Abstract
Morphological segmentation of the aorta is significant for aortic diagnosis, intervention, and prognosis. However, it is difficult for existing methods to achieve the continuity of spatial information and the integrity of morphological extraction, due to the gradually variable and irregular geometry of the aorta in the long-sequence computed tomography (CT). In this paper, we propose a geometry-constrained deformable attention network (GDAN) to learn the aortic common features through interaction with context information of the anatomical space. The deformable attention extractor in our model can adaptively adjust the position and the size of patches to match different shapes of the aorta. The self-attention mechanism is also helpful to explore the long-range dependency in CT sequences and capture more semantic features. The geometry-constrained guider simplifies the morphological representation with a high spatial similarity. The guider imposes strong constraints on geometric boundaries, which changes the sensitivity of gradually variable aortic morphology in the network. Guider can assist the correct extraction of semantic features combining deformable attention extractor. In 204 cases of aortic CT dataset, including 42 normal aorta, 45 coarctation of the aorta, and 107 aortic dissection, our method obtained a mean dice similarity coefficient of 0.943 on the test set (20%), outperforming 6 state-of-the-art methods about aortic segmentation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hiratzka, L.F., et al.: 2010 ACCF/AHA/AATS/ACR/ASA/SCA/SCAI/SIR/STS/SVM guidelines for the diagnosis and management of patients with thoracic aortic disease. J. Am. Coll. Cardiol. 55(14), 27–129 (2010)
Erbel, R., et al.: 2014 ESC guidelines on the diagnosis and treatment of aortic diseases. Russ. J. Cardiol. 123(7), 7–72 (2015)
Roberts, C.S., Roberts, W.C.: Aortic dissection with the entrance tear in the descending thoracic aorta. Analysis of 40 necropsy patients. Ann. Surg. 213(4), 356–368 (1991)
Zhao, Q., et al.: Predictors of aortic dilation in patients with coarctation of the aorta: evaluation with dual-source computed tomography. BMC Cardiovasc. Disord. 18(1), 1–7 (2018)
Garzón, G., Fernández-Velilla, M., Martí, M., Acitores, I., Ybáñez, F., Riera, L.: Endovascular stent-graft treatment of thoracic aortic disease. Radiographics 25(suppl 1), S229–S244 (2005)
Spinelli, D., et al.: Current evidence in predictors of aortic growth and events in acute type B aortic dissection. J. Vasc. Surg. 68(6), 1925–1935 (2018)
Dugas, A., et al.: Reproducibility of abdominal aortic aneurysm diameter measurement and growth evaluation on axial and multiplanar computed tomography reformations. Cardiovasc. Interv. Radiol. 35(4), 779–787 (2012)
Nance, J.W., Ringel, R.E., Fishman, E.K.: Coarctation of the aorta in adolescents and adults: a review of clinical features and CT imaging. J. Cardiovasc. Comput. Tomogr. 10(1), 1–12 (2016)
Fleischmann, D., et al.: Imaging and surveillance of chronic aortic dissection: a scientific statement from the American heart association. Circ. Cardiovasc. Imaging 15(3), e000075 (2022)
Gao, Z., Liu, X., Qi, S., Wu, W., Hau, W.K., Zhang, H.: Automatic segmentation of coronary tree in CT angiography images. Int. J. Adapt. Control Signal Process. 33(8), 1239–1247 (2019)
Wu, C., et al.: Vessel-GAN: angiographic reconstructions from myocardial CT perfusion with explainable generative adversarial networks. Future Gener. Comput. Syst. 130, 128–139 (2022)
Gao, Z., et al.: Learning physical properties in complex visual scenes: an intelligent machine for perceiving blood flow dynamics from static CT angiography imaging. Neural Netw. 123, 82–93 (2020)
Fantazzini, A., et al.: 3D automatic segmentation of aortic computed tomography angiography combining multi-view 2D convolutional neural networks. Cardiovasc. Eng. Technol. 11(5), 576–586 (2020)
Kovács, T., Cattin, P., Alkadhi, H., Wildermuth, S., Székely, G.: Automatic segmentation of the aortic dissection membrane from 3D CTA images. In: Yang, G.-Z., Jiang, T.Z., Shen, D., Gu, L., Yang, J. (eds.) MIAR 2006. LNCS, vol. 4091, pp. 317–324. Springer, Heidelberg (2006). https://doi.org/10.1007/11812715_40
Cao, L., et al.: Fully automatic segmentation of type B aortic dissection from CTA images enabled by deep learning. Eur. J. Radiol. 121, 108713 (2019)
Chen, D., et al.: Multi-stage learning for segmentation of aortic dissections using a prior aortic anatomy simplification. Med. Image Anal. 69, 101931 (2021)
Pepe, A., et al.: Detection, segmentation, simulation and visualization of aortic dissections: a review. Med. Image Anal. 65, 101773 (2020)
Fu, F., et al.: Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network. Nat. Commun. 11(1), 1–12 (2020)
Raman, R., Napel, S., Beaulieu, C.F., Bain, E.S., Jeffrey Jr., R.B., Rubin, G.D.: Automated generation of curved planar reformations from volume data: method and evaluation. Radiology 223(1), 275–280 (2002)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022(2021)
Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. arXiv preprint arXiv:2201.00520 (2022)
Kirkland, E.J.: Bilinear interpolation. In: Kirkland, E.J. (ed.) Advanced Computing in Electron Microscopy, pp. 261–263. Springer, Boston (2010). https://doi.org/10.1007/978-1-4419-6533-2_12
Lee, T.C., Kashyap, R.L., Chu, C.N.: Building skeleton models via 3-D medial surface axis thinning algorithms. Graph. Models Image Process. 56(6), 462–478 (1994)
Lyu, T., et al.: Dissected aorta segmentation using convolutional neural networks. Comput. Methods Programs Biomed. 211, 106417 (2021)
Deng, X., Zheng, Y., Xu, Y., Xi, X., Li, N., Yin, Y.: Graph cut based automatic aorta segmentation with an adaptive smoothness constraint in 3D abdominal CT images. Neurocomputing 310, 46–58 (2018)
Yu, Y., et al.: A threedimensional deep convolutional neural network for automatic segmentation and diameter measurement of type B aortic dissection. Korean J. Radiol. 22(2), 168–178 (2021)
Cheng, J., Tian, S., Yu, L., Ma, X., Xing, Y.: A deep learning algorithm using contrast-enhanced computed tomography (CT) images for segmentation and rapid automatic detection of aortic dissection. Biomed. Signal Process. Control 62, 102145 (2020)
Acknowledgement
This work is supported by Shenzhen Science and Technology Program (Grant No. GXWD20201231165807008, 20200825113400001), Guangdong Basic and Applied Basic Research Foundation (2022A1515011384), National Natural Science Foundation of China (62101606), Guangdong Natural Science Funds (2020B1515120061), and Natural Science Foundation of Guangdong Province (Grant No. 2020A1515010650).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, W., Liu, H., Gu, L., Gao, Z. (2022). A Geometry-Constrained Deformable Attention Network for Aortic Segmentation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science, vol 13435. Springer, Cham. https://doi.org/10.1007/978-3-031-16443-9_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-16443-9_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16442-2
Online ISBN: 978-3-031-16443-9
eBook Packages: Computer ScienceComputer Science (R0)