Abstract
Automatic aortic valve segmentation in cardiac CT scans is of high significance for surgeons’ diagnosis on aortic valve disease and planning of aortic valve-sparing surgery. However, the very fast flapping speed, ambiguous shapes and extremely thin structures of the aortic valve lead to great difficulties in developing automatic segmentation algorithms. In this paper, we proposed an end-to-end deep learning method to address the problem of segmentation of the aortic valve from cardiac CT scans. Our method uses 3D voxel-wise dilated residual network (DRN) as backbone network and we equip it with novel attention-guided decoder modules to suppress non-valve artifacts and noise and pay attention on the fine leaflets in order to acquire accurate valve segmentation results. We conducted qualitative and quantitative analysis to compare with state-of-the-art (SOTA) 3D medical image segmentation models. Experiment results corroborate that the proposed method has very high competence.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Beyersdorf, F., et al.: Current state of the reimplantation technique (DAVID Operation): surgical details and results. HSR Proc. Intensive Care Cardiovasc. Anesth. 4(2), 73 (2012)
Long, J., et al.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)
Bai, W., et al.: Recurrent neural networks for aortic image sequence segmentation with sparse annotations. In: Frangi, A., Schnabel, J., 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
Lalys, F., et al.: Automatic aortic root segmentation and anatomical landmarks detection for TAVI procedure planning. Minim. Invasive Ther. Allied Technol. 28(3), 1–8 (2018). https://doi.org/10.1080/13645706.2018.1488734
Pouch, A.M., et al.: Medially constrained deformable modeling for segmentation of branching medial structures: application to aortic valve segmentation and morphometry. Med. Image Anal. 26(1), 217–231 (2015). https://doi.org/10.1016/j.media.2015.09.003
Khamooshian, A., et al.: Dynamic three-dimensional geometry of the aortic valve apparatus—a feasibility study. J. Cardiothorac. Vasc. Anesth. 31(4), 1290–1300 (2017). https://doi.org/10.1053/j.jvca.2017.03.004
Lin, T.Y., et al.: Feature pyramid networks for object detection. In: CVPR, pp. 2117–2125 (2017)
Yu, F., et al.: Dilated residual networks. In: CVPR, pp. 636–644 (2017)
Roy, A.G., et al.: Concurrent spatial and channel ‘squeeze & excitation’ in fully convolutional networks. In: Frangi, A., Schnabel, J., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. LNCS, vol. 11070, pp. 421–429. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_48
He, K., et al.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Shi, Z., et al.: Bayesian VoxDRN: a probabilistic deep voxelwise dilated residual network for whole heart segmentation from 3D MR images. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11073, pp. 569–577. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00937-3_65
Hu, J., et al.: Squeeze-and-excitation networks. In: CVPR, pp. 7132–7141 (2018)
Wang, P., et al.: Understanding convolution for semantic segmentation. In: WACV, pp. 1451–1460 (2018)
Çiçek, Ö., Abdulkadir, A., Lienkamp, Soeren S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_49
Milletari, F., et al.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV, pp. 565–571 (2016)
Oktay, O., et al.: Attention U-Net: learning where to look for the pancreas. arXiv preprint (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Fan, B. et al. (2019). Attention-Guided Decoder in Dilated Residual Network for Accurate Aortic Valve Segmentation in 3D CT Scans. In: Liao, H., et al. Machine Learning and Medical Engineering for Cardiovascular Health and Intravascular Imaging and Computer Assisted Stenting. MLMECH CVII-STENT 2019 2019. Lecture Notes in Computer Science(), vol 11794. Springer, Cham. https://doi.org/10.1007/978-3-030-33327-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-33327-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33326-3
Online ISBN: 978-3-030-33327-0
eBook Packages: Computer ScienceComputer Science (R0)
