT images using multi-objective differential evolution-based convolutional neural networks. Eur J Clin Microbiol Infect Dis. 2020; 39(7):1379-1389. PMC: 7183816. DOI: 10.1007/s10096-020-03901-z. View

Hahn S, Perry M, Morris C, Wshah S, Bertges D . Machine deep learning accurately detects endoleak after endovascular abdominal aortic aneurysm repair. JVS Vasc Sci. 2021; 1:5-12. PMC: 8489204. DOI: 10.1016/j.jvssci.2019.12.003. View

Do H, Ijaz A, Gharahi H, Zambrano B, Choi J, Lee W . Prediction of Abdominal Aortic Aneurysm Growth Using Dynamical Gaussian Process Implicit Surface. IEEE Trans Biomed Eng. 2018; 66(3):609-622. PMC: 6414317. DOI: 10.1109/TBME.2018.2852306. View

Oliver-Williams C, Sweeting M, Jacomelli J, Summers L, Stevenson A, Lees T . Safety of Men With Small and Medium Abdominal Aortic Aneurysms Under Surveillance in the NAAASP. Circulation. 2019; 139(11):1371-1380. PMC: 6415808. DOI: 10.1161/CIRCULATIONAHA.118.036966. View

Mohammadi S, Mohammadi M, Dehlaghi V, Ahmadi A . Automatic Segmentation, Detection, and Diagnosis of Abdominal Aortic Aneurysm (AAA) Using Convolutional Neural Networks and Hough Circles Algorithm. Cardiovasc Eng Technol. 2019; 10(3):490-499. DOI: 10.1007/s13239-019-00421-6. View

10.

Schmitz-Rixen T, Keese M, Hakimi M, Peters A, Bockler D, Nelson K . Ruptured abdominal aortic aneurysm-epidemiology, predisposing factors, and biology. Langenbecks Arch Surg. 2016; 401(3):275-88. DOI: 10.1007/s00423-016-1401-8. View

11.

Harris R, Kim S, Lohr J, Towey S, Velichkovich Z, Kabachenko T . Classification of Aortic Dissection and Rupture on Post-contrast CT Images Using a Convolutional Neural Network. J Digit Imaging. 2019; 32(6):939-946. PMC: 6841906. DOI: 10.1007/s10278-019-00281-5. View

12.

Lindholt J, Sogaard R, Laustsen J . Prognosis of ruptured abdominal aortic aneurysms in Denmark from 1994-2008. Clin Epidemiol. 2012; 4:111-3. PMC: 3372968. DOI: 10.2147/CLEP.S31098. View

13.

Peters A, Hakimi M, Erhart P, Keese M, Schmitz-Rixen T, Wortmann M . Current treatment strategies for ruptured abdominal aortic aneurysm. Langenbecks Arch Surg. 2016; 401(3):289-98. DOI: 10.1007/s00423-016-1405-4. View

14.

Sweeting M, Marshall J, Glover M, Nasim A, Bown M . Evaluating the Cost-Effectiveness of Changes to the Surveillance Intervals in the UK Abdominal Aortic Aneurysm Screening Programme. Value Health. 2021; 24(3):369-376. DOI: 10.1016/j.jval.2020.10.015. View

15.

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

16.

Ghesu F, Georgescu B, Zheng Y, Grbic S, Maier A, Hornegger J . Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans. IEEE Trans Pattern Anal Mach Intell. 2018; 41(1):176-189. DOI: 10.1109/TPAMI.2017.2782687. View

17.

Golla A, Bauer D, Schmidt R, Russ T, Norenberg D, Chung K . Convolutional Neural Network Ensemble Segmentation With Ratio-Based Sampling for the Arteries and Veins in Abdominal CT Scans. IEEE Trans Biomed Eng. 2020; 68(5):1518-1526. DOI: 10.1109/TBME.2020.3042640. View

18.

Zhang L, Jiang Z, Choi J, Lim C, Maiti T, Baek S . Patient-Specific Prediction of Abdominal Aortic Aneurysm Expansion Using Bayesian Calibration. IEEE J Biomed Health Inform. 2019; 23(6):2537-2550. PMC: 6890695. DOI: 10.1109/JBHI.2019.2896034. View

19.

Salata K, Hussain M, de Mestral C, Greco E, Aljabri B, Mamdani M . Comparison of Outcomes in Elective Endovascular Aortic Repair vs Open Surgical Repair of Abdominal Aortic Aneurysms. JAMA Netw Open. 2019; 2(7):e196578. PMC: 6624804. DOI: 10.1001/jamanetworkopen.2019.6578. View

20.

Hirata K, Nakaura T, Nakagawa M, Kidoh M, Oda S, Utsunomiya D . Machine Learning to Predict the Rapid Growth of Small Abdominal Aortic Aneurysm. J Comput Assist Tomogr. 2020; 44(1):37-42. DOI: 10.1097/RCT.0000000000000958. View