Abstract
One of the most common imaging methods for diagnosing an abdominal aortic aneurysm, and an endoleak detection is computed tomography angiography. In this paper, we address the problem of aorta and thrombus semantic segmentation, what is a mandatory step to estimate aortic aneurysm diameter. Three end-to-end convolutional neural networks were trained and evaluated. Finally, we proposed an ensemble of deep neural networks with underlying U-Net, ResNet, and VBNet frameworks. Our results show that we are able to outperform state-of-the-art methods by 3% on the Dice metric without any additional post-processing steps.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bai, W., et al.: Recurrent neural networks for aortic image sequence segmentation with sparse annotations. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11073, pp. 586–594. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00937-3_67
Claridge, R., Arnold, S., Morrison, N., van Rij, A.M.: Measuring abdominalaortic diameters in routine abdominal computed tomography scans and implications for abdominal aortic aneurysm screening. J. Vasc. Surg. 65(6), 1637–1642 (2017). https://doi.org/10.1016/j.jvs.2016.11.044
Duquette, A.A., Jodoin, P.M., Bouchot, O., Lalande, A.: 3D segmentation of abdominal aorta from CT-scan and MR images. Comput. Med. Imaging Graph. 36(4), 294–303 (2012). https://doi.org/10.1016/j.compmedimag.2011.12.001. http://www.sciencedirect.com/science/article/pii/S0895611111001480
Hahn, S., Perry, M., Morris, C.S., Wshah, S., Bertges, D.J.: Machine deep learning accurately detects endoleak after endovascular abdominal aortic aneurysm repair. Vasc. Sci. JVS 1, 5–12 (2020)
Jaeger, P.F., et al.: Retina U-NET: embarrassingly simple exploitation of segmentation supervision for medical object detection. arXiv preprint arXiv:1811.08661 (2018)
Joldes, G.R., Miller, K., Wittek, A., Forsythe, R.O., Newby, D.E., Doyle, B.J.: BioPARR: a software system for estimating the rupture potential index for abdominal aortic aneurysms. Sci. Rep. 7(1), 1–15 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lareyre, F., Adam, C., Carrier, M., Dommerc, C., Mialhe, C., Raffort, J.: A fully automated pipeline for mining abdominal aortic aneurysm using image segmentation. Sci. Rep. 9(1), 13750 (2019). https://doi.org/10.1038/s41598-019-50251-8
Lu, J.-T., et al.: DeepAAA: clinically applicable and generalizable detection of abdominal aortic aneurysm using deep learning. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 723–731. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_80
López-Linares, K., et al.: Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using deep convolutional neural networks. Med. Image Anal. 46, 202–214 (2018). https://doi.org/10.1016/j.media.2018.03.010. http://www.sciencedirect.com/science/article/pii/S1361841518301117
Siriapisith, T., Kusakunniran, W., Haddawy, P.: Outer wall segmentation of abdominal aortic aneurysm by variable neighborhood search through intensity and gradient spaces. J. Digital Imaging 31(4), 490–504 (2018). https://doi.org/10.1007/s10278-018-0049-z
Taha, A.A., Hanbury, A.: Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med. Imaging 15(1), 29 (2015). https://doi.org/10.1186/s12880-015-0068-x
Xie, Q., Hovy, E., Luong, M.T., Le, Q.V.: Self-training with noisy student improves ImageNet classification. arXiv preprint arXiv:1911.04252 (2019)
Zhuge, F., Rubin, G.D., Sun, S., Napel, S.: An abdominal aortic aneurysm segmentation method level: set with region and statistical information. Med. Phys. 33(5), 1440–1453 (2006). https://doi.org/10.1118/1.2193247. https://aapm.onlinelibrary.wiley.com/doi/abs/10.1118/1.2193247
Acknowledgements
This work has been partially supported by Statutory Funds of Electronics, Telecommunications and Informatics Faculty, Gdansk University of Technology and grants from National Centre for Research and Development (Internet platform for data integration and collaboration of medical research teams for the stroke treatment centers, PBS2/A3/17/2013).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Dziubich, T., Białas, P., Znaniecki, Ł., Halman, J., Brzeziński, J. (2020). Abdominal Aortic Aneurysm Segmentation from Contrast-Enhanced Computed Tomography Angiography Using Deep Convolutional Networks. In: Bellatreche, L., et al. ADBIS, TPDL and EDA 2020 Common Workshops and Doctoral Consortium. TPDL ADBIS 2020 2020. Communications in Computer and Information Science, vol 1260. Springer, Cham. https://doi.org/10.1007/978-3-030-55814-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-55814-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-55813-0
Online ISBN: 978-3-030-55814-7
eBook Packages: Computer ScienceComputer Science (R0)