Abstract
Patient-specific 3D printing of congenital heart anatomy demands an accurate segmentation of the thin tissue interfaces which characterise these diagnoses. Even when a label set has a high spatial overlap with the ground truth, inaccurate delineation of these interfaces can result in topological errors. These compromise the clinical utility of such models due to the anomalous appearance of defects. CNNs have achieved state-of-the-art performance in segmentation tasks. Whilst data augmentation has often played an important role, we show that conventional image resampling schemes used therein can introduce topological changes in the ground truth labelling of augmented samples. We present a novel pipeline to correct for these changes, using a fast-marching algorithm to enforce the topology of the ground truth labels within their augmented representations. In so doing, we invoke the idea of cardiac contiguous topology to describe an arbitrary combination of congenital heart defects and develop an associated, clinically meaningful metric to measure the topological correctness of segmentations. In a series of five-fold cross-validations, we demonstrate the performance gain produced by this pipeline and the relevance of topological considerations to the segmentation of congenital heart defects. We speculate as to the applicability of this approach to any segmentation task involving morphologically complex targets.
Nick Byrne is funded by a National Institute for Health Research (NIHR), Doctoral Research Fellowship for this research project. This report presents independent research funded by the NIHR. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care. The authors have no conflicts of interest to disclose.
G. Montana and A. P. King—Joint last authors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Those whose binary label value can be flipped without changing the topology of the overall label map.
- 2.
The topology of a well-composed set is independent of neighbourhood connectivity.
- 3.
All results reported as median (interquartile range).
References
Bazin, P.L., Pham, D.L.: Topology correction of segmented medical images using a fast marching algorithm. Comput. Methods Programs Biomed. 88(2), 182–190 (2007)
Li, J., Zhang, R., Shi, L., Wang, D.: Automatic whole-heart segmentation in congenital heart disease using deeply-supervised 3D FCN. In: Zuluaga, M.A., Bhatia, K., Kainz, B., Moghari, M.H., Pace, D.F. (eds.) RAMBO/HVSMR – 2016. LNCS, vol. 10129, pp. 111–118. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52280-7_11
Lösel, P., Heuveline, V.: A GPU based diffusion method for whole-heart and great vessel segmentation. In: Zuluaga, M.A., Bhatia, K., Kainz, B., Moghari, M.H., Pace, D.F. (eds.) RAMBO/HVSMR – 2016. LNCS, vol. 10129, pp. 121–128. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52280-7_12
Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565–571. IEEE (2016)
Pace, D.F., Dalca, A.V., Geva, T., Powell, A.J., Moghari, M.H., Golland, P.: Interactive whole-heart segmentation in congenital heart disease. Med. Image Comput. Comput. Assist. Interv. 9351, 80–88 (2015). https://doi.org/10.1007/978-3-319-24574-4_10
Wolterink, J.M., Leiner, T., Viergever, M.A., Išgum, I.: Dilated convolutional neural networks for cardiovascular MR segmentation in congenital heart disease. In: Zuluaga, M.A., Bhatia, K., Kainz, B., Moghari, M.H., Pace, D.F. (eds.) RAMBO/HVSMR – 2016. LNCS, vol. 10129, pp. 95–102. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52280-7_9
Yu, L., et al.: Automatic 3D cardiovascular MR segmentation with densely-connected volumetric ConvNets. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 287–295. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66185-8_33
Yu, L., Yang, X., Qin, J., Heng, P.-A.: 3D FractalNet: dense volumetric segmentation for cardiovascular MRI volumes. In: Zuluaga, M.A., Bhatia, K., Kainz, B., Moghari, M.H., Pace, D.F. (eds.) RAMBO/HVSMR – 2016. LNCS, vol. 10129, pp. 103–110. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52280-7_10
Zuluaga, M.A., Biffi, B., Taylor, A.M., Schievano, S., Vercauteren, T., Ourselin, S.: Strengths and pitfalls of whole-heart atlas-based segmentation in congenital heart disease patients. In: Zuluaga, M.A., Bhatia, K., Kainz, B., Moghari, M.H., Pace, D.F. (eds.) RAMBO/HVSMR – 2016. LNCS, vol. 10129, pp. 139–146. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52280-7_14
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
Byrne, N., Clough, J.R., Valverde, I., Montana, G., King, A.P. (2019). Topology-Preserving Augmentation for CNN-Based Segmentation of Congenital Heart Defects from 3D Paediatric CMR. In: Wang, Q., et al. Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis. PIPPI SUSI 2019 2019. Lecture Notes in Computer Science(), vol 11798. Springer, Cham. https://doi.org/10.1007/978-3-030-32875-7_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-32875-7_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32874-0
Online ISBN: 978-3-030-32875-7
eBook Packages: Computer ScienceComputer Science (R0)